{"id":"W4416353551","doi":"10.48550/arxiv.2511.12039","title":"Positive Characteristic Sets for Relational Pattern Languages","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Relevance (law); Context (archaeology); Set (abstract data type); Class (philosophy); Word (group theory); String (physics); Statistical relational learning; Relational database","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"],"consensus_categories":[],"category_scores_codex":[0.0006348526,0.0006073086,0.0006439467,0.0002402841,0.0005303251,0.0002665042,0.001292595,0.0004120447,0.0001923876],"category_scores_gemma":[0.0004359123,0.0006309623,0.0004055746,0.0002646128,0.0001010752,0.0002354174,0.001533248,0.001348835,0.0003538063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001321469,"about_ca_system_score_gemma":0.0004092359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002733026,"about_ca_topic_score_gemma":0.000009030833,"domain_scores_codex":[0.9963631,0.0003160288,0.0007125186,0.001542791,0.0004204075,0.0006451737],"domain_scores_gemma":[0.9968523,0.0009790743,0.0005801846,0.001018479,0.0003856891,0.0001842324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006444778,0.0003956665,0.6063458,0.0009083445,0.0006092976,0.0001381439,0.006105119,0.001523602,0.0001368248,0.002793175,0.001313418,0.3796662],"study_design_scores_gemma":[0.0005338394,0.0001367827,0.7478773,0.0008058144,0.00009625674,0.00001739784,0.00004030467,0.2459927,0.0001179596,0.000423379,0.003333858,0.0006244309],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.296723,0.0004409164,0.6866415,0.007612565,0.004057252,0.001069607,0.0009077738,0.0003683592,0.002178973],"genre_scores_gemma":[0.9673215,0.00007001399,0.01237151,0.001812249,0.001251964,0.0002038329,0.0009215319,0.00003894456,0.01600842],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.67427,"threshold_uncertainty_score":0.9996142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0309174079851195,"score_gpt":0.3145953865389807,"score_spread":0.2836779785538612,"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."}}