Datasets:

happy8825
/

anet_ret_train_global_rzen_sft_nothinking

Modalities:

Text

Formats:

Size:

Libraries:

Dataset card Data Studio Files Files and versions

xet

Community

Dataset Viewer

Auto-converted to Parquet Duplicate

Split (1)

train · 95 rows

messages listlengths 2 2	videos listlengths 5 5
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A man is shown standing in front of a blue background as many harmonicas are shown and he starts playing them. He is then shown speaking into the camera and going into detail with regards to the products features. He shows off how many he has in his coat and continues talking. He is then shown playing another harmonica as he gives instruction on it. He speaks some more and shows his harmonica again as the video goes to an end title screen that reads Howcast original\".\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [5] > [3] > [1] > [4] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_CB0yYGVNcOk.mp4", "activitynet/videos/v_RULNhPrXnfA.mp4", "activitynet/videos/v_nDbLtdY66dA.mp4", "activitynet/videos/v_oO6jZR9Aijc.mp4", "activitynet/videos/v_PKdQIdYuXo8.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A man uses a large plastic blue bat. He swings it at a pinata shaped like spongebob squarepants. He misses several times, and keeps swinging.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [5] > [2] > [3] > [1] > [4] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_ac1DjqY4xHs.mp4", "activitynet/videos/v_3fg_CB3rBSk.mp4", "activitynet/videos/v_e_X0K2t8API.mp4", "activitynet/videos/v_CCL8kqQMCRw.mp4", "activitynet/videos/v_LFeoVokXAFY.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"Someone is brushing their teeth with an electric toothbrush. They wear braces so they make sure to scrub all around very well. You can see the tongue moving around never really being comfortable inside of the mouth. The man continues to brush, toothpaste spewing down his lips a bit .\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [4] > [2] > [5] > [3] > [1] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_Ktxr4ZiqO3o.mp4", "activitynet/videos/v_8l7SuE4_lCk.mp4", "activitynet/videos/v_Ia3Aa4AO-_E.mp4", "activitynet/videos/v_5kIl4TspdR0.mp4", "activitynet/videos/v_ZW3SKczQzJU.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A man is seen playing a set of bagpipes while people behind him push around bicycles. He is seen playing again while more people walk in and out of frame with children and dogs. Some people stop to hear him play and he stops to look to the camera.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [3] > [4] > [5] > [1] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_UusDcf16TVQ.mp4", "activitynet/videos/v_-G8N5FxjZbw.mp4", "activitynet/videos/v_qmOYKPkURiw.mp4", "activitynet/videos/v_0dgmG3h9RLA.mp4", "activitynet/videos/v_sYAGVE3luRo.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"An unseen person navigates several Amazon dot com pages on exercise equipment. An Amazon page showing an exercise machine alone is shown, followed by another image of a Amazon page showing a woman using an exercise machine along with a price and information about the equipment. Another page showing a eliptical trainer is shown in which an active computer mouse is navigating the review for the item at which point another model elliptical trainer on another page is shown.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [3] > [4] > [5] > [1] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_WElK913B33U.mp4", "activitynet/videos/v_43j1BAyP6Q0.mp4", "activitynet/videos/v_sV6JEbmqDUw.mp4", "activitynet/videos/v_f6NpnKJZJE0.mp4", "activitynet/videos/v_Yr2unlRQZa0.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A woman in a pink shirt is riding a cycle bike. She is then doing push ups on the ground. She does sit ups on the ground.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [4] > [5] > [1] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_x8yuq2i72eo.mp4", "activitynet/videos/v_MGF7I9aCPPM.mp4", "activitynet/videos/v_QxsELAtsSWE.mp4", "activitynet/videos/v_UsexiHSzIQI.mp4", "activitynet/videos/v_BhxKjirVF4Y.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"Two men are standing on the side of the court holding basketball. The men are giving interview, talking to the camera, while one man is talking the other man is listening, then vice versa. The man went to the basket dribble to the ball, the men ran to the basket and shot the ball.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [3] > [1] > [4] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_9029wVyGkvg.mp4", "activitynet/videos/v_eW5W8dVB_I4.mp4", "activitynet/videos/v_UwZbkuVsPno.mp4", "activitynet/videos/v_p8h3G0Tblqc.mp4", "activitynet/videos/v_iYxj8a1TPYk.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A man is seen running down the street holding a box and speaking to another. The man then plays a game with a small girl and bows after each game. The two continue to play with the man laughing at the camera and him giving her a kiss in the end.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [2] > [4] > [5] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_nKnsvy7-wAI.mp4", "activitynet/videos/v_n6A8YtBAJX0.mp4", "activitynet/videos/v_i1llwxnI_Vo.mp4", "activitynet/videos/v_AmW-O5MmJHk.mp4", "activitynet/videos/v_X4IE65LtDzQ.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"The starting list for the men's pole vault event is displayed over the background of the competition area. Multiple vaulters attempt to vault, one after another, some successfully and some not. The camera cuts to a man wiping his face with a towel, then a quick shot of the last vault attempt, then a quick shot of another man walking away from the camera. Another man in white and blue vaults and is successful. The camera cuts to four other competitors watching. The camera cuts to a man in white and blue celebrating while holding a flag against his black. The man who celebrated is being interviewed. A different competitor, wearing red, is being interviewed.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [4] > [5] > [3] > [2] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_pjF6uBZHVRE.mp4", "activitynet/videos/v_GXEuuWhEMCY.mp4", "activitynet/videos/v_nmUJ2GfVkKY.mp4", "activitynet/videos/v_RQO61KXeBos.mp4", "activitynet/videos/v_OH5UXwa3F7E.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A woman is sitting at a table using a hookah while another woman makes silly faces and gestures behind her. They speak animatedly with the person behind the camera. There is a close up of the items on the table in front of them. The woman with the camera turns it to face herself before aiming it back toward the other women. One of the women coughs as a cloud of smoke hits her in the face.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [3] > [5] > [4] > [2] > [1] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_1D7iddqIIhM.mp4", "activitynet/videos/v_lgWH94ea3-U.mp4", "activitynet/videos/v_oEd7WT4mVSE.mp4", "activitynet/videos/v_SbX8KDWMhio.mp4", "activitynet/videos/v_Vbkq1ldn3A8.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"woman is walking wearing a bikini and eating a chocolate is snowy day. people are in sidewalk watching the girl walks. woman is in a restaurant wearing a bikini and two aiter are watching her. woman walks in a airport eating a restaurant.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [5] > [1] > [3] > [4] > [2] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_ITGlho0dw-k.mp4", "activitynet/videos/v_fruimvo90vA.mp4", "activitynet/videos/v_YPXeQVi39nU.mp4", "activitynet/videos/v_EHVkkRI7mBQ.mp4", "activitynet/videos/v_jUPbimyUndA.