{"id":"W4387211475","doi":"10.1007/978-3-031-43898-1_55","title":"Trust Your Neighbours: Penalty-Based Constraints for Model Calibration","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Constraint (computer-aided design); Smoothing; Pixel; Mathematical optimization; Flexibility (engineering); Artificial intelligence; Segmentation; Perspective (graphical); Code (set theory); Data mining; Machine learning; Algorithm; Computer vision; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004098668,0.001597655,0.00194329,0.0008906178,0.0008996492,0.002237021,0.004085242,0.00363698,0.008251997],"category_scores_gemma":[0.02637533,0.001444871,0.001111503,0.001409558,0.002026656,0.004984464,0.004966911,0.004867611,0.001699971],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009020186,"about_ca_system_score_gemma":0.001085317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003724436,"about_ca_topic_score_gemma":0.003952962,"domain_scores_codex":[0.9978505,0.001124965,0.0000981554,0.0003143982,0.0004908426,0.0001212293],"domain_scores_gemma":[0.9928067,0.004804957,0.000499789,0.0008744612,0.0007369343,0.0002771588],"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":[0.0001469002,0.00004266946,0.0002671793,0.0001297958,0.00004659629,0.0001004596,0.00007654056,0.8354899,0.001267693,0.1075109,0.004121752,0.05079957],"study_design_scores_gemma":[0.000008503765,0.00001186471,0.00003306324,0.00001314932,0.000003625703,0.00001449482,0.00000605376,0.9566994,0.0002495396,0.04213396,0.0008173984,0.000008854854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002568755,0.0001390066,0.9943417,0.0002020849,0.00005398486,0.00001813736,0.00005864294,0.0001369722,0.002480601],"genre_scores_gemma":[0.3738057,0.0006070194,0.6089956,0.0003976853,0.0002259889,0.0003333745,0.0006902814,0.001079601,0.01386471],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008251997,"threshold_uncertainty_score":0.02760565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0470612905123171,"score_gpt":0.2920188113869439,"score_spread":0.2449575208746268,"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."}}