{"id":"W4409880954","doi":"10.1007/s10994-025-06777-2","title":"Prioritizing the essential: A robust evaluation framework for novelty detection","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Novelty; Novelty detection; Computer science; Artificial intelligence; Machine learning; Psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001613514,0.0001098843,0.0001047622,0.0001190614,0.0004953674,0.0003157817,0.000642727,0.00007338471,0.000004126758],"category_scores_gemma":[0.001751057,0.00008964839,0.00005764575,0.0004619907,0.00002463832,0.000263165,0.0003061212,0.000339408,0.00000334574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007754016,"about_ca_system_score_gemma":0.00005703301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009320044,"about_ca_topic_score_gemma":0.00005114939,"domain_scores_codex":[0.9988842,0.0001804628,0.000178075,0.0003286473,0.0002311715,0.0001974411],"domain_scores_gemma":[0.9987692,0.0005125697,0.0001138607,0.0004644184,0.0001213462,0.00001859553],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001312551,0.00002819596,0.001180348,0.0000347876,0.00003275501,7.861565e-7,0.0005800901,0.002275218,0.004670242,0.07915508,0.0002655111,0.9117638],"study_design_scores_gemma":[0.0001885528,0.00005566347,0.001456967,0.00009059616,0.00002974607,0.000005199048,0.00003153791,0.9526073,0.00423351,0.03234152,0.008846926,0.000112484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003942125,0.0001562672,0.9923199,0.001534281,0.0003636219,0.0004360536,0.000002182636,0.0005641669,0.0006814091],"genre_scores_gemma":[0.6299542,0.000004973301,0.3695362,0.0001793453,0.00007217137,0.0001256066,0.00001076326,0.000008948909,0.0001077669],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9503321,"threshold_uncertainty_score":0.3810015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02530489185627873,"score_gpt":0.3263598317383786,"score_spread":0.3010549398820999,"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."}}