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A large group of people are at a carnival playing in their own bumper cars and a few of them bump into one another and come to a stop. They laugh and begin to pull their bumper cars away from one another. The people start driving around again where they all continue to either bump into one another or just drive around. Eventually all the bumper cars come to a complete stop and the ride is over.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [3] > [1] > [4] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_tQ9yPS_BJHQ.mp4", "activitynet/videos/v_bX8QXK9mjKA.mp4", "activitynet/videos/v_SiqB6_9kNQU.mp4", "activitynet/videos/v_Fp8e9dbWeSg.mp4", "activitynet/videos/v_jx7_0MRlScw.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A boy in an orange shirt is standing in a room. He starts punching a punching bag. The punching bag moves in the air.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [5] > [2] > [1] > [3] > [4] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_tilmCzSf1oc.mp4", "activitynet/videos/v_fQDj7pnGdVY.mp4", "activitynet/videos/v_-NndIs9BaS4.mp4", "activitynet/videos/v_4E40jmmc2N8.mp4", "activitynet/videos/v_gU81ZXdYh7o.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A woman is sitting down wearing green sunglasses. She is talking on the cell phone. She is riding in a car. She is laying on a chair getting her foot tattooed. She is showing her foot tattoo. She is sitting outside talking again.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [1] > [5] > [4] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_AyYpsQ4xOo8.mp4", "activitynet/videos/v_kWPvAxLzGw8.mp4", "activitynet/videos/v_-8FS4LbXAgE.mp4", "activitynet/videos/v_vgO3mzJGbSI.mp4", "activitynet/videos/v_PtoVL69LEh4.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A boy on a team throws a basketball at other team members. Others join in, some falling as they are hit with the ball.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [2] > [3] > [4] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_PLgcXxX3A2A.mp4", "activitynet/videos/v_wvlyV067oOU.mp4", "activitynet/videos/v_pHZogKGkc9o.mp4", "activitynet/videos/v_UySzNwvkQKQ.mp4", "activitynet/videos/v_B7Q1egUKmZg.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"Two young men are shown running back and fourth down a court hitting a tennis ball. They keep hitting the ball against the wall and chasing the ball around. One pauses and hits the ball on his racket and again throws it for the boys to play. One falls down on the ground towards the end and the other helps him up.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [4] > [5] > [2] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_rggwT0-G5sk.mp4", "activitynet/videos/v_P3BkKdkf43I.mp4", "activitynet/videos/v_q6bl7g5JGng.mp4", "activitynet/videos/v_jIYRVlrXJgc.mp4", "activitynet/videos/v_aWz9H0jTv3c.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A young girl is seen sitting in a chair with a person standing next to her. The person next to her then piercing one ear followed by the other. The person rubs lotion on the piercings afterwards.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [3] > [2] > [4] > [5] > [1] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_KCxa27MM7Cg.mp4", "activitynet/videos/v_yyvc2OSPx1Y.mp4", "activitynet/videos/v_69IsHpmRyfk.mp4", "activitynet/videos/v_Jbl0E75cx8o.mp4", "activitynet/videos/v_PQgydNnSggw.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A man in a suit is sitting behind a desk. People are playing lacrosse on a field of grass. A person in a yellow uniform is standing in front of a net blocking balls.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [3] > [1] > [4] > [2] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_xww6n1FoJIM.mp4", "activitynet/videos/v_agZNSscDJww.mp4", "activitynet/videos/v_t0ajvfx6dgA.mp4", "activitynet/videos/v_sJUUm0n4cXA.mp4", "activitynet/videos/v_XazKuBawFCM.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A man was sitting inside a room. He is holding a bowl of noodles and broth. He is drinking the broth from a bowl.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [4] > [1] > [5] > [2] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_AR-VPPtV7ag.mp4", "activitynet/videos/v_jNGa0jPAMjI.mp4", "activitynet/videos/v_G9m5zxl2f08.mp4", "activitynet/videos/v_---9CpRcKoU.mp4", "activitynet/videos/v_Gd6YooP1_CU.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A person is holding a flute. The person shows a fingering for the second octave of the note. The person shows the fingering on the third octave. The woman talks directly to the camera.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [1] > [4] > [3] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_P6ijX0vabJs.mp4", "activitynet/videos/v_p9iE8iemCMs.mp4", "activitynet/videos/v_f5xSylPY_bQ.mp4", "activitynet/videos/v_J6ScF5n_Cug.mp4", "activitynet/videos/v_oTKYejnHLtE.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"Three girls are on the beach talking. They do several flips on the beach. They lift one of the girls up for a stunt.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [3] > [5] > [4] > [2] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_4x7HYKV8zkY.mp4", "activitynet/videos/v_w8LDUu66JWI.mp4", "activitynet/videos/v_II0BlR0BriI.mp4", "activitynet/videos/v_6-P9SRNbwac.mp4", "activitynet/videos/v_3Edxa-t4MxA.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"The camera pans above lush and green terrain over what looks like a mountain range. A man is shown covered in sweat and then jumping across various hills performing stunts on a dirt bike. He rotates and flips and performs all sorts of acrobatics. He is highly skilled and jumping over everything. The video then shows multiple men on dirt bikes jumping in various different places and shows the action from a variety of angles. The men continue performing their stuns in various other landscapes.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [4] > [5] > [3] > [2] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v__Af_9cK5x4E.mp4", "activitynet/videos/v_KCOzA0Suy5U.mp4", "activitynet/videos/v_QtCNHRtycmg.mp4", "activitynet/videos/v_p6jip892RdM.mp4", "activitynet/videos/v_v-dxQNxdMrU.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"Athletes throw a javelin during a competition. A man practices his throwing stance walking and doing half throws without javeline. A man practices his throwing stance walking and doing half throws holding a javeline. The man swings a hammer. The man throws a weighted ball. Athletes train in a gym doing throwing motions on weighted cable machines.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [3] > [1] > [4] > [2] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_GKK32IWDlSE.mp4", "activitynet/videos/v_uBhuULfs3Hc.mp4", "activitynet/videos/v_HxJnPUqF9i8.mp4", "activitynet/videos/v_aEUbl9oT_0s.mp4", "activitynet/videos/v_zLF5DSuDixg.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A man is giving advice on outdoor activities, specifically mushrooming and closeup is shown and the man talks about it. The man cuts one open and then cuts it in half. Another man talks about the experience.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [1] > [4] > [3] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_1LrEiYVd3qg.mp4", "activitynet/videos/v_UYHgieL5IKM.mp4", "activitynet/videos/v_rHWOESWciSc.mp4", "activitynet/videos/v_SIeV0DPSpHQ.mp4", "activitynet/videos/v_c-3ed17J3F8.