{"id":"W2141694739","doi":"10.1145/544220.544227","title":"Using librarian techniques in automatic text summarization for information retrieval","year":2002,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; National Science Foundation","keywords":"Automatic summarization; Computer science; Information retrieval; Multi-document summarization; Operationalization; World Wide Web; Seekers","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001745935,0.00005560534,0.00006818036,0.0001894735,0.00004302127,0.0001823298,0.0002367058,0.00005398975,0.00002114809],"category_scores_gemma":[0.00007036253,0.00005348331,0.0000180985,0.0003310636,0.000005524303,0.002781347,0.0000642765,0.0000402905,0.00000827992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004705786,"about_ca_system_score_gemma":0.00001801776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001766506,"about_ca_topic_score_gemma":0.000002640354,"domain_scores_codex":[0.9994064,0.00001598217,0.0002443976,0.00009853002,0.0001107923,0.0001238718],"domain_scores_gemma":[0.9996465,0.0000356776,0.00005977416,0.0002029914,0.00003289836,0.00002216537],"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":[0.000003246497,0.00004505165,0.0009966616,0.0001010985,0.000004764284,8.852608e-7,0.00259881,0.001900134,0.001067333,0.2917525,0.0006087351,0.7009208],"study_design_scores_gemma":[0.0001114882,0.00001446401,0.0001034668,0.00001991478,8.430733e-7,0.000001892191,0.0000112206,0.9927732,0.003034415,0.002890473,0.0009693433,0.00006925187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00478232,0.00000694333,0.9888841,0.0003957358,0.000073863,0.0002831223,3.674327e-7,0.0003090876,0.00526447],"genre_scores_gemma":[0.3513265,0.000001866166,0.6482898,0.0002642121,0.00002142999,0.000005559114,0.000002049548,0.000002821044,0.00008575132],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9908731,"threshold_uncertainty_score":0.2180986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04868112608135101,"score_gpt":0.2590906807895311,"score_spread":0.2104095547081801,"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."}}