{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002938884,0.0006976913,0.0005842861,0.0005225602,0.000292869,0.001295779,0.0007094942,0.001057373,0.002953934],"category_scores_gemma":[0.02293175,0.0005613029,0.0003276296,0.0002972075,0.0005329755,0.00172471,0.001117731,0.001429942,0.0002705367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003424268,"about_ca_system_score_gemma":0.0004659889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005604287,"about_ca_topic_score_gemma":0.0008285879,"domain_scores_codex":[0.9979583,0.0007762139,0.000168454,0.0005093886,0.0004753497,0.0001121899],"domain_scores_gemma":[0.9819857,0.01017743,0.004814463,0.001550762,0.0006325855,0.0008389716],"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":[0.011763,0.008682403,0.07964671,0.0006769947,0.000263811,0.0003097426,0.005831725,0.008363911,0.7920304,0.004621224,0.00113746,0.08667262],"study_design_scores_gemma":[0.001523051,0.01960995,0.6516469,0.0002300888,0.0002824705,0.0006210225,0.001802176,0.1633951,0.1219763,0.03434955,0.004123939,0.0004395804],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9938174,0.00002839519,0.00483816,0.00006917975,0.00001097797,0.00009477953,0.00006956155,0.00004556953,0.001025985],"genre_scores_gemma":[0.9895488,0.00003766703,0.009190711,0.00006571322,0.00001318215,0.0002530345,0.0001164561,0.00002836695,0.0007460364],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002953934,"threshold_uncertainty_score":0.01554245,"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."}}