{"id":"W2127856808","doi":"10.1007/s11263-010-0385-z","title":"On Learning Conditional Random Fields for Stereo","year":2010,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"National Science Foundation","keywords":"Conditional random field; Artificial intelligence; Pattern recognition (psychology); Computer science; Mathematics; Computer vision","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":[0.0003801396,0.00009818037,0.0001455406,0.0002454001,0.00008050368,0.0002355996,0.0008957494,0.00004496165,0.00004593168],"category_scores_gemma":[0.0001284176,0.00007926961,0.0001630449,0.00005711239,0.00002432814,0.000724297,0.0001308008,0.0004136299,0.00001578807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002175439,"about_ca_system_score_gemma":0.00004534512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.914689e-7,"about_ca_topic_score_gemma":3.586771e-7,"domain_scores_codex":[0.9988068,0.00003533224,0.0003637957,0.000153971,0.000522421,0.0001177184],"domain_scores_gemma":[0.998264,0.0005732274,0.0003109805,0.0001192079,0.0006520568,0.00008052733],"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":[0.0004922512,0.0002268139,0.0001336702,0.000005229608,0.00008801449,0.00009272669,0.0002664395,0.01251735,0.005341318,0.09974829,0.01180846,0.8692794],"study_design_scores_gemma":[0.005450204,0.00109193,0.001614215,0.0001423548,0.000005367566,0.0005274691,0.000006918787,0.835735,0.002639831,0.07331685,0.07926717,0.0002027279],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01923956,0.00001086759,0.972637,0.003021699,0.004737423,0.00006184347,0.000001664766,0.00002542256,0.0002645033],"genre_scores_gemma":[0.7762722,0.000005956556,0.2214426,0.001336273,0.0008495036,0.00000129003,0.000004143282,0.000006205982,0.00008175873],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8690767,"threshold_uncertainty_score":0.3232521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008022493281083063,"score_gpt":0.3236647983551791,"score_spread":0.3156423050740961,"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."}}