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A young child is seen sitting behind a drum set playing the drums. The boy continues playing the instrument while the camera zooms in on him playing.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [3] > [4] > [1] > [5] > [2] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_90LkAH4tZC4.mp4", "activitynet/videos/v_ItFq_6cIByw.mp4", "activitynet/videos/v_nvsK9ggeics.mp4", "activitynet/videos/v_q3-S2tg4ULw.mp4", "activitynet/videos/v_FMUaey1tigI.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"The video begins with a title sequence. A young man is shown in a gym performing tricks with a jump rope as music plays in the background. He then lays down and begins doing tricks on the floor. The young man gets up again and does more tricks while standing. At one point, his friends assist with the jump rope tricks. The video ends with credits showing the young man's name, along with the names of those who assisted him.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [4] > [2] > [1] > [5] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_ABB755sPZfY.mp4", "activitynet/videos/v_MlbM7Mew0Ys.mp4", "activitynet/videos/v_A0F6uT95xhA.mp4", "activitynet/videos/v_y7WO-8cQfO0.mp4", "activitynet/videos/v_Zhfm2dWtnpc.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A lady is seen putting wax on a mans shoes. We see the cloth hanging on the wall. We see the footprints on the platform. The woman rubs the mans shoes with a cloth. We see the cloth on the wall, then the lines of cloth near the shoes shine sign. A man is standing on a platform. We see the holographic man on the wall with the paper.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [3] > [5] > [2] > [1] > [4] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_nEcOF04KK0g.mp4", "activitynet/videos/v_r34VM4v0ShI.mp4", "activitynet/videos/v_74EoyLUbtgI.mp4", "activitynet/videos/v_UsqhZb0co6o.mp4", "activitynet/videos/v_1OJa2iiFxfk.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"Two girls stand between a girl in a hair salon stool and begin brushing her and parting her hair. One woman braids her hair continuously to eventually create a french braid. Both women stand talking to the camera while presenting the braid just made.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [4] > [5] > [1] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_Tovbyt_ZiIc.mp4", "activitynet/videos/v_WY9zvUkK_4Y.mp4", "activitynet/videos/v_4b2_OpAGwW0.mp4", "activitynet/videos/v_cS19K2310Lc.mp4", "activitynet/videos/v_1FMjfLRpXwM.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A man sits in a chair as he is getting his hair cut. A man in a black shirt moves a light around. People scramble behind the hair stylist. A hair stylist continuously combs and cuts the man's hair. The hair stylists rubs some pomade on the man's hair. The man is seen posing.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [5] > [4] > [3] > [1] > [2] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_7_5VT6QCqNI.mp4", "activitynet/videos/v_04LdesS7Pxk.mp4", "activitynet/videos/v_wr2FC2P3hIs.mp4", "activitynet/videos/v_g-Egl6eXlX4.mp4", "activitynet/videos/v_JgHQCKz_DRc.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A group of people are on a field. They attach a camera to one of the player's heads. They lift each other over their heads in cheerleading stunts that can be seen from the camera's view. They smile and laugh as they continue to perform stunts.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [5] > [3] > [4] > [2] > [1] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_DbF6oI705UA.mp4", "activitynet/videos/v_vPhAXENSjiw.mp4", "activitynet/videos/v_BSl22Hx2WGM.mp4", "activitynet/videos/v_d0h_l9bE1o0.mp4", "activitynet/videos/v_Vjsd6Ec6eKA.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"Music plays as surfers ride the waves. A few men are shown preparing to surf, prepping their board and getting dressed. A helicopter rides over the shoreline where the surfers are riding. A couple laughs together on the beach in a tent awaiting more surfing. A man is then shown prepping his board with surf wax. The crowd watches others riding waves. The crowd cheers multiples surfing runs on. Kelly Slater is featured on a successful run, followed by more clips riding the waves. Kelly Slater is paused mid wave to wrap up the story line. Music and producer credits are then shown.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [3] > [1] > [2] > [4] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_ANB_IQfi9kA.mp4", "activitynet/videos/v_O9crPOB_9tE.mp4", "activitynet/videos/v_QdmUojrWdmE.mp4", "activitynet/videos/v_r0P0egQt-jU.mp4", "activitynet/videos/v_DHWmzuAWxLM.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A girl is seen talking to the camera with her hand on her hip and leads into her holding up various ingredients. She then mixes the ingredients together on a slice of bread and creates a sandwich while pouring chips out onto the side. She then presents the plate while speaking to the camera and holding up various liquids.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [4] > [3] > [5] > [1] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_78UikTQkGgg.mp4", "activitynet/videos/v_KE2tDW9x9d8.mp4", "activitynet/videos/v_LlI1IJEkW5E.mp4", "activitynet/videos/v_GtYf9VsPHO0.mp4", "activitynet/videos/v_GaxyzK2mHqw.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A boy surfs in a big wave. A group of people lye down on surfboards in a wave. Suddenly, a boy stands an surf below the wave. Men stand in the beach holding surfboards.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [1] > [5] > [4] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_O0uVjGlOW8M.mp4", "activitynet/videos/v_B3ZVUyLeT84.mp4", "activitynet/videos/v_ThRbaI4pGIs.mp4", "activitynet/videos/v_yrf93aLQXBE.mp4", "activitynet/videos/v_sVeC5VlDsjk.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A girl with several facial piercings his seen rubbing lotion all over her face and powdering her cheeks and face. She then puts eyeliner on followed by mascara and lip liner. She colors in her eyebrows and puts on fake eye lashes, then rubbing some of the black off and more mascara on. She puts a bit of blush in her cheeks and then smiles and waves to the camera.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [3] > [1] > [4] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_4WNso9fVJG8.mp4", "activitynet/videos/v_QeVVKZhoFCg.mp4", "activitynet/videos/v_avGe67wRvxA.mp4", "activitynet/videos/v_3ddoLUFrGsE.mp4", "activitynet/videos/v_RA61jh8HwPI.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A woman is standing by a toilet in a bikini. A man is rubbing sunscreen onto her legs. She begins to rub her leg.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [5] > [3] > [2] > [4] > [1] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_6h-WE-0eBlA.mp4", "activitynet/videos/v_OoyoTLkSOuY.mp4", "activitynet/videos/v_MY6o5ZObFLE.mp4", "activitynet/videos/v_HeHQxObROwQ.mp4", "activitynet/videos/v_wBhtt9x74TA.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A woman is seen speaking to the camera while holding up various objects. The puts tape on he eye and begins putting eyeliner above her eye. She continues putting the makeup on while speaking to the camera and takes off the tape in the end.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [4] > [3] > [2] > [1] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_Ie7DREiXp08.mp4", "activitynet/videos/v_aSPPD0fDI3g.mp4", "activitynet/videos/v_InA8Xbg-hvo.mp4", "activitynet/videos/v_f-aGlEjgZoE.mp4", "activitynet/videos/v_extd66Y1tJ8.