{"id":"W4392822490","doi":"10.48550/arxiv.2403.08335","title":"A Sparsity Principle for Partially Observable Causal Representation Learning","year":2024,"lang":"en","type":"preprint","venue":"UvA-DARE (University of Amsterdam)","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Samsung; International Max Planck Research School for Environmental, Cellular and Molecular Microbiology; International Max Planck Research School for Advanced Methods in Process and Systems Engineering; Institut de Valorisation des Données; Bundesministerium für Bildung und Forschung; Institute of Science and Technology Austria","keywords":"Observable; Representation (politics); Computer science; Mathematics; Artificial intelligence; Physics; Quantum mechanics; Political science; Law","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":[0.0004342993,0.0002759794,0.0004699426,0.000200988,0.0002975994,0.0002126019,0.00142879,0.0003151425,0.0000332959],"category_scores_gemma":[0.00005758796,0.0003574986,0.0003127295,0.0002871814,0.00009557582,0.0003351521,0.003540742,0.0007235755,0.00005837964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001351141,"about_ca_system_score_gemma":0.0004730014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008306347,"about_ca_topic_score_gemma":0.0003114469,"domain_scores_codex":[0.9978628,0.0001320652,0.0002527753,0.0009912594,0.000383335,0.0003777486],"domain_scores_gemma":[0.9982191,0.0001138494,0.0003245915,0.000826485,0.0003653798,0.0001505881],"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":[0.0009999829,0.001070828,0.0131102,0.01060584,0.002280368,0.0009894799,0.06815246,0.3420683,0.006846688,0.282525,0.03125594,0.2400949],"study_design_scores_gemma":[0.0007358017,0.0003129511,0.003103779,0.0008603581,0.0002253741,0.00001212513,0.0007654905,0.9322914,0.0007156724,0.0492148,0.01094481,0.0008174157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1230851,0.0001548454,0.8719311,0.001384888,0.0008030573,0.0004708692,0.00006154212,0.0003916535,0.001716868],"genre_scores_gemma":[0.9064363,0.0000578455,0.08735754,0.00005370943,0.0001138316,0.000003447506,0.0001097485,0.00002457349,0.005842987],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7845736,"threshold_uncertainty_score":0.9998877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0609455785369892,"score_gpt":0.2823344254885941,"score_spread":0.2213888469516049,"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."}}