{"id":"W6910242600","doi":"10.48448/ydjr-6529","title":"Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Generalization; Scheme (mathematics); Source code; Language model; Labrador Retriever","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000923578,0.0003654736,0.0004368779,0.002258347,0.0001362009,0.00007024918,0.001020281,0.0001690102,0.006190066],"category_scores_gemma":[0.0001621515,0.0003744678,0.00006609275,0.004571617,0.000623574,0.000447377,0.0003469507,0.0002608035,0.0002029517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008247941,"about_ca_system_score_gemma":0.001132083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004593601,"about_ca_topic_score_gemma":0.001650624,"domain_scores_codex":[0.9961604,0.0001296657,0.0005847545,0.0008980092,0.001706587,0.0005205434],"domain_scores_gemma":[0.9982079,0.00003451175,0.0007303861,0.0007597303,0.0001399437,0.0001275176],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001809387,0.001116784,0.001052417,0.000328376,0.0001820762,0.0001204027,0.006231077,0.1402667,0.602061,0.04572185,0.1900515,0.01268691],"study_design_scores_gemma":[0.00387689,0.0004892437,0.0005416741,0.0002325063,0.000176784,0.00003136797,0.003871953,0.9248029,0.01759067,0.004023977,0.04214485,0.002217182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.09166594,0.005347974,0.01466631,0.0002867487,0.002435945,0.00461327,0.00201199,0.001661539,0.8773103],"genre_scores_gemma":[0.4089467,0.0003414568,0.04150065,0.0009187114,0.0005914525,0.0002209665,0.003649529,0.002372892,0.5414577],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.7845362,"threshold_uncertainty_score":0.9998707,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02381995500744872,"score_gpt":0.2974050496978124,"score_spread":0.2735850946903637,"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."}}