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A man is seen standing in a field with a dog while holding onto toys. The man then begins throwing the toys while the dog chases after them. The men continues to do tricks with the dog and end with a picture.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [5] > [1] > [4] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_lMbDEY-CVwE.mp4", "activitynet/videos/v_UhB739uudDo.mp4", "activitynet/videos/v_eLeGJBfqURA.mp4", "activitynet/videos/v_KoeytdNfQ_M.mp4", "activitynet/videos/v_Yd98o-oEGvI.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A group of men are in a kayak going down the river bank. The are paddling and looking at the trees in the distance enjoying their day. One of the men gets out of the boat to go swimming in the water, They all get in and start splashing water, swimming under and enjoying the day before getting back in to turn back. Once they start to head back to land and to get ready to get on the dock.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [3] > [1] > [2] > [5] > [4] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_F_sbhegCsyg.mp4", "activitynet/videos/v_AXA-G5DdNrU.mp4", "activitynet/videos/v_djgM0IWIBKc.mp4", "activitynet/videos/v_KxWvKN_kGMY.mp4", "activitynet/videos/v_i69NhEDno_M.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A man wearing a black clothes is sharpening the knife on a stone. The man beside him on blue long sleeves drawing something on the table with his finger. The man turn the knife to sharpen the other side and then wipe it with paper towel. The man in navy blue shirt point to the knife while the man sharpening the knife tries to sharpen it one hand. He continues sharpening the knife, turn it again to further sharpen the other side and wipe it again with paper towel. Throws the old and dirty paper towel and reach the roll of paper towel and clean the knife.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [5] > [2] > [4] > [1] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_Anvhv9FFv1Q.mp4", "activitynet/videos/v_dtvIQ9Pd-Bg.mp4", "activitynet/videos/v_WLpjci5dN8s.mp4", "activitynet/videos/v_UzdI8PLRiXg.mp4", "activitynet/videos/v_E3h0UHRsSQk.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"An intro leads into a woman pulling out a bucket and piecing together a mop. The camera pans around the bucket and the woman continues using the mop inside the bucket and moving around the object.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [4] > [3] > [5] > [2] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_MSjSXzk2k50.mp4", "activitynet/videos/v_B8WIh6PUjE0.mp4", "activitynet/videos/v_E0DbrJVJUho.mp4", "activitynet/videos/v_IkXuooaGnCc.mp4", "activitynet/videos/v_Kq115s7yL3I.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A close up of a wooden bench is seen followed by a person mixing ingredients together. A person is then seen holding a rag and wiping down the bench. More ingredients are mixed afterwards that leads into more wiping down with the rag.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [1] > [3] > [5] > [4] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_1ATBCBUgflA.mp4", "activitynet/videos/v_MiTIi_QYt2k.mp4", "activitynet/videos/v_yOKDaH8Go0A.mp4", "activitynet/videos/v_pn1XDTlNMso.mp4", "activitynet/videos/v_0fw8it7Gj7k.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"Men play badminton in the sand. A man on the left serves the birdie both men on the right miss it. the man on the right serves and the man on the left hits it back but it hits the net. A man stands on the left watching.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [4] > [1] > [3] > [5] > [2] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_MO8Dfz2Lp3w.mp4", "activitynet/videos/v_vlwOSDuiKQA.mp4", "activitynet/videos/v_TnYCazY5WEM.mp4", "activitynet/videos/v_95pMelnv2dQ.mp4", "activitynet/videos/v_ZWHFbIjh0N8.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A class of kids are at outside at school dressed in uniforms with their teacher standing next to them. As they are in line,one girl is in the middle of a game of hop scotch,turns around,finishes and gets back in line. Once she is finishes,all of the other kids takes their turn one by one.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [2] > [3] > [4] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_Fk0z6MeCV0I.mp4", "activitynet/videos/v_l8NepxsCh34.mp4", "activitynet/videos/v_dZ4y7J3ASEE.mp4", "activitynet/videos/v_pieT6K771WQ.mp4", "activitynet/videos/v_yW76UI8lnNc.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A large group of cheerleaders are seen running into an arena cheering and beginning performing a routine with one another. The girls continue cheering around the stage while lifting one another up and performing tricks and pans to the audience in the end.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [5] > [4] > [2] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_O4P07fipvIA.mp4", "activitynet/videos/v_DEmArEKL8gc.mp4", "activitynet/videos/v_mRe2xY_amWw.mp4", "activitynet/videos/v_fZ_CmvF-_No.mp4", "activitynet/videos/v_opAcl-kukdU.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"Two kids are climbing a rock wall. The adults are guiding the lines. The kids continue to climb. The one on the right will make it to the top first. The one on the left did not make it to the top, both hop back down the wall.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [2] > [5] > [4] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_XHMrvd3sKzE.mp4", "activitynet/videos/v_jVM8v6uJx8c.mp4", "activitynet/videos/v_s9Wop4PMZaw.mp4", "activitynet/videos/v_etfSrbmOvUE.mp4", "activitynet/videos/v_q4rVY3sLQqA.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A man walks up to a snow scoop. The man shovels the snow on a roof while the cameraman talks. The man stops scooping the snow.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [1] > [4] > [5] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_Yg6jFRYIyXw.mp4", "activitynet/videos/v_ffyPN2-EDg4.mp4", "activitynet/videos/v_yslzj3NGuLU.mp4", "activitynet/videos/v_Zl6o69-R2DE.mp4", "activitynet/videos/v_NDWJOqVUGeA.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A girl is sitting on a large chair with two girls beside her and a man tattooing her foot. Another man steps into frame and the girls continue talking to each other while the artist.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [5] > [2] > [3] > [4] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_K-r_Tj7uFGw.mp4", "activitynet/videos/v_JzLqc6MhJtc.mp4", "activitynet/videos/v_AyYpsQ4xOo8.mp4", "activitynet/videos/v_ZazjI26IQUo.mp4", "activitynet/videos/v_-tv6laq1ic0.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A woman behind a bar is showing how to make a mixed drink. A series of shots appear with a person pouring alcohol into a martini glass and then the screen fades into the video title screen showing a website name, the name of the drink they are making and the person who will be making it. A website address is shown at the bottom of the screen. A girl standing behind the bar explains what ingredients she is using for the drink, the amounts she is using, and mixes them all together in a glass and presents the drink. The camera zooms in on the drink and fades to black to end the video.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [4] > [3] > [2] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_TOfBNYOlv8c.mp4", "activitynet/videos/v_Rl6US0JizDs.mp4", "activitynet/videos/v_qOi_E_uYCIo.mp4", "activitynet/videos/v_83a5nOzZU1g.mp4", "activitynet/videos/v_sZf6ijFwPDs.