{"id":"W3176369597","doi":"10.1609/aaai.v35i17.17798","title":"Over-MAP: Structural Attention Mechanism and Automated Semantic Segmentation Ensembled for Uncertainty Prediction","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Measure (data warehouse); Segmentation; Identification (biology); Artificial intelligence; Machine learning; Scale (ratio); Data mining; Mechanism (biology); Cartography","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":[0.0007892689,0.0002098269,0.0002601405,0.00007363829,0.0003865397,0.0003658378,0.0004017935,0.00009536894,0.0002915929],"category_scores_gemma":[0.0006411604,0.0001645237,0.00007263225,0.0002600779,0.0002216539,0.0003598843,0.0001777348,0.0001252754,0.00002395321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000062951,"about_ca_system_score_gemma":0.00008567149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006776344,"about_ca_topic_score_gemma":0.00002287088,"domain_scores_codex":[0.998055,0.00005210252,0.0005535253,0.0005597204,0.0004651698,0.0003144903],"domain_scores_gemma":[0.9984834,0.0001073416,0.0004691402,0.0001685695,0.0007028163,0.00006870072],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000868923,0.00002630155,0.0002164947,0.0001344453,0.000005740554,2.568653e-7,0.0004169087,0.0006155468,0.8903611,0.1072017,0.00004376154,0.0008907586],"study_design_scores_gemma":[0.00005294367,0.0001099701,0.0007313839,0.0001373482,0.0000236182,0.000006898135,0.0004423287,0.3187502,0.6117997,0.06783,0.000004017896,0.0001116558],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9933477,0.00001003618,0.003658154,0.0009248428,0.00111131,0.000564986,0.00005095662,0.0001867821,0.0001452529],"genre_scores_gemma":[0.9950013,0.00001065808,0.004601333,0.00008310349,0.00008146172,0.00005173868,0.000009461583,0.00001517677,0.0001458146],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3181346,"threshold_uncertainty_score":0.6709083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03547439520278665,"score_gpt":0.307192391213684,"score_spread":0.2717179960108973,"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."}}