{"id":"W4413145426","doi":"10.1109/cvpr52734.2025.02254","title":"Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable Events","year":2025,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Vector Institute; National Research Foundation","keywords":"Abductive reasoning; Computer science; Defeasible estate; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003134597,0.0001021219,0.0001371739,0.0001781887,0.00007073016,0.0000902843,0.0004523897,0.00005383473,0.00002403014],"category_scores_gemma":[0.0001859811,0.00009644777,0.00002338703,0.0006839497,0.00007638848,0.0005688263,0.0003686455,0.0001227109,0.00005421738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006608594,"about_ca_system_score_gemma":0.00008681254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004563856,"about_ca_topic_score_gemma":0.0002522398,"domain_scores_codex":[0.9989436,0.00005111269,0.0002144715,0.0003846345,0.0001416626,0.0002645474],"domain_scores_gemma":[0.9993907,0.0001390088,0.00003495428,0.0003264228,0.00005750669,0.00005143968],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001604848,0.00009227474,0.1447784,0.00002198811,0.00002259677,0.00001372224,0.002594821,0.001371183,0.0005148766,0.8156908,0.00235973,0.03252362],"study_design_scores_gemma":[0.0003261051,0.0000991932,0.03877041,0.0003892083,0.00001113658,0.00000867427,0.002171888,0.4285119,0.04417266,0.4810726,0.004015665,0.0004504759],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2447913,0.0003043241,0.7010846,0.001687915,0.0003765941,0.0002530792,6.755006e-7,0.0001744883,0.05132702],"genre_scores_gemma":[0.9646078,0.00003914849,0.03153175,0.000331078,0.00001836754,0.00001117124,2.888694e-7,0.000004102571,0.003456312],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7198165,"threshold_uncertainty_score":0.3933026,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01735586867973281,"score_gpt":0.2886292183971071,"score_spread":0.2712733497173743,"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."}}