{"id":"W2114168642","doi":"","title":"One-shot learning by inverting a compositional causal process","year":2013,"lang":"en","type":"article","venue":"DSpace@MIT (Massachusetts Institute of Technology)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":226,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Army Research Office; Multidisciplinary University Research Initiative; National Science Foundation","keywords":"Computer science; Artificial intelligence; Task (project management); Machine learning; Process (computing); Class (philosophy); Turing test; Range (aeronautics); Simple (philosophy); Causality (physics); Bayesian probability","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002726452,0.0003060209,0.0004216139,0.0006482847,0.0004270285,0.0001738374,0.001347658,0.0003552664,0.00008222085],"category_scores_gemma":[0.0003767813,0.0003367887,0.00009919535,0.00137584,0.0004757259,0.001488961,0.000386354,0.0008693819,0.0001761117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001058495,"about_ca_system_score_gemma":0.0001677537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005760083,"about_ca_topic_score_gemma":0.00001125484,"domain_scores_codex":[0.9975219,0.00006122594,0.0005539826,0.0006626672,0.0005976135,0.0006025701],"domain_scores_gemma":[0.9984087,0.00005836832,0.0004591027,0.0005669949,0.0003487454,0.0001581067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005419895,0.001340465,0.05852371,0.000443949,0.0007266994,0.00009287197,0.004620413,0.01126349,0.3689835,0.296427,0.01629899,0.2412247],"study_design_scores_gemma":[0.007342333,0.001658424,0.01389159,0.001333708,0.0001567638,0.0002981562,0.002313752,0.3357244,0.1517341,0.03740661,0.4438789,0.004261322],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5205728,0.000569068,0.437027,0.02478463,0.0007029148,0.0008841728,0.00001552558,0.002476677,0.0129672],"genre_scores_gemma":[0.9278786,0.00001765748,0.07111727,0.0004160652,0.00003882215,0.00009366045,0.00002894501,0.00002556042,0.0003834919],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4275799,"threshold_uncertainty_score":0.9999084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02457841219761775,"score_gpt":0.2623974005152571,"score_spread":0.2378189883176394,"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."}}