{"id":"W4405104912","doi":"10.1007/978-3-031-72890-7_9","title":"SAFT: Towards Out-of-Distribution Generalization in Fine-Tuning","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; Cisco Systems (Canada)","funders":"","keywords":"Computer science; Generalization; Distribution (mathematics); Algorithm; Artificial intelligence; Mathematics; Mathematical analysis","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":[0.003328563,0.001272607,0.001813376,0.0007257229,0.0006033694,0.001198727,0.002133207,0.002339931,0.006205063],"category_scores_gemma":[0.01000687,0.000788595,0.001401926,0.0007237045,0.001713043,0.002326631,0.00379336,0.003345751,0.001602477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006505111,"about_ca_system_score_gemma":0.0008654209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001734215,"about_ca_topic_score_gemma":0.002574584,"domain_scores_codex":[0.9987568,0.0004673644,0.00005826923,0.0002839202,0.0003391767,0.00009452079],"domain_scores_gemma":[0.9966205,0.002055897,0.0001552498,0.0007881424,0.0002528723,0.0001273672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003134241,0.0002014274,0.00108105,0.0003407707,0.0002443038,0.0002277668,0.0002568935,0.4426403,0.01567795,0.2077447,0.01411923,0.3171521],"study_design_scores_gemma":[0.0000141671,0.00003507033,0.0001020842,0.00001399504,0.00001252173,0.0000452387,0.000008515735,0.9032857,0.001306083,0.09282057,0.00234582,0.00001024369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00336851,0.0002067401,0.9932896,0.0001273098,0.00006526395,0.00001756011,0.00003954881,0.001057288,0.001828148],"genre_scores_gemma":[0.3190262,0.0007053774,0.6568051,0.001148338,0.0004022313,0.0002600437,0.0004842306,0.002573344,0.01859512],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006205063,"threshold_uncertainty_score":0.02075797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02970034779102624,"score_gpt":0.2917598775713738,"score_spread":0.2620595297803476,"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."}}