{"id":"W2952508336","doi":"10.1017/9781316135167.025","title":"Phutball Endgames Are Hard","year":2002,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Contrast (vision); Combinatorial game theory; Mathematical economics; Combinatorics; Computer science; Mathematics; Sequential game; Game theory; Artificial intelligence","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002183053,0.000345846,0.0003789707,0.0001643827,0.00008029522,0.0006156405,0.003379936,0.0003210933,0.001013882],"category_scores_gemma":[0.0001211052,0.0003141288,0.0002272041,0.0001768395,0.00009736369,0.0002626102,0.003338556,0.0006546521,0.002781003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008709437,"about_ca_system_score_gemma":0.00006833615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000143488,"about_ca_topic_score_gemma":0.00005016177,"domain_scores_codex":[0.9975709,0.000074266,0.0004523984,0.0009925535,0.0004765929,0.0004332716],"domain_scores_gemma":[0.9974239,0.0001173314,0.0002735742,0.001867945,0.000172644,0.0001445722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005132516,0.0004183355,0.004259093,0.0002488943,0.0001893554,0.0002976404,0.00499975,0.006349449,0.000235482,0.2019017,0.2340417,0.5470535],"study_design_scores_gemma":[0.00008004121,0.00008024358,0.002592762,0.0004119761,0.00002772691,0.00003566563,0.0003072347,0.5239254,0.03548125,0.2241839,0.210753,0.002120792],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003309014,0.0008094442,0.8972182,0.005175686,0.003310874,0.0003552043,0.0000100288,0.001226314,0.08858524],"genre_scores_gemma":[0.6357494,0.0005520806,0.2851831,0.002701061,0.0008795551,0.0001282297,0.000005877538,0.00005862903,0.07474203],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6324404,"threshold_uncertainty_score":0.9999311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09175700883234549,"score_gpt":0.2939007554506296,"score_spread":0.2021437466182841,"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."}}