{"id":"W4409369453","doi":"10.1609/aaai.v39i3.32306","title":"Weakly Supervised Gland Segmentation with Class Semantic Consistency and Purified Labels Filtration","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Natural Science Foundation of Guangxi Province; National Natural Science Foundation of China","keywords":"Consistency (knowledge bases); Segmentation; Class (philosophy); Artificial intelligence; Filtration (mathematics); Computer science; Pattern recognition (psychology); Natural language processing; 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":[0.0002613694,0.0001734381,0.0002057041,0.0001281071,0.0002006364,0.0002699126,0.0006414739,0.00006477523,0.000009165142],"category_scores_gemma":[0.0001837783,0.0001210962,0.00003831356,0.0006604958,0.0002477375,0.0006372872,0.0001546068,0.0001750027,0.000004775971],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002823019,"about_ca_system_score_gemma":0.00009958218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002227246,"about_ca_topic_score_gemma":0.00001309395,"domain_scores_codex":[0.9987554,0.00001706125,0.0003602195,0.0003944596,0.0002743393,0.0001985182],"domain_scores_gemma":[0.9989074,0.0000934686,0.0002058293,0.0002108382,0.0005390833,0.00004330875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008580594,0.00006734938,0.0005905612,0.00008124827,0.00001625422,5.211327e-7,0.0005097614,0.000003975359,0.2143891,0.67409,0.00007104417,0.1100943],"study_design_scores_gemma":[0.00004690448,0.0002253441,0.0004334834,0.0002952424,0.00001667376,0.000003704406,0.0003502825,0.008129917,0.867942,0.1223767,0.0000474768,0.0001322616],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2146967,0.000112846,0.7635083,0.006859117,0.0001985543,0.001104563,0.000005143147,0.0002300253,0.01328477],"genre_scores_gemma":[0.9860435,0.0001180293,0.01318909,0.0003137611,0.00001279823,0.000029794,7.231134e-7,0.000005876338,0.0002864096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7713468,"threshold_uncertainty_score":0.4938161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04124428987364722,"score_gpt":0.2967333376570722,"score_spread":0.255489047783425,"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."}}