{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005395335,0.002202571,0.002909558,0.001192081,0.0007006634,0.002803676,0.005853589,0.003382941,0.002728482],"category_scores_gemma":[0.01857941,0.001697802,0.00169716,0.001307499,0.002826852,0.007036007,0.005234818,0.00527528,0.0009059526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002256768,"about_ca_system_score_gemma":0.00244374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004569184,"about_ca_topic_score_gemma":0.005513312,"domain_scores_codex":[0.9971634,0.001308477,0.0001481301,0.0007221284,0.0004430277,0.0002148885],"domain_scores_gemma":[0.9937453,0.00392236,0.0003833497,0.001272088,0.0004430505,0.0002337379],"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":[0.0001720285,0.0001414581,0.00101278,0.0002003313,0.0001816406,0.00008254238,0.0002411664,0.8162138,0.001688827,0.08903145,0.003451058,0.08758294],"study_design_scores_gemma":[0.000007969575,0.00002102513,0.0000335492,0.00001200338,0.00001098073,0.00001196076,0.000005484491,0.9651694,0.0003765462,0.03387727,0.0004659857,0.00000773281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004168375,0.0004142762,0.993717,0.000339391,0.00003421206,0.00003926934,0.00003821019,0.0005927739,0.0006563856],"genre_scores_gemma":[0.4387772,0.0009304666,0.5525545,0.001150587,0.0003847724,0.000622304,0.0004422807,0.0009008631,0.004237076],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005853589,"threshold_uncertainty_score":0.02853364,"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."}}