{"id":"W4293868236","doi":"10.1109/crv55824.2022.00024","title":"A Permutation Model for the Self-Supervised Stereo Matching Problem","year":2022,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Artificial intelligence; Computer science; Matching (statistics); Generalization; Permutation (music); Monocular; Heuristic; Computer vision; Representation (politics); Context (archaeology); Benchmark (surveying); Stereopsis; Pattern recognition (psychology); Machine learning; Mathematics; Statistics","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":[0.0002241665,0.00005762894,0.00004966812,0.0000316831,0.0005593589,0.0001078587,0.000507606,0.000005136619,0.00002296617],"category_scores_gemma":[0.000003967579,0.00003967849,0.0000403237,0.0001364718,0.000004672157,0.0004138362,0.0003122233,0.00007849448,0.000003975316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003572317,"about_ca_system_score_gemma":0.00004536733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004732158,"about_ca_topic_score_gemma":0.000001285831,"domain_scores_codex":[0.9993704,0.00002346954,0.0001063945,0.0001866834,0.000173284,0.0001397618],"domain_scores_gemma":[0.9995947,0.00009037479,0.00003219074,0.0002282716,0.0000312643,0.00002323456],"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":[0.000008506933,0.00006622642,0.00001430562,0.0000171431,0.00001268868,0.000001023255,0.01469938,0.382008,0.001420888,0.1774674,0.001124007,0.4231604],"study_design_scores_gemma":[0.0002272262,0.00001946296,0.000007679701,0.0000013292,0.000002254544,0.000005662526,0.0004761248,0.9665384,0.00005177678,0.03092207,0.001683423,0.00006455606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006071319,0.00002783639,0.9935306,0.004306227,0.00007697636,0.0003284891,0.000001496018,0.0002115271,0.0009097588],"genre_scores_gemma":[0.285482,0.000002044043,0.7107719,0.002415086,0.00001098997,0.0001556217,0.000001330224,0.00000650352,0.00115456],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5845304,"threshold_uncertainty_score":0.4302193,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02518348330761993,"score_gpt":0.2801547789523273,"score_spread":0.2549712956447073,"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."}}