{"id":"W4399368852","doi":"10.21428/d82e957c.3da7f032","title":"POPCat: Propagation of Particles for Complex Annotation Tasks","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Pipeline (software); Segmentation; Annotation; Margin (machine learning); Set (abstract data type); Video tracking; Computer vision; Precision and recall; Pattern recognition (psychology); Object (grammar); Generalization; Tracking (education); Object detection; Frame (networking); 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":[0.0007739825,0.0001192115,0.0002099088,0.00009834568,0.00003178794,0.0001374933,0.0003996342,0.00008900555,0.00000457353],"category_scores_gemma":[0.00008844429,0.0001011402,0.0001096499,0.0001615355,0.00002643442,0.0000783053,0.0004366271,0.0001279842,0.00001140829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002021447,"about_ca_system_score_gemma":0.0001095884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004221015,"about_ca_topic_score_gemma":0.00002032239,"domain_scores_codex":[0.9989035,0.00008522163,0.0003185231,0.000381814,0.0001742792,0.0001366784],"domain_scores_gemma":[0.9990199,0.0001622478,0.000157778,0.0004412712,0.0001910749,0.00002778843],"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":[0.00001750971,0.00009859072,0.0006633129,0.001892761,0.0001071155,0.000002640809,0.001520431,0.003736066,0.01652597,0.3556441,0.003506386,0.6162851],"study_design_scores_gemma":[0.0001275074,0.00005835058,0.006999834,0.0001021393,0.00001651999,0.000001617042,0.00001325236,0.5454283,0.02689421,0.4194443,0.0007421137,0.0001719195],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.016319,0.0001386062,0.9796891,0.001680933,0.0006326169,0.000473633,0.00002087732,0.0002113877,0.0008338539],"genre_scores_gemma":[0.6172177,0.000004858684,0.3825024,0.00005370063,0.00005733148,0.00006225316,0.00002758603,0.000007067972,0.0000671236],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6161132,"threshold_uncertainty_score":0.4124379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.101955014632766,"score_gpt":0.3708137294391684,"score_spread":0.2688587148064023,"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."}}