{"id":"W2966697812","doi":"","title":"Reproducibility and Stability Analysis in Metric-Based Few-Shot Learning.","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; HEC Montréal","funders":"","keywords":"Reproducibility; Metric (unit); Computer science; Stability (learning theory); Artificial intelligence; Mathematics; Machine learning; Statistics; Engineering","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":[0.002206817,0.0001921778,0.0003025848,0.001028774,0.0001647896,0.0004310761,0.0006349269,0.00008051328,0.001159796],"category_scores_gemma":[0.00346317,0.0002018477,0.0001372492,0.001892344,0.00008510314,0.0005500996,0.0001906586,0.0007412714,0.0001500382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001432349,"about_ca_system_score_gemma":0.0001468033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003127078,"about_ca_topic_score_gemma":0.00008913007,"domain_scores_codex":[0.9962305,0.0006531195,0.0005053504,0.001653073,0.0006882145,0.0002697241],"domain_scores_gemma":[0.9972625,0.0008941542,0.0002776687,0.001039189,0.0004092424,0.0001172204],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004695899,0.0001557883,0.8480616,0.00000927258,0.0001123677,0.000007643929,0.001999688,0.1014825,0.001031537,0.03954124,0.00001144112,0.007540025],"study_design_scores_gemma":[0.0005167928,0.00009360855,0.3845031,0.00001615215,0.00001696411,0.000001473962,0.0007054044,0.6119155,0.0002871461,0.0008694209,0.0008913936,0.0001830486],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8211414,0.00003071581,0.1111903,0.005156448,0.0003866127,0.0004267433,0.000004434991,0.0003010098,0.06136238],"genre_scores_gemma":[0.9940574,0.00001670012,0.003750503,0.0001636651,0.00002281114,0.00003463073,0.00005878191,0.00001043055,0.001885068],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.510433,"threshold_uncertainty_score":0.9997533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07488014056526597,"score_gpt":0.3486097859386539,"score_spread":0.273729645373388,"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."}}