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"Two gymasts are performing in front of a crowd. One is spinning constantly on a beam. The man in red mounts and begins to spin, performing several tricks. The man dismounts, and puts one victorious arm up into the air.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [2] > [3] > [4] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_21krmbuT21s.mp4", "activitynet/videos/v_5kBKAfEX7XA.mp4", "activitynet/videos/v_XuSWH1lfcvI.mp4", "activitynet/videos/v_zLVNSgR4IoA.mp4", "activitynet/videos/v_Le6fNx5IWRI.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A group of men are standing on a diving board and they take terms jumping off of the diving board. As the last person jumps off the board,a group of men are shown walking across the pool.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [5] > [1] > [2] > [4] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_gGg-kio0dmU.mp4", "activitynet/videos/v_Tu1oKxyfHTs.mp4", "activitynet/videos/v_mnS-nMZne3I.mp4", "activitynet/videos/v_vcE8e-fQBhs.mp4", "activitynet/videos/v_3TbZ7uSYUe8.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A close up of a globe is shown with a person pointing a hookah at it. The man is then seen looking closely to the camera. He finally blows smoke rings out of his mouth.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [2] > [3] > [4] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_xld0M1MXNiE.mp4", "activitynet/videos/v_jqRJM8b4pgE.mp4", "activitynet/videos/v_NLkJgnrKaKM.mp4", "activitynet/videos/v_2L9pp85KvbQ.mp4", "activitynet/videos/v_lCuMD23jOxo.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A young girl is seen standing on a tennis court holding a racket. The woman begins swinging the racket while another boy stands beside her. The woman continues swinging and walks back to the boy.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [1] > [4] > [5] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_w6Avae5on_0.mp4", "activitynet/videos/v_hsJJbTqSQR4.mp4", "activitynet/videos/v_f-4PjtdFbP4.mp4", "activitynet/videos/v_vrMWYB0UuGM.mp4", "activitynet/videos/v_eQMT-WmxKM8.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"Several men are playing soccer in a gym. There are some spectators in the background. Another group of men are playing soccer. There are spectators in the background. Various scenes of soccer matches are shown with spectators.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [2] > [5] > [4] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_w-6Oo3bgms4.mp4", "activitynet/videos/v_bMDyOXygNPM.mp4", "activitynet/videos/v_cCISvaObBxI.mp4", "activitynet/videos/v_5qublDzEgsw.mp4", "activitynet/videos/v_wlYxVUJSJVI.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"Cake chemistry explaining how to do a at home experiment, They give all the ingredients needed and begin to explain what they will be doing. The start to give step by step instructions on how to mix the ingredients together. They give very detailed information about what to do before putting them in the oven. Once, they come out of the oven they explain the difference between all of the cakes and the different ingredients they did not put in each to see why the results were different.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [4] > [2] > [5] > [3] > [1] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_oNc2lJ9hV9E.mp4", "activitynet/videos/v_1f_EQl4C700.mp4", "activitynet/videos/v_XCwPsQwzfiA.mp4", "activitynet/videos/v_MBouLt-hXDU.mp4", "activitynet/videos/v_2PCZkpF1_wU.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A person in blue pants is raking some fallen leaves from the ground. There is a black dog and a white dog jumping around the person raking the leaves. The white dog is trying to bite off the rake. Both the dogs are playing around the man raking the leaves, trying to bite the rake. The person is moving the rake in circles as the dogs are jumping around him.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [5] > [3] > [2] > [1] > [4] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_a2Xwx37YbhE.mp4", "activitynet/videos/v_08wKlw4a_so.mp4", "activitynet/videos/v_aBr9bdWrl0I.mp4", "activitynet/videos/v_k5vE0ehf5TA.mp4", "activitynet/videos/v_0MtST08F2Xc.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A person is seen running along the road wearing equipment and speaking to the camera. The man runs around using strings as well as speaking to the camera. The man continues speaking while more shots are shown of him running.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [4] > [1] > [2] > [3] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_fXgszraP2tc.mp4", "activitynet/videos/v_qZTAv1s_eBQ.mp4", "activitynet/videos/v_aKhD_bFB7MA.mp4", "activitynet/videos/v_ffWMjZCysO0.mp4", "activitynet/videos/v_hFtmkU7wdx4.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A pinata hangs from a tree, as a group of girls stand in front of it. One has a stick and is blindfolded. She hits the pinata, then walks away.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [3] > [1] > [5] > [2] > [4] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_WJ4tCIdAgVo.mp4", "activitynet/videos/v_ibHRKaD5MbM.mp4", "activitynet/videos/v_tjuYS-6UC_M.mp4", "activitynet/videos/v_RgeVltfPDXQ.mp4", "activitynet/videos/v_T98RJsOiQWc.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"a man is seated, talking to a talk show host. They are animated as they speak to one another. They continue talking, then the host presents the man with a gift.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [1] > [5] > [4] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_0jvbBtMIA8k.mp4", "activitynet/videos/v_NnEUVHhtLZs.mp4", "activitynet/videos/v_sS1Zh8mqMOE.mp4", "activitynet/videos/v_86sxvTk3YEY.mp4", "activitynet/videos/v_RJpWgi0EaUE.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"An intro starts and begins showing a group of people. Various people perform a dance routine together with an instructor performing front and center. The routine continues with the people and instructor moving around with their arms and legs doing various movements to music.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [2] > [5] > [4] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_zDPsJ3ECaTI.mp4", "activitynet/videos/v_Z3bPr9odxpw.mp4", "activitynet/videos/v_h3uTJ7HknzA.mp4", "activitynet/videos/v_jLwUrFMRGzY.mp4", "activitynet/videos/v_8EGM3zcvjs8.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A female news anchor introduces a story. A female news reporter speaks to a fitness instructor inside a gym, where cyclists are riding fitness bikes. Exercises such as yoga and bicycling are demonstrated by those in the gym. The female news reporter continues talking to the fitness instructor. She speaks to the anchor back in the studio.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [2] > [5] > [4] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_QxsELAtsSWE.mp4", "activitynet/videos/v_nGsRDNIsc2o.mp4", "activitynet/videos/v_ClE77VhGQsk.mp4", "activitynet/videos/v_jwOZsKS25oc.mp4", "activitynet/videos/v_tgPjcWP7Vig.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A game of volleyball is being played between blue and yellow team. The yellow team servies the ball and it is hit continually back and forth until the yellow team scores a point. A player on the yellow team falls and the players on each team assist her. They take her shoe and sock off and massage her leg. Two people proceed to pick her up with the help of a third and take her off the court and lay her down to the side to continue care.