{"id":"W1767311454","doi":"10.1007/11550518_62","title":"Object Categorization and the Need for Many-to-Many Matching","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Categorization; Computer science; Cognitive neuroscience of visual object recognition; Bridging (networking); Artificial intelligence; Object (grammar); Matching (statistics); Bridge (graph theory); Pattern recognition (psychology); Natural language processing; Computer vision; Mathematics","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":[0.001070258,0.0003976749,0.0004387981,0.0004933743,0.0003843325,0.0006799358,0.002092163,0.0001784576,0.000002734383],"category_scores_gemma":[0.0001561948,0.0002844981,0.000101316,0.0004952665,0.0004738851,0.0007456091,0.001061665,0.0004505186,0.000007271051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000157725,"about_ca_system_score_gemma":0.0001708175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001785449,"about_ca_topic_score_gemma":0.00001769837,"domain_scores_codex":[0.9974754,0.00002847121,0.0004049919,0.001079388,0.0005241455,0.0004876463],"domain_scores_gemma":[0.9978133,0.0007455191,0.0002146587,0.0008956266,0.0002168972,0.0001139967],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002221526,0.000006527721,0.000003582685,0.00002469701,0.00000597404,0.000006201049,0.001012714,0.003834567,0.0001708907,0.1605837,0.00002498066,0.8343039],"study_design_scores_gemma":[0.0005672458,0.0001748078,0.00003801965,0.0002120061,0.00001141568,0.00004998928,4.240464e-7,0.2583313,0.005423547,0.7294556,0.005174542,0.0005611115],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001661101,0.0005194535,0.994351,0.002436386,0.0005167358,0.001116322,0.000003344462,0.0002156177,0.0008245576],"genre_scores_gemma":[0.05911243,0.000171172,0.9342207,0.005173796,0.0006458505,0.00004798529,0.000003849671,0.00004129739,0.0005829188],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8337428,"threshold_uncertainty_score":0.9999607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01319591343664738,"score_gpt":0.2679685007766699,"score_spread":0.2547725873400226,"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."}}