{"id":"W4406983107","doi":"10.1073/pnas.2416866122","title":"Errors are robustly tamed in cumulative knowledge processes","year":2025,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Army Research Office; Office of Naval Research; Multidisciplinary University Research Initiative; National Science Foundation","keywords":"Heuristics; Computer science; Simple (philosophy); Probabilistic logic; Adversarial system; Bounded function; Fraction (chemistry); Process (computing); Theoretical computer science; Artificial intelligence; Mathematics; Epistemology; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03026168,0.001513682,0.00221218,0.003603837,0.003076656,0.0074642,0.005106895,0.004771793,0.003213173],"category_scores_gemma":[0.2039183,0.0016568,0.002880526,0.001927919,0.01544665,0.02214889,0.01363435,0.005616171,0.0009362168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004034146,"about_ca_system_score_gemma":0.002712193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003851388,"about_ca_topic_score_gemma":0.001622401,"domain_scores_codex":[0.9709495,0.009187211,0.00179193,0.007893967,0.008038759,0.002138465],"domain_scores_gemma":[0.7320753,0.1608019,0.02389522,0.06876306,0.01127569,0.003188874],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003705731,0.0001157008,0.005211118,0.000254706,0.0002781342,0.0009260818,0.003677958,0.1391239,0.003280987,0.8033821,0.00132046,0.04205828],"study_design_scores_gemma":[0.00005531187,0.00007765813,0.0004431654,0.00006279993,0.000122391,0.0002281622,0.0002063337,0.1683477,0.00415722,0.8241667,0.002065224,0.00006748136],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1381043,0.0004534505,0.8479311,0.003338094,0.00008946008,0.0001584629,0.0001528643,0.001403769,0.008368523],"genre_scores_gemma":[0.9228298,0.0003076281,0.07278021,0.0005207887,0.0001358259,0.0001929338,0.0001221905,0.0002396203,0.002870882],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03026168,"threshold_uncertainty_score":0.160041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05174160605511081,"score_gpt":0.3288787505353769,"score_spread":0.2771371444802661,"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."}}