{"id":"W4402557614","doi":"10.1109/tpami.2024.3462291","title":"Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of Guelph; Ontario Tech University; York University","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003417867,0.0001394827,0.0001889371,0.0008101754,0.0001315412,0.0005424028,0.0001589765,0.00004559681,0.0000351297],"category_scores_gemma":[0.00000714759,0.000127234,0.00006869729,0.001336591,0.00003307705,0.0008750079,0.000006621483,0.0003185564,0.0000137509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002935928,"about_ca_system_score_gemma":0.00001418386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006302936,"about_ca_topic_score_gemma":0.002621401,"domain_scores_codex":[0.9989436,0.00009019212,0.0003694656,0.0002747512,0.0001667048,0.0001553172],"domain_scores_gemma":[0.9995388,0.0001311971,0.00006042614,0.0001680978,0.00003251216,0.00006899639],"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":[0.000002433784,0.00001903791,0.0009918148,0.00003914302,0.00008457603,0.000005318644,0.0007776649,0.3074532,0.000002894388,0.0002161471,0.000001661806,0.6904061],"study_design_scores_gemma":[0.00004204908,0.00004662051,0.001115699,0.00005043118,0.00009288954,0.000004603462,0.0001053579,0.998018,0.0002070419,0.00006434638,0.0001137316,0.0001392544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003517306,0.0001532654,0.9956852,0.0003518382,0.0001188354,0.00006452477,0.000009560186,0.00008645526,0.00001298591],"genre_scores_gemma":[0.9973652,0.00106122,0.001158323,0.0003255579,0.0000043017,0.000005645947,0.00003247677,0.000005808816,0.00004144476],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9945269,"threshold_uncertainty_score":0.5230402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02018833194401566,"score_gpt":0.3023741369426208,"score_spread":0.2821858049986051,"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."}}