{"id":"W2121513215","doi":"10.5555/2484920.2484965","title":"Evaluating state-space abstractions in extensive-form games","year":2013,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Abstraction; Metric (unit); Domain (mathematical analysis); Perfect information; Theoretical computer science; Focus (optics); Task (project management); State (computer science); Quality (philosophy); State space; Space (punctuation); Artificial intelligence; Algorithm; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003089899,0.0001086921,0.0001145557,0.0001340697,0.00007958419,0.0002408783,0.000490954,0.00003806151,0.0006037652],"category_scores_gemma":[0.0002226038,0.00009428681,0.0000375387,0.0002997854,0.00005084702,0.001808233,0.0001562605,0.0001597484,0.002985038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006540119,"about_ca_system_score_gemma":0.00006808678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001739001,"about_ca_topic_score_gemma":0.0003972839,"domain_scores_codex":[0.9987506,0.00003882062,0.0003011291,0.0003130946,0.0002671318,0.000329219],"domain_scores_gemma":[0.9989088,0.000273376,0.00007549306,0.0004311549,0.0002332235,0.00007800779],"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":[0.000002768748,0.0001383528,0.004079076,0.000009073192,0.00001212784,0.00001558568,0.004724679,0.01336201,0.01695931,0.05878279,0.004874559,0.8970397],"study_design_scores_gemma":[0.0000828508,0.0001126306,0.05067296,0.00002866833,0.000002077059,0.00001431038,0.001806042,0.8046408,0.03830045,0.1025802,0.001402462,0.0003565064],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7352336,0.00005080078,0.2427985,0.005446776,0.0004077382,0.0003861253,3.711531e-7,0.0002598176,0.01541628],"genre_scores_gemma":[0.9094185,0.00001219517,0.08647039,0.0004967062,0.00002809768,0.00005487058,3.033527e-7,0.000007213369,0.003511707],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8966832,"threshold_uncertainty_score":0.9977912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08231356342286796,"score_gpt":0.3665186465027483,"score_spread":0.2842050830798803,"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."}}