{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005934482,0.0002289705,0.0003490046,0.0002832782,0.0001809697,0.0001596583,0.001497826,0.00009560204,0.000009229614],"category_scores_gemma":[0.00004718012,0.0002039671,0.0001840311,0.0002554845,0.00008171205,0.002437826,0.0002292361,0.0002368364,0.000001535251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001777017,"about_ca_system_score_gemma":0.0001116959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002264675,"about_ca_topic_score_gemma":2.84744e-7,"domain_scores_codex":[0.9979779,0.0001103829,0.0007407944,0.000319912,0.0005577921,0.0002932422],"domain_scores_gemma":[0.9981913,0.00009728653,0.0006138174,0.0005900039,0.0002581553,0.0002494203],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001329763,0.000499768,0.00007853331,0.000007240461,0.00003895554,0.00001812667,0.006040193,0.0001864432,0.9254264,0.001987977,0.0007378199,0.06484553],"study_design_scores_gemma":[0.001419881,0.004399514,0.00051291,0.00009515913,0.00001024052,0.0002683123,0.002258458,0.1190323,0.8681633,0.003411104,0.0001780025,0.0002508991],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4877282,0.0008274399,0.5100704,0.0001957608,0.0008624661,0.000228811,0.00001811646,0.00003683225,0.00003188791],"genre_scores_gemma":[0.6340944,0.00001392213,0.3654032,0.000141324,0.0003099772,0.00000425593,0.00001708303,0.00001117765,0.000004732221],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1463661,"threshold_uncertainty_score":0.8317535,"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."}}