{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005895472,0.000671957,0.000462095,0.0008883502,0.0002213336,0.0006023484,0.0002266731,0.0005601862,0.00198904],"category_scores_gemma":[0.006005252,0.000193596,0.0002833839,0.0004940675,0.0002820222,0.0005465671,0.0005790187,0.0005397255,0.0003795479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002667689,"about_ca_system_score_gemma":0.0001869896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0037797,"about_ca_topic_score_gemma":0.005694019,"domain_scores_codex":[0.9994215,0.0001135051,0.00008623564,0.0001488869,0.0001624889,0.00006733476],"domain_scores_gemma":[0.9968594,0.001381338,0.001018874,0.0002057823,0.0002916567,0.0002428906],"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":[0.00712781,0.001148829,0.4281258,0.0005567962,0.0003033229,0.0005853556,0.006250719,0.00121294,0.504313,0.0001696012,0.001088469,0.04911746],"study_design_scores_gemma":[0.00003740058,0.001081196,0.9898045,0.00001312561,0.00002444994,0.00017916,0.0003400678,0.001155796,0.006988524,0.00006208011,0.0002862374,0.00002747694],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9978167,0.00009096164,0.0009481955,0.00001526959,0.000003994449,0.00007056259,0.0003936626,0.00004104797,0.0006195991],"genre_scores_gemma":[0.9970957,0.00006425368,0.001515454,0.00001194612,0.000005372183,0.0001258119,0.0005332517,0.00002313143,0.0006251121],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0037797,"threshold_uncertainty_score":0.00751543,"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."}}