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [3] > [4] > [5] > [2] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_3gsF785TAmg.mp4", "activitynet/videos/v_RZqM8Z0ocjE.mp4", "activitynet/videos/v_tl2hDYGBfqU.mp4", "activitynet/videos/v_k67UWfSt-iE.mp4", "activitynet/videos/v_D8dHEAYIawg.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"We see an opening screen and a man runs and does a high jump at fifteen feet. We see a man jump the high jump on a track at various height with lots of cut scenes. We see seventeen and a still of the man. We see fifteen nine scroll across the screen. We see a series of still of the man and sixteen six. Seventeen two scrolls across the screen. We see seventeen nine scroll across the screen. We then see the ending credits.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [2] > [4] > [3] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_OH5UXwa3F7E.mp4", "activitynet/videos/v_VCg6_fuipp8.mp4", "activitynet/videos/v_tJLm2D4J3X0.mp4", "activitynet/videos/v_R3ffxWaI9QU.mp4", "activitynet/videos/v_VM-ldOw7e4Y.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A cheer-leading team begins to hold up posters as their mascot runs behind them. They then begin to do a routine and some of the girls run with streamers as the rest of them hold up the girls for their stunt. The stunt is finished and the retreat back to their original position and begin doing cartwheels and other tricks and stunts along with their mascot. As the routine continues,more stunts are performed and the Tiger mascot continues to cheer with the girls.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [4] > [3] > [1] > [2] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_iaqFvTpoceI.mp4", "activitynet/videos/v_fZ_CmvF-_No.mp4", "activitynet/videos/v_IC61TQ-sd8o.mp4", "activitynet/videos/v_1fF1OQtpctg.mp4", "activitynet/videos/v_4-Xe_9Ywvd8.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"Alexandra Raisman from Massachusetts is seen wearing purple leotards, getting ready to do gymnastics on the horse bar. She jumps right onto the horse bar and does some front and back flips. Then she does some back hand springs on the horse bar. she swiftly jumps on the horse bar while maintaining complete control over body and balance. She does a final back flip and a front flip and then, gets off the horse bar. The spectators cheer for her as she walks away.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [3] > [5] > [4] > [2] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_62h9hnNTKWM.mp4", "activitynet/videos/v_xYM6h31PrM0.mp4", "activitynet/videos/v_56sQMnSUWaI.mp4", "activitynet/videos/v_bRVazNYfpGE.mp4", "activitynet/videos/v_sByOncVAMqg.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A news man is speaking in front of a group of people. A man is shown on a diving board high atop a cliff. He dives, jumping into the shallow waters below.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [5] > [1] > [4] > [2] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_-y5p8UMdM20.mp4", "activitynet/videos/v_YmAIoN4uuz0.mp4", "activitynet/videos/v_wfc_R5VnoHU.mp4", "activitynet/videos/v_L5nqeFWufrE.mp4", "activitynet/videos/v_4innF37ifyY.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"We see a GoPro opening screen. We see a lady walking with a raft into a river. We see people riding rafts in the river. We see a mans's legs and the lady rides past. We see the lady handing a beverage in a can to the cameraman. The cameraman goes under a branch that is across the water. We then see the GoPro ending scene.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [5] > [1] > [2] > [3] > [4] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_EmlmKZ6Gi3Y.mp4", "activitynet/videos/v_8olnQLX0hO8.mp4", "activitynet/videos/v_r40TuTkt9y4.mp4", "activitynet/videos/v_hrN0hOmQrD4.mp4", "activitynet/videos/v_KpOSIph2hHw.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A woman holds the back section of a girls hair while she gets ready to style it. The woman uses a single pick comb to separate strands of hair. The woman clips back sections of hair. The woman pulls on strands of hairs to get them straightened out. The woman braids them the strands of hair together.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [2] > [4] > [3] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_YZJghuPmff8.mp4", "activitynet/videos/v_uLT7PmD_AJA.mp4", "activitynet/videos/v_fM4pJeHb8hQ.mp4", "activitynet/videos/v_xbWAmySRE88.mp4", "activitynet/videos/v_H-hgVm5G54Y.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A news segment begins and black and white picture of a smiling girl appears on the screen and the banner on the screen says \"HENRICO TEEN DIES AFTER RACE FATHER RECOUNTS DAUGHTER'S FINAL MOMENTS\". The newscaster appears with her parents talking about the girl while clips of the race play, and still shot pictures of the girl appear on the camera. When the pictures and video clips of the interview and race are over, the newscaster is speaking alone back at the news station.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [3] > [2] > [4] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_hMUoeOFmquI.mp4", "activitynet/videos/v_QRcwvzq7QUM.mp4", "activitynet/videos/v_fOGXvBAmTsY.mp4", "activitynet/videos/v_MXN34b2OUjQ.mp4", "activitynet/videos/v_WBkqGBFsdgI.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A close up of ballet shoes are shown followed by a woman putting them on and moving around in a bedroom. She moves her arms and feet in the point shoes and whips her hair all around the room.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [3] > [2] > [4] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_feio1hW6Dy0.mp4", "activitynet/videos/v_7ftCKS5SCCk.mp4", "activitynet/videos/v_ifDsS6ZRsRM.mp4", "activitynet/videos/v_hru57dsi0N0.mp4", "activitynet/videos/v_iJzt1rvGiOc.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A ballerina is shown in class warming up her feet and walking away crying. Various actors talk to the camera about filming a movie about ballet and the moves they learned. The ballerinas are moving around the set while the camera is rolling. The actors continue talking about tricks and what they learned. A man plays the violin while the final scene is filmed and everyone is dancing.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [3] > [4] > [2] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v__ekWWP0dQZM.mp4", "activitynet/videos/v_9XanCE5nX2Q.mp4", "activitynet/videos/v_li16LYa7us8.mp4", "activitynet/videos/v_-5Yp-vToI2E.mp4", "activitynet/videos/v_aAlbRFeu32E.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A woman is seen shaving down the fur of a dog while the camera shows many dogs sitting in crates. A woman is seen speaking to the camera and showing off several dogs with long hair and afterwards. The woman continues shaving down the sides of the dog while stopping to speak to the camera and showing off the shaved dog.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [1] > [4] > [3] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_p8C7govzEPw.mp4", "activitynet/videos/v_dSsMVoPLQOk.mp4", "activitynet/videos/v_2fp9Ni7Ms6A.mp4", "activitynet/videos/v_u4nL6NXfsak.mp4", "activitynet/videos/v_63Zt34YuyRk.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"Ladies are standing in a workout room. The ladies are belly dancing. The ladies dip down and toss their hair backwards. They swing their dipped bodies. The ladies dip and bend backwards. The ladies throw their hair back and forth. 2:43 A man is in the room in the back and bends down. The ladies finish dancing and take a bow.