{"id":"W4390041630","doi":"10.48550/arxiv.2312.11753","title":"Recording and Describing Poker Hands","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Gambling Behavior and Treatments","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Parsing; Benchmark (surveying); Popularity; Field (mathematics); Code (set theory); Source code; Representation (politics); Information retrieval; Artificial intelligence; World Wide Web; 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":[0.0009906424,0.00060485,0.0003430154,0.002372926,0.0005881139,0.001636485,0.0006023785,0.000786738,0.0536296],"category_scores_gemma":[0.01063412,0.0002774942,0.0002479503,0.001902941,0.0005920623,0.002299749,0.00145608,0.0006928229,0.01421198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003806136,"about_ca_system_score_gemma":0.0006352004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001679768,"about_ca_topic_score_gemma":0.002657817,"domain_scores_codex":[0.9991174,0.0002296952,0.0001184468,0.0001791393,0.0002839255,0.00007137945],"domain_scores_gemma":[0.9951925,0.002823247,0.0002673067,0.0009545791,0.0006027829,0.0001596147],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001265508,0.0001292264,0.008593339,0.001585735,0.0000323204,0.001190606,0.004469276,0.00421169,0.01495134,0.03461092,0.1904541,0.7385061],"study_design_scores_gemma":[0.00008153669,0.0001873603,0.01586002,0.0008415006,0.00002316752,0.001598459,0.001960254,0.008276789,0.02363714,0.02218409,0.9251937,0.0001560333],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1189233,0.002933999,0.4421228,0.001237986,0.002097401,0.002241985,0.1606168,0.02817692,0.2416488],"genre_scores_gemma":[0.4077109,0.002756693,0.3158945,0.0009253677,0.0007322631,0.004119041,0.1183377,0.007781706,0.141742],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0536296,"threshold_uncertainty_score":0.1794089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4584999047487887,"score_gpt":0.2908221850475672,"score_spread":0.1676777197012214,"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."}}