{"id":"W7091188132","doi":"","title":"Iterative Amortized Inference: Unifying In-Context Learning and Learned Optimizers","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Leverage (statistics); Inference; Scalability; Task (project management); Generalization; Context (archaeology); Iterative and incremental development; Key (lock); Range (aeronautics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000438707,0.0001615527,0.0002342177,0.0002748448,0.0002362228,0.0002235,0.0003036697,0.00007676047,0.0000413215],"category_scores_gemma":[0.0005127694,0.0001612603,0.00004275173,0.0006852038,0.00008174567,0.000539583,0.0002460122,0.0004828317,0.00004609712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005161264,"about_ca_system_score_gemma":0.000104289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000561226,"about_ca_topic_score_gemma":0.00003491135,"domain_scores_codex":[0.9985944,0.0002275686,0.0002964356,0.0004418041,0.0001402002,0.000299589],"domain_scores_gemma":[0.9991701,0.0003652168,0.0001097193,0.0002027651,0.00007457253,0.00007768784],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000451204,0.0000392805,0.8737387,0.00002659132,0.00003922636,0.00003927605,0.01211538,0.003410573,0.001903428,0.02308192,0.0000400943,0.08552042],"study_design_scores_gemma":[0.005745422,0.0001951661,0.6554881,0.0004501653,0.00002148823,0.000008724966,0.01047746,0.3020946,0.001535003,0.002052822,0.0211024,0.0008286235],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8196844,0.0003149894,0.1677271,0.001188663,0.000190203,0.0001557132,1.464102e-7,0.00017012,0.01056866],"genre_scores_gemma":[0.9891899,0.0000908541,0.006202559,0.0007466041,0.00001329476,0.00001697209,0.000002209578,0.000007817228,0.003729764],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.298684,"threshold_uncertainty_score":0.6576005,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04017124907675231,"score_gpt":0.3162799663917387,"score_spread":0.2761087173149864,"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."}}