{"id":"W4403780071","doi":"10.48550/arxiv.2409.13687","title":"A Bottom-Up Approach to Class-Agnostic Image Segmentation","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Class (philosophy); Segmentation; Computer science; Image (mathematics); Computer vision; Artificial intelligence; Top-down and bottom-up design; Geology; Software engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001407908,0.0003922101,0.0002917145,0.0004978742,0.00008874949,0.001006097,0.001974836,0.0001497333,0.000007242873],"category_scores_gemma":[0.00008045604,0.0004631098,0.000263524,0.001022008,0.0001009965,0.0007601597,0.004684228,0.0005547806,0.001157503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002905086,"about_ca_system_score_gemma":0.0003251641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000921476,"about_ca_topic_score_gemma":0.000004440319,"domain_scores_codex":[0.9975055,0.00007209922,0.0002068223,0.001587588,0.0001980131,0.0004299084],"domain_scores_gemma":[0.9979859,0.00008044757,0.0001163329,0.001274294,0.0001706565,0.0003723854],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005901363,0.001015182,0.000488023,0.001228259,0.0004647619,0.001093712,0.001350652,0.1337574,0.0005440668,0.7867056,0.06937978,0.003913551],"study_design_scores_gemma":[0.0007739447,0.0001137745,0.0004856348,0.0004251185,0.0004571408,0.00002399549,0.0002398927,0.7251775,0.001073646,0.267958,0.001694646,0.001576793],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1726222,0.0002031429,0.7172326,0.0004498667,0.00528447,0.001210688,0.0001698234,0.001859279,0.1009679],"genre_scores_gemma":[0.9811282,0.00001474118,0.01286972,0.0003301994,0.0001843367,0.000006855749,0.00006599273,0.00003910103,0.005360906],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.808506,"threshold_uncertainty_score":0.9997821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05059498197141481,"score_gpt":0.2012697275964091,"score_spread":0.1506747456249943,"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."}}