{"id":"W6947922172","doi":"10.48448/9nv4-mw35","title":"Modelling Recognition in Human Puzzle Solving","year":2021,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Phytochemistry and biological activities of Ficus species","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Task (project management); Context (archaeology); Simple (philosophy); Reinforcement learning; Artificial neural network; Quality (philosophy)","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":[0.0002938893,0.0002242464,0.0002757233,0.00005200246,0.0003003631,0.0001453389,0.0005216224,0.0002563223,0.005292102],"category_scores_gemma":[0.0000528102,0.00009411452,0.00007007701,0.0006688134,0.0004442816,0.0001074141,0.0001909161,0.000302536,0.00002079051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008012279,"about_ca_system_score_gemma":0.00002874707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008386215,"about_ca_topic_score_gemma":0.002322122,"domain_scores_codex":[0.9983077,0.00003208922,0.0002285504,0.0006432629,0.000324688,0.0004637208],"domain_scores_gemma":[0.9995338,0.00007491855,0.0001456234,0.0000878541,0.00005700934,0.000100809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007174095,0.0003717887,0.0002453655,0.00005030707,0.00001069115,0.00003830394,0.00002941056,0.0001587894,0.940727,0.0003361807,0.006835689,0.0511893],"study_design_scores_gemma":[0.0009811413,0.0008277207,0.001701455,0.003940975,0.00005686728,0.00007763651,0.003393894,0.01822206,0.1677238,0.02281686,0.7752667,0.004990826],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.190408,0.0008113029,0.00005040072,0.0005437264,0.0002940671,0.0003128493,0.0001425558,0.0002412433,0.8071958],"genre_scores_gemma":[0.9156071,0.0002599367,0.001525356,0.0001748383,0.001310861,0.0000271563,0.0008314301,0.000009634032,0.08025368],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7730032,"threshold_uncertainty_score":0.9956172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06416277626335828,"score_gpt":0.2579445039598775,"score_spread":0.1937817276965192,"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."}}