{"id":"W2094154930","doi":"10.1145/1498698.1564507","title":"An experimental investigation of set intersection algorithms for text searching","year":2009,"lang":"en","type":"article","venue":"ACM Journal of Experimental Algorithmics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Intersection (aeronautics); Context (archaeology); Set (abstract data type); Computer science; Algorithm; Theoretical computer science; Randomized algorithm; Information retrieval; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01357784,0.002003091,0.002437027,0.004347849,0.002110477,0.003180409,0.004360543,0.002915689,0.005356369],"category_scores_gemma":[0.07633378,0.000828636,0.001229983,0.01035625,0.001858535,0.0100238,0.002966919,0.002504588,0.002053349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003162829,"about_ca_system_score_gemma":0.003032711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00566234,"about_ca_topic_score_gemma":0.004351618,"domain_scores_codex":[0.9735156,0.01100332,0.003365615,0.002809769,0.008079876,0.001225744],"domain_scores_gemma":[0.9079359,0.06547686,0.002809742,0.01448052,0.008281083,0.001015889],"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":[0.01764018,0.006767702,0.01547404,0.003142161,0.001037632,0.0002803172,0.001016191,0.1580258,0.02467954,0.02127401,0.0330486,0.7176138],"study_design_scores_gemma":[0.002385447,0.005987216,0.00850171,0.0001481137,0.0003915657,0.0008763836,0.001230593,0.8830354,0.05911114,0.02395898,0.01418534,0.0001880235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7971624,0.008279687,0.1471307,0.001881431,0.0007701963,0.001566219,0.00574924,0.01509611,0.02236395],"genre_scores_gemma":[0.6515135,0.00142655,0.3300089,0.0003507946,0.0002331611,0.001273325,0.01041007,0.001221005,0.003562612],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01357784,"threshold_uncertainty_score":0.07180738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0479229736013965,"score_gpt":0.3482190534161552,"score_spread":0.3002960798147586,"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."}}