{"id":"W4393147607","doi":"10.1609/aaai.v38i14.29497","title":"Lost Domain Generalization Is a Natural Consequence of Lack of Training Domains","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Generalization; Natural (archaeology); Training (meteorology); Domain (mathematical analysis); Computer science; Psychology; Artificial intelligence; Mathematics; History; Geography","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":[0.01020994,0.001267979,0.002731046,0.0009517904,0.001345162,0.002230376,0.003413636,0.002661652,0.002327694],"category_scores_gemma":[0.05860348,0.0009027743,0.001873523,0.001042708,0.004017218,0.005718099,0.00541513,0.005793569,0.0008539968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001654979,"about_ca_system_score_gemma":0.001509662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001679839,"about_ca_topic_score_gemma":0.001370526,"domain_scores_codex":[0.9919851,0.002362421,0.000679697,0.002627431,0.001819772,0.0005254721],"domain_scores_gemma":[0.9350708,0.04407,0.002608416,0.01482121,0.002257331,0.001172263],"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":[0.001311459,0.0006736055,0.02474609,0.0008643148,0.0003730636,0.0008668573,0.0006707516,0.5869668,0.01879187,0.06968399,0.01543028,0.279621],"study_design_scores_gemma":[0.0001058481,0.0005202451,0.004508443,0.00007975387,0.00006641657,0.0009794362,0.000172701,0.8138415,0.01304112,0.1612232,0.005412554,0.00004887616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1566231,0.001286615,0.8304766,0.003107807,0.0001460218,0.0002234399,0.000612159,0.001595732,0.005928625],"genre_scores_gemma":[0.7453358,0.0006085786,0.2466141,0.001866995,0.0001828077,0.0005236219,0.00136017,0.0004395319,0.003068411],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01020994,"threshold_uncertainty_score":0.05399591,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1468599123278508,"score_gpt":0.3403925985309042,"score_spread":0.1935326862030534,"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."}}