{"id":"W2039987681","doi":"10.1016/j.artint.2014.03.007","title":"On our best behaviour","year":2014,"lang":"en","type":"article","venue":"Artificial Intelligence","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Clearance; Computer science; Epistemology; Context (archaeology); Cognitive science; Artificial intelligence; Artificial general intelligence; Psychology; Data science; Philosophy; History","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003965579,0.000163768,0.0001530674,0.0000886005,0.0001978498,0.000208507,0.001017985,0.00007922139,0.00003631191],"category_scores_gemma":[0.0002958544,0.0001422285,0.00008521682,0.0003175166,0.00003927807,0.0002145413,0.0001693942,0.0001817276,0.005757063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003075236,"about_ca_system_score_gemma":0.00003599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007594478,"about_ca_topic_score_gemma":0.00008904487,"domain_scores_codex":[0.9986047,0.00008202311,0.0002634475,0.0004682058,0.0002122325,0.0003693829],"domain_scores_gemma":[0.9989179,0.0001268007,0.00007599498,0.0006302624,0.000105211,0.0001438802],"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":[0.000003905186,0.0001471134,0.0002417523,0.000001969928,0.000002594844,0.000004923684,0.0003958633,0.0001094728,0.0002308815,0.8130439,0.0005151495,0.1853025],"study_design_scores_gemma":[0.00005477064,0.001212725,0.0009235966,0.00007005421,0.00001808184,0.00002555242,0.0004330256,0.1305547,0.1314179,0.7271287,0.007318646,0.0008422564],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04309573,0.00003599436,0.9231673,0.0009529438,0.001536251,0.0001213176,9.062776e-7,0.0002275796,0.03086195],"genre_scores_gemma":[0.9951158,0.000006139389,0.003376288,0.0004036054,0.000269268,0.00001159158,0.000001006699,0.000009870496,0.0008064462],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.95202,"threshold_uncertainty_score":0.9950171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05246896499110883,"score_gpt":0.3039279630235122,"score_spread":0.2514589980324033,"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."}}