{"id":"W2560513213","doi":"10.1101/091298","title":"Compositional Inductive Biases in Function Learning","year":2016,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Companhia Brasileira de Metalurgia e Mineração; National Science Foundation","keywords":"Principle of compositionality; Computer science; Inductive bias; Artificial intelligence; Predictability; Property (philosophy); Prior probability; Function (biology); Process (computing); Machine learning; Natural language processing; Bayesian probability; Multi-task learning; Mathematics; Task (project management)","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":[0.0005871911,0.0004760553,0.0004931038,0.0004735451,0.0001725145,0.00009986798,0.0003001097,0.0005511762,0.0007690852],"category_scores_gemma":[0.0001669288,0.0004636074,0.0001348737,0.0003346621,0.0001140149,0.0001074456,0.0003298945,0.001462536,0.0007279734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004089552,"about_ca_system_score_gemma":0.0003348357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005480489,"about_ca_topic_score_gemma":0.000002183114,"domain_scores_codex":[0.9970676,0.0003513111,0.0005102635,0.001131868,0.0003266727,0.0006122493],"domain_scores_gemma":[0.9985313,0.0001898963,0.0003748808,0.0005061888,0.0002218707,0.0001758645],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0006670286,0.000893168,0.3528217,0.0001799032,0.0007477212,0.0003239615,0.0001763451,0.0002224931,0.6231338,0.01905063,0.001726369,0.00005682981],"study_design_scores_gemma":[0.0008103617,0.00009123238,0.9798833,0.0009294683,0.00004293593,3.021066e-8,0.00001405653,0.00001614542,0.00516887,0.00001135266,0.01234733,0.0006849797],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.994918,0.0005489027,0.000592981,0.0003609017,0.002263319,0.0004018741,0.00006737439,0.0003825944,0.0004639762],"genre_scores_gemma":[0.9980639,0.00003060787,0.0005126797,0.0001710226,0.0008811022,0.0001874161,0.000001168016,0.0001016459,0.00005047807],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6270615,"threshold_uncertainty_score":0.9997815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02411887202055137,"score_gpt":0.2536443436264952,"score_spread":0.2295254716059438,"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."}}