{"id":"W1946985707","doi":"10.1023/a:1015736313131","title":"The IJCAR ATP System Competition","year":2002,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Programming language; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0008938497,0.0001039213,0.0001956772,0.00007797056,0.000369117,0.0004311482,0.0006692662,0.00006216553,0.000005027805],"category_scores_gemma":[0.00008117787,0.0000611867,0.0001196142,0.0002913682,0.00003465745,0.0003577248,0.00006181301,0.00019485,0.00007616192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001043216,"about_ca_system_score_gemma":0.00002706211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000113248,"about_ca_topic_score_gemma":0.00000129948,"domain_scores_codex":[0.9986293,0.0001568206,0.0004483595,0.0001125558,0.0004061953,0.0002467428],"domain_scores_gemma":[0.9986866,0.0001311106,0.0005997515,0.0002563047,0.000232844,0.00009340922],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001129669,0.0001005765,0.0009292257,0.0001001747,0.0002223971,0.0005790144,0.004119963,0.0007812206,0.0007427162,0.9368878,0.01018807,0.04533756],"study_design_scores_gemma":[0.000697043,0.0003033349,0.001480714,0.0002236997,0.00003087897,0.004574575,0.0007609759,0.9223472,0.0004756487,0.0004454023,0.06844022,0.0002202729],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07132954,0.01822915,0.8204706,0.004667046,0.01437825,0.0007090608,0.000001059828,0.004448195,0.06576712],"genre_scores_gemma":[0.9966967,0.00005362512,0.002791944,0.00002998518,0.0002436262,0.000001654961,1.726073e-7,0.000008064338,0.000174245],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9364424,"threshold_uncertainty_score":0.4157572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01484449246328016,"score_gpt":0.230399420483365,"score_spread":0.2155549280200848,"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."}}