{"id":"W4360797517","doi":"10.1101/2023.03.22.533826","title":"Visual working memory models of delayed estimation do not generalize to whole-report tasks","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Working memory; Task (project management); Computer science; Set (abstract data type); Encoding (memory); Orientation (vector space); Context (archaeology); Recall; Similarity (geometry); Bayesian probability; Artificial intelligence; Cognitive psychology; Psychology; Mathematics; Cognition","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01640836,0.0008830017,0.001350647,0.0006288068,0.0004309267,0.002958242,0.003646451,0.001102461,0.003879439],"category_scores_gemma":[0.09895653,0.0009103592,0.001869878,0.0005420568,0.001530672,0.006073399,0.002220554,0.003542224,0.0008808026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001032036,"about_ca_system_score_gemma":0.0007392248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002444675,"about_ca_topic_score_gemma":0.001713046,"domain_scores_codex":[0.9962292,0.001316825,0.0003609835,0.00114499,0.000712974,0.0002349814],"domain_scores_gemma":[0.9300311,0.03927696,0.006146083,0.02123302,0.002239934,0.001072803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.007628447,0.002402734,0.1867186,0.001775169,0.002734335,0.0005571712,0.004841148,0.2993784,0.1063577,0.06083351,0.008937309,0.3178355],"study_design_scores_gemma":[0.0002244913,0.0005971173,0.06705669,0.0001261213,0.0002087818,0.0003942426,0.0002088418,0.7876938,0.01652599,0.1253199,0.001465316,0.0001786957],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6199731,0.0003145005,0.3729186,0.0005619829,0.0001109015,0.0002929928,0.001009418,0.0009269193,0.003891467],"genre_scores_gemma":[0.9679664,0.00009567219,0.02925969,0.0002146818,0.00003457524,0.0002793562,0.000925627,0.0002565536,0.0009672691],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01640836,"threshold_uncertainty_score":0.08677673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.131314816940368,"score_gpt":0.3415136377647082,"score_spread":0.2101988208243402,"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."}}