{"id":"W2097162546","doi":"10.1109/icpr.1994.576328","title":"Recognizing volumetric objects in the presence of uncertainty","year":2002,"lang":"en","type":"article","venue":"","topic":"Image and Object Detection Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; A priori and a posteriori; Artificial intelligence; Parametric statistics; Context (archaeology); Object (grammar); Set (abstract data type); Process (computing); Key (lock); Machine learning; Probability density function; Cognitive neuroscience of visual object recognition; Conditional probability distribution; Pattern recognition (psychology); Data mining; 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":[0.0003944369,0.00005600932,0.00007833438,0.000229823,0.00004044325,0.00005124849,0.00069234,0.00002946117,0.00004739789],"category_scores_gemma":[0.0002061089,0.00003710928,0.0000350027,0.001643337,0.00002499717,0.0003055541,0.00007844528,0.0001037817,0.00002143557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001645036,"about_ca_system_score_gemma":0.000007563407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003486801,"about_ca_topic_score_gemma":0.00006399892,"domain_scores_codex":[0.9992647,0.00009124567,0.0001561232,0.0001560517,0.0001901477,0.000141712],"domain_scores_gemma":[0.9993095,0.0002108069,0.00004781604,0.0003659242,0.00005173947,0.00001417757],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000002011139,0.0001245725,0.0005281938,0.00001826717,0.000004464411,0.00002021018,0.003862197,0.00004294969,0.001062839,0.001740819,0.009106926,0.9834865],"study_design_scores_gemma":[0.0006963168,0.0007015782,0.008066937,0.00009529194,0.000007998209,0.0001116235,0.001224608,0.4536895,0.5117949,0.01427989,0.008741105,0.0005902592],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02940851,0.0006940394,0.7916574,0.001105806,0.0003438966,0.0005604153,6.493707e-7,0.0005127921,0.1757164],"genre_scores_gemma":[0.9873829,0.00004811668,0.01162966,0.0003507556,0.00001517361,0.00001244399,5.804057e-8,0.00000204803,0.0005587994],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9828963,"threshold_uncertainty_score":0.1513272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02562943105250544,"score_gpt":0.2360566652436295,"score_spread":0.2104272341911241,"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."}}