{"id":"W4300767868","doi":"10.48550/arxiv.1712.02822","title":"Hybrid eye center localization using cascaded regression and\\n hand-crafted model fitting","year":2017,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Pattern recognition (psychology); Regression; Face (sociological concept); Computer vision; Training set; Feature (linguistics); Statistics; Mathematics","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0005193011,0.0007785036,0.0008004408,0.0006145669,0.002219475,0.0006639944,0.002269132,0.0006231713,0.00001227501],"category_scores_gemma":[0.0001724204,0.0008707842,0.0002750195,0.0003617984,0.0009846458,0.0009315126,0.004230733,0.001216869,0.00002520842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004056778,"about_ca_system_score_gemma":0.0003275549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002688614,"about_ca_topic_score_gemma":0.0000215487,"domain_scores_codex":[0.995584,0.0002837113,0.00050109,0.002577629,0.0001929862,0.0008605837],"domain_scores_gemma":[0.9957065,0.00007999407,0.001247174,0.002157639,0.0004987988,0.0003099168],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00016708,0.0003420831,0.0414696,0.0003315778,0.0002294522,0.001268116,0.0006944211,0.9266701,0.001772112,0.01654312,0.0001388534,0.01037349],"study_design_scores_gemma":[0.001285333,0.00005627373,0.001336263,0.001454076,0.0001706863,0.00004484071,0.00005329647,0.9771915,0.002305249,0.01514192,0.0001247873,0.0008357583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4517368,0.00007801692,0.5470526,0.0001048348,0.0004110117,0.0002263116,0.00001953896,0.0001848265,0.0001860667],"genre_scores_gemma":[0.9940975,0.0004052838,0.00401616,0.00009412188,0.00008433868,7.459144e-7,0.00002700245,0.00004805421,0.001226782],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5430365,"threshold_uncertainty_score":0.9993743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1094378448735498,"score_gpt":0.2327398598932448,"score_spread":0.1233020150196951,"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."}}