{"id":"W4401132864","doi":"10.1007/978-3-031-66329-1_12","title":"Evaluating and Improving Disparity Maps Without Ground Truth","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University; University of Waterloo","funders":"","keywords":"Ground truth; Common ground; Computer science; Cartography; Artificial intelligence; Geography; Computer vision; Psychology; Social psychology","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"],"consensus_categories":[],"category_scores_codex":[0.0006461759,0.0004045223,0.0005605931,0.0001496367,0.0001544083,0.0008111459,0.000275117,0.0003148503,0.000002507994],"category_scores_gemma":[0.00006899804,0.0003228862,0.00006060461,0.00008484665,0.00007650107,0.0002285709,0.0004283573,0.0009026762,0.000002708127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006855955,"about_ca_system_score_gemma":0.00003172661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006359942,"about_ca_topic_score_gemma":0.00003784877,"domain_scores_codex":[0.9979878,0.00004873374,0.0004512166,0.0008840609,0.000274202,0.0003539801],"domain_scores_gemma":[0.9987392,0.0004647951,0.0002015836,0.0004349712,0.0000483742,0.0001110553],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001262536,0.000005882353,0.0003653363,0.0006712278,0.00004732254,0.00007354577,0.0004497565,0.01683927,0.0000254308,0.1153086,0.00003265415,0.8661683],"study_design_scores_gemma":[0.0001992459,0.00005769719,0.00003169827,0.001574707,0.00002340166,0.0001004901,0.000004347158,0.9470075,7.526941e-7,0.04839683,0.002232519,0.0003708161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00007405537,0.04933302,0.940389,0.0001062287,0.002097379,0.0003882949,0.000003584911,0.0001228734,0.007485607],"genre_scores_gemma":[0.9595656,0.00124728,0.0248255,0.0003557404,0.001905329,0.00003752933,0.00002378202,0.00014126,0.01189794],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9594916,"threshold_uncertainty_score":0.9999223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02923050687627012,"score_gpt":0.2987372750956879,"score_spread":0.2695067682194178,"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."}}