{"id":"W4410432646","doi":"10.32473/flairs.38.1.138913","title":"Creating Domain-Specific Datasets for Intelligent Environmental Feature Comparison","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Advanced Computational Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Windsor","funders":"","keywords":"Domain (mathematical analysis); Feature (linguistics); Computer science; Artificial intelligence; Data mining; Pattern recognition (psychology); Information retrieval; 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":[0.002348991,0.001137452,0.0007173264,0.006773276,0.001003006,0.001996932,0.002485445,0.001792912,0.002493997],"category_scores_gemma":[0.009873876,0.0004143671,0.001561844,0.00511487,0.0008315207,0.003744878,0.003232079,0.002006299,0.002068526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001356506,"about_ca_system_score_gemma":0.001054856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008477127,"about_ca_topic_score_gemma":0.02319186,"domain_scores_codex":[0.9972801,0.000635454,0.0002557122,0.0009890916,0.0006356302,0.0002039198],"domain_scores_gemma":[0.9948171,0.001246288,0.0004440193,0.002012797,0.001193159,0.0002866468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004936531,0.001805678,0.09170217,0.003161316,0.000696157,0.001199636,0.001692284,0.1089779,0.02708492,0.030856,0.2604746,0.4718557],"study_design_scores_gemma":[0.0001772154,0.0003036142,0.09982429,0.0008583984,0.0002122304,0.001127943,0.007541972,0.3140211,0.0387319,0.05268278,0.4841581,0.0003605357],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.1806583,0.001194155,0.4025927,0.002183981,0.0006149773,0.002255847,0.3606459,0.02470475,0.02514944],"genre_scores_gemma":[0.1619617,0.0003423419,0.3820376,0.0004055675,0.00005786034,0.001302148,0.4514647,0.0009186005,0.00150951],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.008477127,"threshold_uncertainty_score":0.01685554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1059942501670421,"score_gpt":0.4030994945546468,"score_spread":0.2971052443876047,"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."}}