{"id":"W2562960946","doi":"10.1109/itsc.2016.7795907","title":"Generic hypothesis generation for small and distant objects","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Object (grammar); Homogeneous; Variety (cybernetics); Automotive industry; Object detection; Image (mathematics); Key (lock); Computer vision; Scheme (mathematics); Pattern recognition (psychology); Voting; Machine learning; 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":[],"consensus_categories":[],"category_scores_codex":[0.00008850511,0.00006700237,0.00006922348,0.0000327486,0.00005890874,0.00005362012,0.0001507761,0.00002381564,0.000003484771],"category_scores_gemma":[0.00008516668,0.00003874206,0.00002324945,0.00007571528,0.00001929986,0.0003040186,0.00006175046,0.00001072343,0.000003251505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001697804,"about_ca_system_score_gemma":0.00001345274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002015868,"about_ca_topic_score_gemma":0.000006645031,"domain_scores_codex":[0.9994905,0.00001083568,0.00008903501,0.0002323925,0.00005114868,0.0001260812],"domain_scores_gemma":[0.9995642,0.0001058247,0.00002920652,0.0002138576,0.00004602526,0.00004083163],"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":[0.000002826281,0.00000781172,0.00003530887,0.000003843564,0.000002644333,9.055058e-7,0.00002349272,9.64636e-8,0.2951441,0.01396124,0.000669486,0.6901483],"study_design_scores_gemma":[0.0002033479,0.0001376373,0.0002149293,0.000007789639,0.000002829327,0.000005426298,0.000002599251,0.003079875,0.9571722,0.02985211,0.009181475,0.0001397918],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00494456,0.0001301256,0.9935752,0.0006476227,0.00005168817,0.0001521197,0.000001543526,0.0001742962,0.0003229065],"genre_scores_gemma":[0.3177303,0.0001859574,0.680517,0.0003582432,0.00006809321,0.00003393125,3.159367e-7,0.000006009039,0.001100144],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6900085,"threshold_uncertainty_score":0.1579855,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06775736436148054,"score_gpt":0.2593020941395209,"score_spread":0.1915447297780404,"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."}}