{"id":"W4296878065","doi":"10.1007/978-3-031-17120-8_31","title":"Coarse-to-Fine Retriever for Better Open-Domain Question Answering","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Labrador Retriever; Computer science; Domain (mathematical analysis); Representation (politics); Construct (python library); Information retrieval; Artificial intelligence; Reading (process); Natural language processing; Linguistics; Mathematics; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00239712,0.002615534,0.003106172,0.004197723,0.001235617,0.003716076,0.003114237,0.003156121,0.05008301],"category_scores_gemma":[0.01035542,0.001056055,0.002196875,0.003262992,0.0008846363,0.01005956,0.006411635,0.003650459,0.04441892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008302132,"about_ca_system_score_gemma":0.001679229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00366304,"about_ca_topic_score_gemma":0.007217957,"domain_scores_codex":[0.9974093,0.0006308859,0.0003251309,0.0008009514,0.0005555954,0.0002782112],"domain_scores_gemma":[0.9935096,0.002234727,0.0001412127,0.00273459,0.001048727,0.0003311237],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008201114,0.0006521488,0.001143177,0.0009180281,0.0001327056,0.0003638044,0.0004331142,0.003504741,0.05533867,0.01007125,0.154652,0.7719702],"study_design_scores_gemma":[0.0005226311,0.0008632884,0.003445056,0.000273361,0.000423458,0.002049963,0.001277337,0.5554572,0.1290105,0.1033955,0.202963,0.0003185968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0292887,0.003209458,0.7698499,0.001460321,0.001090423,0.0007435098,0.008192949,0.1726635,0.01350118],"genre_scores_gemma":[0.137403,0.001053219,0.7980401,0.001499232,0.0007878595,0.00042299,0.03068357,0.008193841,0.02191618],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05008301,"threshold_uncertainty_score":0.1675444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02721815459113205,"score_gpt":0.2740297315924848,"score_spread":0.2468115770013527,"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."}}