{"id":"W2051101123","doi":"10.1145/1031171.1031182","title":"Scoring missing terms in information retrieval tasks","year":2004,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Ministério da Educação; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Query expansion; Information retrieval; Vocabulary; Web query classification; Web search query; Ranking (information retrieval); Query language; Query optimization; Focus (optics); RDF query language; Sargable; Natural language processing; Search engine; Artificial intelligence","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":[0.000323442,0.00006956605,0.0000717537,0.0002351532,0.00008100389,0.0003143258,0.0003441408,0.00004386888,0.00001844819],"category_scores_gemma":[0.00005699603,0.00005855634,0.00002710993,0.0005782774,0.00001654189,0.004456128,0.0001102386,0.0001325487,0.0002334738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001222491,"about_ca_system_score_gemma":0.00009428301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006151929,"about_ca_topic_score_gemma":0.00000366008,"domain_scores_codex":[0.9990799,0.00001041207,0.0002862551,0.00008050503,0.0003196001,0.0002233178],"domain_scores_gemma":[0.9996125,0.00001356796,0.00005003841,0.0001974452,0.00005587168,0.00007060904],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006189079,0.0001351721,0.006382465,0.00009126973,0.00000699358,0.0000464499,0.01458018,0.003764147,0.004422068,0.4240198,0.0001742781,0.5463153],"study_design_scores_gemma":[0.01195998,0.0007645286,0.3749879,0.0005714936,0.00001036864,0.0002769221,0.001099117,0.1771201,0.3529326,0.05318564,0.0247876,0.00230367],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2446763,0.000005249308,0.7323537,0.001586991,0.000263849,0.0001959967,7.828993e-7,0.0001989899,0.02071815],"genre_scores_gemma":[0.9738291,0.000002929641,0.02546442,0.0005978241,0.00001588577,0.000001872594,0.00000395177,0.000001756597,0.00008228619],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7291528,"threshold_uncertainty_score":0.3230586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01795538351522202,"score_gpt":0.2604083802063343,"score_spread":0.2424529966911123,"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."}}