{"id":"W4387947426","doi":"10.48550/arxiv.2310.15709","title":"Causal Representation Learning Made Identifiable by Grouping of Observational Variables","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Precursory Research for Embryonic Science and Technology; Japan Society for the Promotion of Science; Canadian Institute for Advanced Research","keywords":"Identifiability; Latent variable; Causality (physics); Robustness (evolution); Observational study; Representation (politics); Computer science; Machine learning; Causal inference; Consistency (knowledge bases); Confounding; Causal model; Feature learning; Artificial intelligence; Causal structure; Instrumental variable; Econometrics; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006044778,0.0002204718,0.0003045293,0.0003039739,0.000235439,0.000189153,0.001049607,0.0002118295,0.00005803106],"category_scores_gemma":[0.0002418725,0.0002933077,0.0001459232,0.0009981192,0.00007686468,0.0007076962,0.001200167,0.0005959281,0.00008110378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001359382,"about_ca_system_score_gemma":0.0001733352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006093914,"about_ca_topic_score_gemma":0.00001422394,"domain_scores_codex":[0.9979241,0.0002780393,0.0003483329,0.0009284943,0.0002231622,0.0002978789],"domain_scores_gemma":[0.9981434,0.0003680428,0.0005570923,0.0005926629,0.0002358626,0.000102982],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001302426,0.00003770763,0.0149862,0.00008580042,0.0000883891,0.00004397982,0.0004570827,0.8326824,0.001979249,0.1480764,0.001324647,0.0002250805],"study_design_scores_gemma":[0.0003911806,0.00002584276,0.009882198,0.0001415727,0.00004037919,0.000001887242,0.0003828088,0.9530538,0.0004469689,0.03428152,0.001006722,0.000345141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1062489,0.00003528655,0.8909347,0.0001190733,0.0006434057,0.0001745396,0.00001076074,0.0003562867,0.001476986],"genre_scores_gemma":[0.9741596,0.00009131806,0.006092752,0.00004654364,0.0000542047,0.000001931088,0.0002124155,0.00002653752,0.01931469],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.884842,"threshold_uncertainty_score":0.9999519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1939487437415773,"score_gpt":0.2332537626158407,"score_spread":0.03930501887426341,"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."}}