{"id":"W7154579623","doi":"10.48448/px0m-2c23","title":"Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models","year":2025,"lang":"","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Bespoke; Probabilistic logic; Inference; Construct (python library); Domain (mathematical analysis); Statistical model; Key (lock); Language model; Cognition","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","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaepi_narrow","sts","insufficient_payload"],"category_scores_codex":[0.007843035,0.001758642,0.002528415,0.007262301,0.001411525,0.001422521,0.007614917,0.0006433572,0.00522097],"category_scores_gemma":[0.006575138,0.001747093,0.0003575183,0.009530897,0.00614602,0.002147751,0.002922653,0.001286366,0.004518816],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001631922,"about_ca_system_score_gemma":0.01400874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001730352,"about_ca_topic_score_gemma":0.001846628,"domain_scores_codex":[0.9858104,0.000654714,0.002777793,0.004384183,0.004267299,0.002105627],"domain_scores_gemma":[0.9895478,0.001571985,0.001823386,0.003074633,0.003186896,0.0007953328],"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":[0.000432566,0.001981583,0.000002811085,0.0007462341,0.0002316485,0.00001693107,0.000179192,0.7981493,0.001730144,0.1867684,0.001054199,0.008707055],"study_design_scores_gemma":[0.001020759,0.0003123758,0.000001210534,0.009953212,0.0009427077,0.00001009797,0.0002696775,0.7965789,0.002930698,0.1863267,0.000327292,0.00132633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.001006688,0.0004501177,0.05448545,0.0003959857,0.0009733354,0.006399589,0.00167546,0.0002484706,0.9343649],"genre_scores_gemma":[0.9024009,0.0002332826,0.01493382,0.0003799624,0.0002466788,0.0004036243,0.00008913696,0.000730588,0.08058198],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9013942,"threshold_uncertainty_score":0.9998885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05903420046737664,"score_gpt":0.33149844038105,"score_spread":0.2724642399136734,"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."}}