{"id":"W3198606375","doi":"10.1167/jov.21.9.2125","title":"Gaze behaviour: a window into quantifying task difficulty and performance using the Tower of London Task","year":2021,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Gaze; Saccade; Workspace; Task (project management); Fixation (population genetics); Cognitive psychology; Psychology; Cognition; Eye movement; Computer science; Computer vision; Artificial intelligence; Communication; Robot; Engineering; Population","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":[0.0004177608,0.0000873176,0.0002008246,0.00009815708,0.0001410417,0.000071444,0.0003502179,0.00006039269,0.000002971596],"category_scores_gemma":[0.00006006792,0.00005457951,0.00007309762,0.0002698849,0.00008315003,0.0003098429,0.0002036674,0.0002877173,5.396237e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003071949,"about_ca_system_score_gemma":0.00006293726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009820226,"about_ca_topic_score_gemma":0.000003884903,"domain_scores_codex":[0.9990696,0.00006115992,0.0003281961,0.0001397841,0.0002703558,0.0001309424],"domain_scores_gemma":[0.9990216,0.00007355693,0.0003595645,0.0002365728,0.0002689099,0.00003975287],"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":[0.00004132753,0.0002538196,0.09713425,0.00004601076,0.00003782279,0.0001475445,0.001432178,0.0002931287,0.7268839,0.0004818338,0.0001854653,0.1730627],"study_design_scores_gemma":[0.000769406,0.0006156245,0.9314377,0.0006899284,0.00005054211,0.00154384,0.0002749245,0.02134215,0.04248307,0.0002962387,0.000333895,0.000162672],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9553095,0.0009776941,0.04273982,0.0006930447,0.0002304194,0.00002719398,4.82065e-7,0.00001138384,0.0000105186],"genre_scores_gemma":[0.9839306,0.0001554984,0.01583168,0.00003314151,0.00003297086,1.946191e-7,1.753e-7,0.000004278033,0.00001145442],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8343034,"threshold_uncertainty_score":0.2225688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02662539947731933,"score_gpt":0.3018505833387473,"score_spread":0.2752251838614279,"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."}}