{"id":"W2062666034","doi":"10.2495/data070181","title":"Performance of information retrieval models using term co-occurrences","year":2007,"lang":"en","type":"article","venue":"WIT transactions on information and communication technologies","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Vector space model; Term Discrimination; Divergence-from-randomness model; Scalability; Standard Boolean model; Set (abstract data type); Exploit; Term (time); Information retrieval; Boolean model; Data mining; Artificial intelligence; Search engine; Boolean function; Concept search; Database; Algorithm; Boolean expression","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":[0.0004646818,0.0001139954,0.0001277675,0.0005135251,0.0003495737,0.0001296985,0.0007161415,0.0001354896,0.000003542514],"category_scores_gemma":[0.00001655874,0.0001002033,0.00002994007,0.0005631058,0.0001885494,0.005756904,0.00003233875,0.0002223865,0.000007587429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000413164,"about_ca_system_score_gemma":0.00003929546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001366383,"about_ca_topic_score_gemma":0.000001684951,"domain_scores_codex":[0.9989845,0.00001833929,0.0005375574,0.00007164453,0.000237196,0.000150749],"domain_scores_gemma":[0.9988065,0.00007072022,0.0003099515,0.0006349055,0.0001529304,0.00002499342],"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":[0.00004514275,0.0000437619,0.0001577121,0.00005616529,0.00001484818,4.648992e-8,0.002219526,0.005398454,0.00006083931,0.04080079,0.00001775413,0.951185],"study_design_scores_gemma":[0.0007169543,0.0004248592,0.002004714,0.0001383858,0.00001552791,0.00002875594,0.004943255,0.9644034,0.01929692,0.005211222,0.002441475,0.0003745439],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06714952,0.00009089003,0.9278893,0.000367836,0.00005548561,0.0001988284,0.00001171114,0.0004667255,0.00376974],"genre_scores_gemma":[0.9515982,0.00122263,0.04708104,0.00007238056,0.000001066031,0.000006275867,0.00001455571,0.000001649574,0.000002183517],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9590049,"threshold_uncertainty_score":0.4173616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0288517107677187,"score_gpt":0.2618619079778876,"score_spread":0.2330101972101689,"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."}}