{"id":"W1596449068","doi":"10.1007/s13420-010-0001-7","title":"Pigeons exhibit higher accuracy for chosen memory tests than for forced memory tests in duration matching-to-sample","year":2010,"lang":"en","type":"article","venue":"Learning & Behavior","topic":"Cognitive and developmental aspects of mathematical skills","field":"Mathematics","cited_by":44,"is_retracted":false,"has_abstract":false,"ca_institutions":"Wilfrid Laurier University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Psychology; Two-alternative forced choice; Test (biology); Task (project management); Statistics; Interval (graph theory); Matching (statistics); Sample (material); Audiology; Selection (genetic algorithm); Memory test; Cognitive psychology; Mathematics; Cognition; Artificial intelligence; Computer science; Chemistry","routes":{"ca_aff":true,"ca_fund":true,"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"],"consensus_categories":[],"category_scores_codex":[0.0006911206,0.0003441973,0.0004561429,0.0001932257,0.0003005646,0.0001270093,0.0002741056,0.0001812921,0.0003973702],"category_scores_gemma":[0.006925368,0.0003201403,0.0001825127,0.0002202421,0.0000467123,0.0002810001,0.0001345506,0.0004800643,0.0001034595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000886474,"about_ca_system_score_gemma":0.00006564624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001054173,"about_ca_topic_score_gemma":0.0008696453,"domain_scores_codex":[0.9978658,0.0000483619,0.0006440682,0.0005158558,0.000323069,0.0006028332],"domain_scores_gemma":[0.9938999,0.005145145,0.0002544332,0.000310325,0.0001907023,0.0001994318],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0008582004,0.004117882,0.03697021,0.001166708,0.0001293839,0.0000710346,0.01509679,0.00005033959,0.7548345,0.02359388,0.003295375,0.1598157],"study_design_scores_gemma":[0.01119347,0.001647917,0.6337736,0.001367883,0.0006505108,0.00006227398,0.002510908,0.0004311688,0.1211999,0.2169187,0.006708275,0.003535388],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9883838,0.000006105809,0.006847917,0.0004773547,0.0003270365,0.00297137,0.00004686157,0.0002365212,0.0007030835],"genre_scores_gemma":[0.8976374,8.879608e-7,0.09637464,0.0001556345,0.0002032893,0.001795267,0.00009993622,0.0001062233,0.003626767],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6336346,"threshold_uncertainty_score":0.9999251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03930081224055187,"score_gpt":0.3480553800815972,"score_spread":0.3087545678410453,"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."}}