{"id":"W2157788896","doi":"10.1109/robot.1990.126278","title":"Heuristic relaxation approaches for 3-D object recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Heuristic; Object (grammar); Computer science; Relaxation (psychology); Cognitive neuroscience of visual object recognition; Representation (politics); Artificial intelligence; Tree (set theory); Theoretical computer science; Machine learning; Algorithm; Pattern recognition (psychology); Mathematics; Combinatorics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001859177,0.00005730393,0.00005432163,0.00005364496,0.0001012279,0.00006326361,0.0001771485,0.00003005636,0.00004819667],"category_scores_gemma":[0.0000564771,0.00004920704,0.00004576939,0.000163045,0.00001516015,0.000285686,0.00002077229,0.00003611851,0.000128647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007119893,"about_ca_system_score_gemma":0.000002582138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000101891,"about_ca_topic_score_gemma":6.349055e-7,"domain_scores_codex":[0.9995006,0.00003156029,0.00009419742,0.000187198,0.00006808757,0.0001184132],"domain_scores_gemma":[0.9996371,0.0001010018,0.00003814941,0.0001656212,0.00002809497,0.0000300177],"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":[0.000002848823,0.00008152061,0.00002065437,0.00001439295,0.00000858469,0.000001033004,0.0004740873,0.00003464582,0.00004688386,0.2760906,0.001413711,0.7218111],"study_design_scores_gemma":[0.0002812327,0.0001095828,0.0002317327,0.000007094136,0.000005436276,0.00001069016,0.00003373985,0.5913476,0.001535663,0.4054266,0.0008660808,0.000144587],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003050983,0.00004318034,0.9806993,0.0003110823,0.0001794857,0.0001581691,0.000001848318,0.0001644014,0.01539158],"genre_scores_gemma":[0.8676318,0.000006656989,0.1305097,0.0001685261,0.00006499056,0.00005319648,0.000007291726,0.00000481623,0.001553025],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8645808,"threshold_uncertainty_score":0.2006605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08661393962803618,"score_gpt":0.2222201019998742,"score_spread":0.135606162371838,"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."}}