{"id":"W4283827058","doi":"10.1007/s11409-022-09313-y","title":"How accurate and predictive are judgments of solvability? Explorations in a two-phase anagram solving paradigm","year":2022,"lang":"en","type":"article","venue":"Metacognition and Learning","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Okanagan College","funders":"Flinders University; Australian Government","keywords":"Anagrams; Anagram; Psychology; Task (project management); Set (abstract data type); Duration (music); Cognitive psychology; Developmental psychology; Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.002525063,0.0001131335,0.0003027321,0.0004123155,0.000473286,0.000327854,0.0001330607,0.0000252633,0.0001595918],"category_scores_gemma":[0.00181063,0.0001023573,0.0000576552,0.0005035815,0.00009156729,0.0006890457,0.0001854451,0.0003655038,0.000002993261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003201724,"about_ca_system_score_gemma":0.00002685108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001737067,"about_ca_topic_score_gemma":0.00004443684,"domain_scores_codex":[0.9979411,0.0006143328,0.0004520441,0.0004240888,0.0004093945,0.0001590455],"domain_scores_gemma":[0.998482,0.0007898816,0.0004022882,0.0001547761,0.00009468952,0.00007629777],"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":[0.0003696347,0.0007166778,0.08425553,0.00001503226,0.00004004542,0.00003879177,0.008802745,0.01113888,0.0014359,0.0002720616,0.0001569949,0.8927577],"study_design_scores_gemma":[0.01330303,0.002476754,0.1198868,0.0002216291,0.0003025438,0.00009340926,0.2543956,0.4013251,0.0007642327,0.1865483,0.01944126,0.001241377],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9939989,0.0001598098,0.004794684,0.000462325,0.0001135331,0.0001922633,0.0000755731,0.00001983562,0.0001830253],"genre_scores_gemma":[0.9992999,0.00002063519,0.0003622056,0.00006992008,0.00001571914,0.00005718661,0.00002526003,0.000007974562,0.0001411411],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8915163,"threshold_uncertainty_score":0.4174008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1576797683991574,"score_gpt":0.4104401498600355,"score_spread":0.2527603814608781,"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."}}