{"id":"W3132584191","doi":"10.48550/arxiv.2201.01942","title":"Efficiently Disentangle Causal Representations","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Generalization; Computer science; Contrast (vision); Code (set theory); Adaptation (eye); Artificial intelligence; Source code; Causal model; Sample (material); Machine learning; Theoretical computer science; Algorithm; Mathematics; Set (abstract data type); Statistics; Programming language","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":[0.002813735,0.00132274,0.001377256,0.002388734,0.0006375284,0.002279,0.003023277,0.001713266,0.004195366],"category_scores_gemma":[0.01725547,0.00118488,0.001770326,0.001952534,0.001332709,0.008415652,0.004176975,0.004317753,0.0009449576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001111277,"about_ca_system_score_gemma":0.001846898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003407642,"about_ca_topic_score_gemma":0.003895287,"domain_scores_codex":[0.9979414,0.0006932035,0.0001232617,0.0005585798,0.0005435503,0.0001399642],"domain_scores_gemma":[0.9939497,0.003545373,0.0006079181,0.00135369,0.0003809969,0.000162365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002306202,0.0002074203,0.002554712,0.0003125977,0.0002335435,0.0002426486,0.0004306486,0.2811625,0.005751663,0.2238909,0.004726361,0.4802563],"study_design_scores_gemma":[0.00002399964,0.00003174621,0.0002660005,0.0000293282,0.00003244913,0.00008011477,0.0000393607,0.7753034,0.001722696,0.2203599,0.002088226,0.00002276847],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008253949,0.0001985416,0.989787,0.0002054741,0.00001931523,0.00002795381,0.0001277656,0.0006353815,0.0007445856],"genre_scores_gemma":[0.5051494,0.0007566996,0.4886751,0.0003690906,0.0001260501,0.0001949842,0.00125911,0.000318492,0.003151063],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004195366,"threshold_uncertainty_score":0.01488066,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0952892448215393,"score_gpt":0.2213295657566847,"score_spread":0.1260403209351454,"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."}}