{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006673021,0.0005429607,0.0005910068,0.00040226,0.001059211,0.001087594,0.0021251,0.0002194784,0.00004233732],"category_scores_gemma":[0.0006343332,0.0004993869,0.0002546225,0.0009616135,0.0003329526,0.002799523,0.0007650969,0.000660686,0.00005949385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003431843,"about_ca_system_score_gemma":0.0003208624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005199529,"about_ca_topic_score_gemma":0.00005424822,"domain_scores_codex":[0.9966655,0.00008036793,0.00101035,0.0005468421,0.0006702965,0.001026659],"domain_scores_gemma":[0.9972539,0.0006626198,0.0005634242,0.001088919,0.0002628286,0.0001682884],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002377217,0.0001570024,0.03381094,0.0003336039,0.0001607313,0.000019277,0.002597424,0.003471997,0.00002036953,0.8753341,0.00357265,0.08028417],"study_design_scores_gemma":[0.02174044,0.00261518,0.02747855,0.003775734,0.000556967,0.0003054056,0.01771833,0.5620476,0.01134885,0.08552437,0.2592492,0.007639399],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1229838,0.0001460346,0.8258072,0.003116298,0.005775291,0.00113405,0.00006055238,0.0009127441,0.04006404],"genre_scores_gemma":[0.9689566,0.00001049335,0.02820072,0.001238153,0.000176626,0.0001410881,0.00006380346,0.00003070805,0.001181778],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8459728,"threshold_uncertainty_score":0.9999494,"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."}}