{"id":"W4413267863","doi":"10.1145/3696630.3728530","title":"LicenseGPT: A Fine-tuned Foundation Model for Publicly Available Dataset License Compliance","year":2025,"lang":"en","type":"article","venue":"","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; Huawei Technologies (Canada)","funders":"","keywords":"Foundation (evidence); License; Compliance (psychology); Computer science; Computer security; Law","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005455521,0.000154084,0.0002412508,0.0004264591,0.0004670105,0.001815332,0.001512662,0.00004563773,0.001412376],"category_scores_gemma":[0.003451415,0.0001206778,0.00008333002,0.001482306,0.00008149694,0.0007444152,0.0007343663,0.00007212003,0.003282747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004754218,"about_ca_system_score_gemma":0.0001620808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001099404,"about_ca_topic_score_gemma":0.0005768068,"domain_scores_codex":[0.9968581,0.0000657733,0.0006824855,0.001211755,0.0007950139,0.0003868798],"domain_scores_gemma":[0.9958348,0.001097242,0.0001821559,0.002272584,0.0005118919,0.0001012977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003474367,0.00006633252,0.0001308714,0.0000104974,0.00001126562,4.053674e-7,0.00003847118,0.001545333,0.00007259232,0.01432215,0.9470603,0.03670704],"study_design_scores_gemma":[0.0003122314,0.000009516163,0.00009478305,0.00001091454,0.000008034836,3.313819e-7,0.00006628484,0.5513734,0.00007218814,0.007896278,0.4400733,0.00008279944],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.002505481,0.00003414822,0.9492694,0.006474514,0.001158364,0.0006280009,0.001054828,0.0001472171,0.03872805],"genre_scores_gemma":[0.1558812,0.00000719006,0.09832378,0.007457015,0.0001254528,0.0001342095,0.004352608,0.00001931966,0.7336993],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8509456,"threshold_uncertainty_score":0.9995005,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3884682337846641,"score_gpt":0.4575310168340584,"score_spread":0.06906278304939434,"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."}}