{"id":"W4226208814","doi":"10.1007/978-3-030-99736-6_41","title":"Another Look at DPR: Reproduction of Training and Replication of Retrieval","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Information retrieval; Question answering; Replication (statistics); Codebase; Ranking (information retrieval); Scope (computer science); Encoder; Artificial intelligence; Natural language processing; Programming language; Source code","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001606292,0.0002043861,0.0003716173,0.0004376895,0.0001222591,0.00004244679,0.001174635,0.0001242389,0.00002950652],"category_scores_gemma":[0.0001763519,0.0002060814,0.00006140753,0.0003903054,0.0004101282,0.0003092718,0.001149978,0.0003206839,8.602676e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001848167,"about_ca_system_score_gemma":0.0002263395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002058207,"about_ca_topic_score_gemma":0.000008629913,"domain_scores_codex":[0.9969221,0.00003310708,0.0005179225,0.001598011,0.0007028959,0.0002259931],"domain_scores_gemma":[0.9970088,0.0001771042,0.0004940056,0.002131669,0.0001467755,0.00004162575],"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":[0.00001778205,0.00001974106,0.0001661271,0.00008869878,0.00001185199,0.000006974035,0.004860323,0.02785309,0.00669732,0.02577607,0.000007599627,0.9344944],"study_design_scores_gemma":[0.0005226089,0.0005199859,0.0004894102,0.0004331413,0.00002194652,0.0002446992,0.000001874416,0.8034599,0.04850119,0.1399849,0.005004734,0.0008156357],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003330078,0.0005906721,0.9933462,0.0005308404,0.0006224572,0.0002514731,0.000002783902,0.00004799768,0.001277564],"genre_scores_gemma":[0.567528,0.0001016802,0.4311284,0.0003207762,0.0002731945,0.000004660073,0.000004043729,0.0000304337,0.0006088119],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9336788,"threshold_uncertainty_score":0.8403758,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03770741802576652,"score_gpt":0.2571676180958307,"score_spread":0.2194602000700642,"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."}}