{"id":"W7106851162","doi":"10.48448/xd2p-5b46","title":"InfiniBench: A Benchmark for Large Multi-Modal Models in Long-Form Movies and TV Shows","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Benchmark (surveying); Set (abstract data type); Process (computing); Range (aeronautics); Cognition; Video recording","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003733254,0.003951971,0.0009312255,0.002416214,0.001090029,0.003290201,0.006122941,0.003872166,0.01519634],"category_scores_gemma":[0.02307315,0.0009583804,0.002472182,0.001781659,0.0009523369,0.006894063,0.003924924,0.003871991,0.006758324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003136611,"about_ca_system_score_gemma":0.002619623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04533343,"about_ca_topic_score_gemma":0.05799522,"domain_scores_codex":[0.9964508,0.001160753,0.0003093675,0.001139148,0.0006755018,0.0002644163],"domain_scores_gemma":[0.9907354,0.00605086,0.0003058628,0.001274374,0.001128049,0.0005054176],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002035809,0.002681567,0.01693879,0.004845628,0.001075084,0.001177023,0.002350862,0.2430874,0.01035386,0.01565287,0.3311256,0.3686755],"study_design_scores_gemma":[0.0003991016,0.0005738874,0.006165398,0.0004632565,0.0001523176,0.0003694534,0.001410193,0.8861549,0.01077089,0.01708365,0.07632113,0.0001357826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.3028177,0.008201286,0.2540439,0.004140752,0.001499638,0.003256659,0.1383438,0.2228589,0.06483734],"genre_scores_gemma":[0.3902107,0.001418156,0.2426797,0.00135783,0.0001541799,0.002109265,0.3421421,0.007258707,0.01266935],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.04533343,"threshold_uncertainty_score":0.09013909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05817615553321386,"score_gpt":0.342483739009024,"score_spread":0.2843075834758101,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}