{"id":"W7154613484","doi":"10.48448/pcgf-tr51","title":"Think outside the box: Making up casual hypotheses from unreliable evidence","year":2025,"lang":"","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Dalhousie University","funders":"","keywords":"Salient; Casual; Heuristics; Bayesian inference; Bayesian probability; Cognition; Mechanism (biology); Natural (archaeology)","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":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","sts","insufficient_payload"],"category_scores_codex":[0.01092799,0.002659711,0.002189776,0.002974922,0.005112831,0.004980102,0.01545234,0.001184027,0.01928567],"category_scores_gemma":[0.02210935,0.001979959,0.0006152348,0.0104238,0.01667104,0.003063818,0.005422065,0.003598923,0.03412789],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003312893,"about_ca_system_score_gemma":0.02067941,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01384489,"about_ca_topic_score_gemma":0.006564739,"domain_scores_codex":[0.9783942,0.00128132,0.002639061,0.005902014,0.007441025,0.004342391],"domain_scores_gemma":[0.9774837,0.009584875,0.002959777,0.007122647,0.002054261,0.000794694],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001474983,0.002442645,0.006521448,0.001132007,0.002718903,0.001018137,0.03180379,0.02106463,0.07887653,0.09591127,0.6060384,0.1509973],"study_design_scores_gemma":[0.003625888,0.001099058,0.004763112,0.06109562,0.004234029,0.0002244692,0.0332924,0.2115614,0.01253218,0.07425405,0.5821142,0.01120358],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.004297086,0.06165002,0.03727987,0.01060672,0.04118476,0.01007103,0.004164753,0.002816461,0.8279293],"genre_scores_gemma":[0.4772339,0.001987235,0.02676331,0.005415458,0.003303594,0.0001126786,0.00005071456,0.001505482,0.4836277],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.4729368,"threshold_uncertainty_score":0.9986998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0839022793333959,"score_gpt":0.3562585872677383,"score_spread":0.2723563079343424,"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."}}