{"id":"W4414829247","doi":"10.4230/lipics.csl.2026.25","title":"Constructing Witnesses for Lower Bounds on Behavioural Distances","year":2025,"lang":"en","type":"article","venue":"Leibniz-Zentrum für Informatik (Schloss Dagstuhl)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Leverhulme Trust","keywords":"Soundness; Mathematical proof; Bounding overwatch; Completeness (order theory); Probabilistic logic; Equivalence (formal languages); Constructive; Context (archaeology); Modal logic","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009099292,0.001079822,0.001282732,0.002962798,0.001687029,0.004163268,0.003589144,0.003122605,0.007387158],"category_scores_gemma":[0.07431809,0.001681215,0.002850425,0.001814299,0.005966547,0.01353937,0.01007944,0.009008871,0.001206403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002364244,"about_ca_system_score_gemma":0.001771084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000798827,"about_ca_topic_score_gemma":0.001061293,"domain_scores_codex":[0.9887465,0.002958746,0.0009511837,0.002742547,0.003767197,0.0008338797],"domain_scores_gemma":[0.9160919,0.06528445,0.003075179,0.009409643,0.005128747,0.001010123],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000161734,0.00008500712,0.001836178,0.0003723384,0.00008244479,0.000366454,0.0009247152,0.01757461,0.009280774,0.9337838,0.001324824,0.03420702],"study_design_scores_gemma":[0.00004340408,0.00006644464,0.0003310966,0.0001126739,0.00005845289,0.0001922605,0.0001664428,0.0690224,0.01318675,0.9125291,0.004234883,0.00005608122],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02688862,0.0001630044,0.965528,0.001271111,0.00008282685,0.00009490424,0.0002750415,0.000719275,0.004977158],"genre_scores_gemma":[0.5538665,0.0005381182,0.4389926,0.0008754485,0.0001714185,0.0004449342,0.0009704027,0.0006375234,0.003503055],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009099292,"threshold_uncertainty_score":0.04812223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01361237046816071,"score_gpt":0.3008382864708418,"score_spread":0.2872259160026811,"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."}}