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [4] > [2] > [1] > [5] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_QQQ7jSVSG3A.mp4", "activitynet/videos/v_PxEu0AAH9LI.mp4", "activitynet/videos/v_KPv8ZGrb78Y.mp4", "activitynet/videos/v_HVfr9FnEj-Q.mp4", "activitynet/videos/v_nY8a1E4QH5Q.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"Cotton balls are being set on fire and put out in various ways. An ax is used to put out the fire. A piece of wood is used to put out the fire.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [4] > [5] > [3] > [1] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_wQbVxdVTN-I.mp4", "activitynet/videos/v_2kx--bbqXHg.mp4", "activitynet/videos/v_O337_rGYZPc.mp4", "activitynet/videos/v_Lg6QZST92xo.mp4", "activitynet/videos/v_3jb0w48ACkU.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A woman wash the head of a man and cuts his hair, then the woman stands next two man an touch the head of the young man. The woman cuts the hair of a young man using first a machine, and then a comb and scissors. Then, the woman dry the hair with a dryer and brush the head. After, the woman takes cream on her hands and comb the head of the man with her fingers to gives form to the hair. Next, the woman explains the hairstyle.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [2] > [3] > [4] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_lHy_OZ8GygM.mp4", "activitynet/videos/v_ZYAY3TEUjGI.mp4", "activitynet/videos/v_TT2e7-NbUxo.mp4", "activitynet/videos/v_hPQEkPZmNsU.mp4", "activitynet/videos/v_h9YbUJuYzLk.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"Two men plays foosball in an arena with two referees standing near by watching the fame. We see the bleacher an spectators. A point is scored and see people clapping and a replay and a title screen. The man in gray backs up and wipes sweat. We see the man in black speaking with the people behind him before the men return to the game. We see the ending title screen.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [5] > [1] > [4] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_ahOnhEvMgq0.mp4", "activitynet/videos/v_0j9TxzwRr6E.mp4", "activitynet/videos/v_W34A9wUi-4g.mp4", "activitynet/videos/v_hJn5L1nrkL4.mp4", "activitynet/videos/v_cvatsuUhqhk.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"There are two men playing table tennis in an indoor stadium. One of the players is wearing blue and the other player is in a red shirt. There is a person dressed in a black shirt seated near the players. There are several spectators seated in the stadium. They continue playing a rally for some time. The player in the red shirt misses the ball and gives his opponent a winning point. The player in blue cheers loudly after his winning point and breaks into a dance. He continues dancing and goes towards his opponent to mock him. He then goes back to the table tennis table. The man dressed on black shows the score.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [4] > [3] > [5] > [2] > [1] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_2Tm_2wgv2Zs.mp4", "activitynet/videos/v_6azNzt8rXAs.mp4", "activitynet/videos/v_ahOnhEvMgq0.mp4", "activitynet/videos/v_hJn5L1nrkL4.mp4", "activitynet/videos/v_G-zVpNXq224.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A close up of booklets are shown with a person flipping them open and reading. The woman marks a name down and peels it off to put on a sock. The woman then lays an iron over the name and peels off the paper to show how to properly label a gift.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [3] > [1] > [4] > [5] > [2] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_QWFedtlPRYM.mp4", "activitynet/videos/v_0JCM9uzZafU.mp4", "activitynet/videos/v_JTGS1YulUQw.mp4", "activitynet/videos/v_a7QrIgqkyao.mp4", "activitynet/videos/v_mSPUMHD4F-E.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A man is seen holding a glass while speaking to the camera when another man walks in and begins painting the wall. The man continues to paint up and down the wall while the camera captures him and the other man walks away.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [1] > [3] > [5] > [4] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_llcbN-s26vs.mp4", "activitynet/videos/v_GQVqSLs2Ulg.mp4", "activitynet/videos/v_Zso0ZBs2y6E.mp4", "activitynet/videos/v_F53s94562zc.mp4", "activitynet/videos/v_2Ua6E2a6kT4.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A lady pulls and fixes her outfit. The lady messes with her hair. The lady tries on shoes while standing and sitting.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [4] > [1] > [3] > [2] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_9riZioI46sM.mp4", "activitynet/videos/v_avGe67wRvxA.mp4", "activitynet/videos/v_F2Igw6lvqwk.mp4", "activitynet/videos/v_RisNywzGXt8.mp4", "activitynet/videos/v_VNROQWtYhlw.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"An intro is shown of maps and a house close up. Afterwards a close up of a roof is shown as well as logos. More pictures are shown of trucks parked as well as logos.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [3] > [4] > [5] > [2] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_IT9uvR9yjxI.mp4", "activitynet/videos/v_MAUZbZnbM_Y.mp4", "activitynet/videos/v_0RZ5_8VD4vc.mp4", "activitynet/videos/v_ivBgqENFmt0.mp4", "activitynet/videos/v_-fMxoShIXiM.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"People run motocross on a bumpy road in the wood. A person climbs a bump with a motorcycle. Also people rides motorcycles on an unpaved flat surface.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [3] > [5] > [1] > [4] > [2] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_BfSqo9ONd6g.mp4", "activitynet/videos/v_UAgb3FEjBN8.mp4", "activitynet/videos/v_ux4iT6vQQb0.mp4", "activitynet/videos/v_Vq7Mm98I5Qs.mp4", "activitynet/videos/v_cA2ZLOZcCyc.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A closeup of a bag of cement mix is shown. One man adds water into a container while another watches. The first man pours the cement mix into the container. The second man uses a mixer on the container. one of the men applies the mixture to a wall.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [3] > [5] > [1] > [4] > [2] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_lZ2X-e33E0A.mp4", "activitynet/videos/v_oP77DgsbhKQ.mp4", "activitynet/videos/v_JBTiD2-FcR0.mp4", "activitynet/videos/v_IWXIEfaltJ4.mp4", "activitynet/videos/v_SmBEf-g82Ew.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A woman is seen speaking to the camera and leads into the news interviewing a man. Several shots are then shown of two bulls fighting other while others watch and speak to the camera.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [2] > [4] > [3] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_i9g2MGNUVQI.mp4", "activitynet/videos/v_mb2fWzNSob0.mp4", "activitynet/videos/v_AdFg_21LRg4.mp4", "activitynet/videos/v_cufmgoo7E_k.mp4", "activitynet/videos/v_vpvhtd7CqUA.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A woman is shown talking to the camera with her hands and the camera pointing to a building. She stands in front of the building doing a several little dances and continues this in front of several buildings and locations.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [5] > [4] > [2] > [1] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_pieT6K771WQ.mp4", "activitynet/videos/v_JRr3BruqS2Y.mp4", "activitynet/videos/v_bGDwE1v16HU.mp4", "activitynet/videos/v_XFySa1Gc-yM.mp4", "activitynet/videos/v_igwT-3gprOI.