{"id":"W2564000433","doi":"10.1145/2996913.2996956","title":"Enhancing scene parsing by transferring structures via efficient low-rank graph matching","year":2016,"lang":"en","type":"article","venue":"","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Parsing; Computer science; Graph; Rank (graph theory); Matching (statistics); Artificial intelligence; Theoretical computer science; Mathematics; Combinatorics; 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":[0.0004166828,0.0002067563,0.0001859886,0.0001399521,0.0003065009,0.0001421253,0.0006713895,0.00006012731,0.00005451894],"category_scores_gemma":[0.000008581927,0.0001339703,0.0001202222,0.000321444,0.00006549499,0.0003540589,0.00008966552,0.0001110115,0.00002161746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002671856,"about_ca_system_score_gemma":0.0000168737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002481506,"about_ca_topic_score_gemma":0.000006242826,"domain_scores_codex":[0.9983647,0.00008781871,0.0002778242,0.0004871316,0.000290621,0.0004918578],"domain_scores_gemma":[0.9992281,0.0001425764,0.0000449624,0.0004095318,0.00003259856,0.000142196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00000809812,0.00004414125,0.00003006685,0.00002312301,0.00002295081,0.00001126789,0.001161892,0.0006039575,0.811357,0.05960499,0.00002527815,0.1271072],"study_design_scores_gemma":[0.0005651954,0.00004581688,0.0002370922,0.00017676,0.000007570891,0.00003120243,0.00006056653,0.005606133,0.8503098,0.1425063,0.0000439062,0.000409662],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3174448,0.00008522097,0.6813394,0.0002136081,0.0003563679,0.00007447687,0.00000180955,0.0002090779,0.000275154],"genre_scores_gemma":[0.970511,0.00000737946,0.02913923,0.0002124969,0.00004551763,0.000003978535,5.172577e-7,0.00001325683,0.00006660795],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6530662,"threshold_uncertainty_score":0.5463151,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004861370804278732,"score_gpt":0.2037992309609231,"score_spread":0.1989378601566444,"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."}}