{"id":"W3170865782","doi":"","title":"Environment Inference for Invariant Learning","year":2021,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Inference; Invariant (physics); Computer science; Benchmark (surveying); Artificial intelligence; Machine learning; Generalization; Domain (mathematical analysis); 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004480733,0.0002213695,0.0002045564,0.0001607582,0.0003213911,0.0005373575,0.0007502225,0.00007953634,0.001149699],"category_scores_gemma":[0.001076201,0.0002300981,0.0001164352,0.0001536348,0.00003941971,0.0003954193,0.0003184841,0.0007258935,0.0003268163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009904318,"about_ca_system_score_gemma":0.0001311195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002383119,"about_ca_topic_score_gemma":0.000007886951,"domain_scores_codex":[0.9979162,0.0002479907,0.0003407217,0.0006288132,0.0005442062,0.0003220757],"domain_scores_gemma":[0.9986851,0.0004466908,0.0002249054,0.0002690419,0.0002460262,0.0001283034],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003928259,0.0001046553,0.003564078,0.00001171964,0.00007088757,0.00005884545,0.001085335,0.06121727,0.007545754,0.8346936,0.00005946588,0.09154909],"study_design_scores_gemma":[0.0007656515,0.0001786115,0.001154233,0.00005732675,0.000005838288,0.00002269403,0.0002062722,0.8522096,0.001067171,0.00695359,0.1370773,0.0003017301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002923856,0.00007081348,0.9520864,0.005371264,0.0004877423,0.0001382824,0.000004785062,0.0002347889,0.03868203],"genre_scores_gemma":[0.940451,0.0001530233,0.04604184,0.0007896795,0.0001206631,0.00005053015,0.0001205284,0.00002187523,0.01225093],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9375271,"threshold_uncertainty_score":0.9997634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04867667267188184,"score_gpt":0.3042943594813409,"score_spread":0.2556176868094591,"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."}}