{"id":"W4409687339","doi":"10.59275/j.melba.2025-c1d9","title":"GeoLS: an Intensity-based, Geodesic Soft Labeling for Image Segmentation","year":2025,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Digital Image Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Computer vision; Segmentation; Artificial intelligence; Intensity (physics); Geodesic; Computer science; Image segmentation; Image (mathematics); Mathematics; Physics; Geometry; Optics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00323065,0.0001599277,0.000250242,0.0003569004,0.0003574322,0.0004563604,0.001103304,0.00003690429,0.000002057992],"category_scores_gemma":[0.00138267,0.0001121185,0.000131059,0.0003778208,0.0002190899,0.001286335,0.0001773524,0.0004245961,0.000001024164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007555635,"about_ca_system_score_gemma":0.0001874805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001667095,"about_ca_topic_score_gemma":7.131522e-7,"domain_scores_codex":[0.9985505,0.0001187723,0.0005076391,0.0001901937,0.0003242362,0.0003086765],"domain_scores_gemma":[0.9979478,0.0006862385,0.0004406787,0.0002218844,0.000603279,0.0001001833],"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":[0.0002708567,0.0002214069,0.0005423191,0.0002605699,0.00007014731,0.00001605326,0.0004782605,0.0007645815,0.05172096,0.0008695245,0.003289079,0.9414963],"study_design_scores_gemma":[0.001041376,0.0003189793,0.00004329053,0.0003204467,0.0000741063,0.00009406867,0.00008054056,0.9551473,0.01542486,0.01981831,0.007486294,0.000150458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002225371,0.0005398453,0.9860309,0.01047674,0.0002690552,0.000215157,0.000002760974,0.0001807288,0.00005945509],"genre_scores_gemma":[0.2627817,0.0000121944,0.7346466,0.002283636,0.0001254275,0.00001239578,0.00001747262,0.00002292614,0.00009770429],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9543827,"threshold_uncertainty_score":0.4572062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01298276879040531,"score_gpt":0.3178742906932374,"score_spread":0.3048915219028321,"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."}}