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A person is seen standing on a court holding a tennis racket. The man then demonstrates several moves with the tennis racket and hitting the ball to another. The two continuously hit the ball back and fourth to one another.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [3] > [4] > [1] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_xrbKvttgcMA.mp4", "activitynet/videos/v_0JpULUYPDX0.mp4", "activitynet/videos/v_BryW4niZT9Y.mp4", "activitynet/videos/v_nt4Ag91306U.mp4", "activitynet/videos/v_2Peh_gdQCjg.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"People are playing a game in a field. The man with the mallet and the man with the red hat run back and forth. A man with a blue shirt runs toward home plate. The man with the mallet is shown getting hit in slow motion. A woman is up to bat and is shown running after getting a hit.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [5] > [3] > [4] > [2] > [1] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_UYUvjnlU9Ho.mp4", "activitynet/videos/v_TpURw9nc8ks.mp4", "activitynet/videos/v_Lt6waJFJWI0.mp4", "activitynet/videos/v_U0IJmOHoa1M.mp4", "activitynet/videos/v_zlOErVVHKEk.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A woman is seen kneeling into frame next to a patio set. She then shows off various cleaning tools an rubs them along a chair. She brings the chair inside and pours paint into a bucket and paints along the side. She shows off the chair outside again while speaking to the camera.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [2] > [5] > [4] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_xpEbejnuGEY.mp4", "activitynet/videos/v_cKHdMUfKsQ8.mp4", "activitynet/videos/v_LSvjzZHbetU.mp4", "activitynet/videos/v__JE5T2RKZvo.mp4", "activitynet/videos/v_I5YCAQXHoFw.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"There are lots of adults in the room (elderly or young) and they're all watching this girl play the clarinet. First the girl walks to the front of the classroom as she holds her clarinet and the man who plays the piano gets up from his seat to play the piano. Then he starts playing the piano and she plays the clarinet along with the piano, when she's done everyone claps for her.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [4] > [5] > [1] > [3] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_AYhduTuI_zM.mp4", "activitynet/videos/v_vpu4Bwq-xHI.mp4", "activitynet/videos/v_vWEbHvnkogA.mp4", "activitynet/videos/v_cErtrZrWhiQ.mp4", "activitynet/videos/v_eOmL8f-yB40.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A group of young Asian men are indoors with a lot of spectators in the stands holding signs and cheering them on. Two young Asian men stand up with their bow and arrows and they each take turns at shooting at their bulls eye target while the crowd cheers them on after each shot is made, and occasionally 3 suited people are shown making commentaries. When the men are done shooting at the target,one of them raise their arm in victory, they shake each others hands,hug, take a bow and wave to the cheering crowd.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [3] > [4] > [5] > [1] > [2] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_nnWJGghixr0.mp4", "activitynet/videos/v_cjS2B52jBbU.mp4", "activitynet/videos/v_CDWHstJThJA.mp4", "activitynet/videos/v_dh4bxvmrCNs.mp4", "activitynet/videos/v_7lwrP2ma2TU.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"Two men do maneuvers on a canoe pivoting the canoe helping with the paddlers. Then, the men pivot the canoe away from the bow paddlers while paddling fast the oars. After, the men slides the canoe forward using the oars to advance. Next, the men sail on the river until arrive to the bank of the river.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [2] > [3] > [4] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_NV2scxevYKk.mp4", "activitynet/videos/v_ABCRXwB5-JQ.mp4", "activitynet/videos/v_djgM0IWIBKc.mp4", "activitynet/videos/v_-IkL9Kq9zfQ.mp4", "activitynet/videos/v_BD_ON66t6rM.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A bag of Spill Master Absorbant is shown on the screen. A man stands in a warehouse talking to the camera and pours some liquid on the ground. He takes a bowl of some material and sprinkled it over the spills. He then sweeps up the material with a broom and dust pan.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [4] > [2] > [3] > [1] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_NDWJOqVUGeA.mp4", "activitynet/videos/v_K8ZPkLVlAiA.mp4", "activitynet/videos/v_wr_1p7obP-g.mp4", "activitynet/videos/v_UxlDSfC7S-0.mp4", "activitynet/videos/v_KuyaO3brwBc.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A woman is video taping some men in a living room getting jackets on. One of the men motions the the camera person to follow him as he grabs a broom and walks down a hall and out a door to a snow covered parking lot. They walk out into the parking lot as another man comes outside. The man with the broom brushes snow off of an SUV as another man does the same at a car next to him.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [3] > [2] > [4] > [5] > [1] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_BYLxSOPFOuc.mp4", "activitynet/videos/v_3J_-uEjb8UE.mp4", "activitynet/videos/v__-zOtZZ_fwI.mp4", "activitynet/videos/v_3UbQ0UDmbbw.mp4", "activitynet/videos/v_C8IEqXTBod0.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A group of fish swim around in the ocean floor. A long yellow fish passes the camera. Scuba divers gather on a boat as a man speaks. We see several fish and a shark. The scuba divers dive, looking at the fish and waving at the camera.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [5] > [2] > [3] > [1] > [4] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_kuPWb9E4aUQ.mp4", "activitynet/videos/v_Zob68l3snFo.mp4", "activitynet/videos/v_fEsTL9tYOVc.mp4", "activitynet/videos/v_f9eW4rFQG-A.mp4", "activitynet/videos/v_LrwBGQ9B0Vg.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"A man is seen kneeling down next to a dog scrubbing his back while another man pours water over the dog's body. The man continues scrubbing as the other pours water and ends with the dog running away.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [2] > [1] > [3] > [4] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_iAWXaWo82u4.mp4", "activitynet/videos/v_8ClpQ4q6NmM.mp4", "activitynet/videos/v_zJNYqTVWqyY.mp4", "activitynet/videos/v_17ytsjuUCRA.mp4", "activitynet/videos/v_J7LhH4IKvnM.mp4" ]
[ { "content": "System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames. \n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Always output a total order in <answer>.\n\n\nQuery: \"One man is explaining to another man how to use a rowing machine. One of the main starts to row on the rowing machine before the other. Next, the other man joins the first man and starts to row.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n", "role": "user" }, { "content": "<answer> [1] > [3] > [2] > [4] > [5] </answer>", "role": "assistant" } ]	[ "activitynet/videos/v_o5j6N8O6HS4.mp4", "activitynet/videos/v_RpyRgnHdUXc.mp4", "activitynet/videos/v_-ceM4HHukhE.mp4", "activitynet/videos/v_Iib8Qt_9HQc.mp4", "activitynet/videos/v_FjY3eKNvzug.mp4" ]

README.md exists but content is empty.

Downloads last month: 4

Size of downloaded dataset files:

34.9 kB

Size of the auto-converted Parquet files:

34.9 kB

Number of rows:

Collection including happy8825/anet_ret_train_global_rzen_sft_nothinking

vid_fixed_train_validset

Collection

3 items • Updated Dec 12, 2025