{"id":"W4295915865","doi":"10.1007/978-3-031-16452-1_26","title":"Leveraging Labeling Representations in Uncertainty-Based Semi-supervised Segmentation","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Representation (politics); Inference; Consistency (knowledge bases); Pattern recognition (psychology); Pixel; Image segmentation; Scale-space segmentation; Labeled data; Machine learning","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006646795,0.0004316421,0.0003899884,0.001075433,0.0004998799,0.0003008654,0.002568557,0.0001328445,0.00006858959],"category_scores_gemma":[0.00006924638,0.0004785358,0.00010104,0.0018212,0.0002767077,0.0007542886,0.001052805,0.001015554,0.00001625266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008903122,"about_ca_system_score_gemma":0.0005529279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007133514,"about_ca_topic_score_gemma":0.0001306318,"domain_scores_codex":[0.995902,0.00007993765,0.0006556487,0.001746625,0.0009909957,0.0006247857],"domain_scores_gemma":[0.9970775,0.0009315762,0.0003036104,0.001416297,0.0001446894,0.0001263506],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003212262,0.00002120842,0.0001191014,0.00001222938,0.000002701908,0.00003246726,0.0005501636,0.8251259,0.0004941286,0.005962937,0.000007182863,0.1676688],"study_design_scores_gemma":[0.0004098935,0.00004590896,0.00007663538,0.000127315,0.000004639698,0.00001473802,0.000001205935,0.9334088,0.0007219911,0.06397567,0.0007375351,0.0004756969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003407448,0.0002107237,0.9945505,0.002171295,0.0006766167,0.0007521707,0.000006830943,0.0002132262,0.001077858],"genre_scores_gemma":[0.1322292,0.00006181293,0.8633134,0.003648112,0.0002363236,0.0001924395,0.00007535097,0.00005907152,0.0001842249],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1671931,"threshold_uncertainty_score":0.9997666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02901881521604102,"score_gpt":0.2846402789262108,"score_spread":0.2556214637101698,"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."}}