{"id":"W4284682639","doi":"10.1145/3477495.3531749","title":"Document Expansion Baselines and Learned Sparse Lexical Representations for MS MARCO V1 and V2","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; Compute Canada","keywords":"Computer science; Weighting; Ranking (information retrieval); Information retrieval; Natural language processing; Question answering; Artificial intelligence; Sequence (biology); Term (time); Language model; Artificial neural network","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001526615,0.00008904668,0.000104898,0.0003688351,0.0003300511,0.0003108454,0.0006904452,0.00003220329,0.00002190827],"category_scores_gemma":[0.001214879,0.00007237348,0.00001479483,0.0002281691,0.00008835553,0.0009043782,0.001443504,0.0002490274,0.000001238287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009277496,"about_ca_system_score_gemma":0.0001779871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002557187,"about_ca_topic_score_gemma":0.000001880336,"domain_scores_codex":[0.998242,0.00002136329,0.0004038375,0.00022709,0.0009130947,0.0001926331],"domain_scores_gemma":[0.998913,0.0002919951,0.0001402317,0.0001120368,0.0004716372,0.00007104644],"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":[0.001439768,0.0002073145,0.0384203,0.0003186254,0.00006454066,0.00000114309,0.01393472,0.0002627872,0.002537197,0.8314957,0.002298551,0.1090193],"study_design_scores_gemma":[0.007039919,0.00124962,0.1039736,0.0005152453,0.00000758668,0.0000803282,0.01098811,0.4835165,0.031948,0.3110262,0.04879773,0.000857198],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9736354,0.00002614416,0.007580247,0.01617964,0.0002401138,0.0007380152,0.00001195187,0.00002664518,0.001561796],"genre_scores_gemma":[0.9760315,0.0000942314,0.02332602,0.0001696233,0.00001855362,0.0001078509,0.00001090716,0.000003074768,0.0002382072],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5204695,"threshold_uncertainty_score":0.2997489,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1205216399447767,"score_gpt":0.3619357305030352,"score_spread":0.2414140905582585,"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."}}