{"id":"W3048816818","doi":"10.48550/arxiv.2008.04428","title":"Locating Cephalometric X-Ray Landmarks with Foveated Pyramid Attention","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Pyramid (geometry); Artificial intelligence; Landmark; Quadratic growth; Computer science; Computation; Image (mathematics); Representation (politics); Computer vision; Point (geometry); Key (lock); Regression; Pattern recognition (psychology); Mathematics; Algorithm; Statistics; Geometry","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":[0.0001540117,0.0004252872,0.0004439862,0.0007504065,0.0001978361,0.0001892054,0.0006797995,0.0002740588,0.0001672018],"category_scores_gemma":[0.00004982994,0.000461817,0.0003441788,0.002555673,0.0001625873,0.0003298134,0.0005840294,0.0009619335,0.0003281292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001490373,"about_ca_system_score_gemma":0.00007216968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004321678,"about_ca_topic_score_gemma":0.0001091187,"domain_scores_codex":[0.9978695,0.0001280731,0.0002579432,0.001146675,0.0001770332,0.0004207888],"domain_scores_gemma":[0.9985072,0.00007543551,0.0003732665,0.0006545002,0.0001564976,0.0002330731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005896065,0.0003690141,0.9357193,0.0009261527,0.001206586,0.006543113,0.0002028414,0.04555535,0.001344406,0.004839652,0.001203568,0.001500463],"study_design_scores_gemma":[0.004667429,0.0003073369,0.8310678,0.0008970043,0.001669671,0.0001250239,0.001605631,0.1515635,0.0004005764,0.004423975,0.0009606685,0.002311368],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9290687,0.0001483472,0.0592914,0.00003748256,0.0006857772,0.000377192,0.00007971661,0.0003980179,0.009913323],"genre_scores_gemma":[0.9973537,0.00006428584,0.0002637855,0.00007802646,0.0001342297,0.000001406573,0.0002962596,0.00005843817,0.001749838],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1060081,"threshold_uncertainty_score":0.9997833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0473747667486818,"score_gpt":0.1901442267545196,"score_spread":0.1427694600058378,"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."}}