{"id":"W4226105092","doi":"10.1609/aaai.v36i2.20111","title":"Decompose the Sounds and Pixels, Recompose the Events","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Event (particle physics); Computer science; Margin (machine learning); Decomposition; Function (biology); Artificial intelligence; State (computer science); Architecture; Audio visual; Categorization; Natural language processing; Machine learning; Algorithm","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.00117155,0.0002020506,0.0001857396,0.00007144755,0.00153496,0.0003980613,0.003577495,0.00003444009,0.00006775347],"category_scores_gemma":[0.0002104523,0.0001090717,0.00009857191,0.0007587025,0.0003120033,0.0003325008,0.001566145,0.0005436083,0.00002058605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004761494,"about_ca_system_score_gemma":0.0001131625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002825176,"about_ca_topic_score_gemma":0.000008448036,"domain_scores_codex":[0.9980755,0.0000568348,0.0004172685,0.0004505282,0.0006418982,0.000357965],"domain_scores_gemma":[0.9987025,0.0002046015,0.0003884159,0.0003918307,0.0002466903,0.00006593054],"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":[0.0001195992,0.0002760884,0.001241289,0.00003880911,0.00004576501,0.000001323455,0.007613307,0.0001528113,0.05315271,0.5063811,0.001218882,0.4297583],"study_design_scores_gemma":[0.00005744648,0.0003012587,0.0008256899,0.00009647932,0.00002354907,0.00007361259,0.003095062,0.02290076,0.4369965,0.5322708,0.003022206,0.000336684],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9079621,0.0003906225,0.01121492,0.06710165,0.001523792,0.001021831,0.000009939874,0.0001796121,0.01059549],"genre_scores_gemma":[0.99696,0.0000480648,0.001396983,0.001103032,0.00006601861,0.00005858652,2.526917e-7,0.00001083445,0.0003561893],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4294216,"threshold_uncertainty_score":0.9997649,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05858571058833668,"score_gpt":0.2821270915183635,"score_spread":0.2235413809300268,"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."}}