{"id":"W2473775606","doi":"10.29173/cais748","title":"Scanning Compressed Full Text Files","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University; Acadia University","funders":"","keywords":"Computer science; Inverted index; Compression (physics); Data compression; Index (typography); Data file; File format; Information retrieval; Computer graphics (images); Database; World Wide Web; Search engine indexing; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0003549948,0.000292485,0.0004616556,0.0001559949,0.0002063602,0.004034424,0.004414137,0.0001378113,0.00007727228],"category_scores_gemma":[0.003447747,0.0002109769,0.0001563646,0.0004766085,0.0003187633,0.01719531,0.002125952,0.0002890544,0.00001957791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003140621,"about_ca_system_score_gemma":0.0001642501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004269905,"about_ca_topic_score_gemma":0.000003074215,"domain_scores_codex":[0.9979186,0.00002533902,0.0005276441,0.0004559566,0.0005896815,0.0004827813],"domain_scores_gemma":[0.9719942,0.0001623188,0.0007389475,0.0004457899,0.02647935,0.0001794037],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001884171,0.0008912985,0.08727375,0.001118105,0.000337423,0.000006444815,0.06746746,0.0001234649,0.369233,0.1271113,0.1679262,0.1783231],"study_design_scores_gemma":[0.002697658,0.001276307,0.3749599,0.002478906,0.0001323488,0.0001813759,0.004431719,0.1724353,0.2102273,0.04289107,0.1862162,0.002071831],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9798232,0.0002476319,0.006198375,0.002687158,0.0003081243,0.00052694,0.0001044843,0.0001456274,0.009958503],"genre_scores_gemma":[0.9866727,0.00003991187,0.01254212,0.0002124743,0.00008745954,0.00004030516,0.00000423356,0.0000171988,0.0003835908],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2876862,"threshold_uncertainty_score":0.9969995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01860486368640987,"score_gpt":0.2325702940413815,"score_spread":0.2139654303549716,"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."}}