{"id":"W4307895180","doi":"10.48550/arxiv.2205.09393","title":"Two-Step Question Retrieval for Open-Domain QA","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Search engine indexing; Inference; Computer science; Labrador Retriever; Information retrieval; Pipeline (software); Domain (mathematical analysis); Squid; Artificial intelligence; Mathematics; Programming language; Medicine; Biology; Fishery","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"],"consensus_categories":[],"category_scores_codex":[0.0009298014,0.0002664899,0.000329779,0.0002118964,0.0003263338,0.0002763473,0.004482411,0.0001731027,0.0000717369],"category_scores_gemma":[0.00005980096,0.0003448853,0.0001933885,0.0004410851,0.00004360858,0.0005016416,0.008012543,0.0005725177,0.00002084529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005215676,"about_ca_system_score_gemma":0.0003613552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003515788,"about_ca_topic_score_gemma":0.00005363087,"domain_scores_codex":[0.9975659,0.0002503122,0.0002348788,0.0014522,0.0001299595,0.0003667648],"domain_scores_gemma":[0.9976774,0.0001377714,0.0002745487,0.001636302,0.0001340323,0.0001399514],"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":[0.00007038895,0.00005399654,0.0003585001,0.00004676892,0.00003977751,0.00009920924,0.0001362893,0.1755811,0.00002477251,0.8226896,0.0003315085,0.0005680833],"study_design_scores_gemma":[0.001022453,0.00007652257,0.00009220955,0.00004784868,0.00003543805,0.000004401686,0.00009502855,0.7847887,0.00004657685,0.2075758,0.005780612,0.00043446],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05294235,0.0000508037,0.9397317,0.0002716774,0.001403255,0.000884261,0.00002667706,0.0002221193,0.004467164],"genre_scores_gemma":[0.9109378,0.0000342028,0.0836024,0.0002120428,0.0001567216,0.000005407864,0.00004231798,0.00002709402,0.004981997],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8579955,"threshold_uncertainty_score":0.9999003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09835796420991373,"score_gpt":0.2338652679081067,"score_spread":0.135507303698193,"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."}}