{"id":"W2102679851","doi":"10.14778/2350229.2350249","title":"Efficient indexing and querying over syntactically annotated trees","year":2012,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Search engine indexing; Parsing; Coding (social sciences); Set (abstract data type); Natural language; Index (typography); Tree (set theory); Information retrieval; Artificial intelligence; Natural language processing; 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":[0.0003400101,0.0001177337,0.000130706,0.00005742967,0.0001502918,0.0001008341,0.0004941204,0.00003454761,0.000005120908],"category_scores_gemma":[0.00006570981,0.00007379748,0.00004081841,0.0002136291,0.00004670719,0.0003831821,0.0009486343,0.000111213,0.000002263095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003859493,"about_ca_system_score_gemma":0.0000118284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003662682,"about_ca_topic_score_gemma":3.155108e-7,"domain_scores_codex":[0.9989588,0.000006712473,0.0001944441,0.0002050744,0.0003469398,0.0002879772],"domain_scores_gemma":[0.999485,0.00004881633,0.000152023,0.0001460741,0.00006933109,0.00009878416],"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":[0.00008911268,0.001229774,0.1162168,0.0003142767,0.0001753994,0.000002090545,0.01095908,0.0003332112,0.4279587,0.3540902,0.004356822,0.08427459],"study_design_scores_gemma":[0.002318281,0.0002780354,0.3477562,0.0009819949,0.0001034448,0.0001472227,0.0007539759,0.3043641,0.3257514,0.004362381,0.01214288,0.001040172],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.987073,0.0004955329,0.00827936,0.0007319494,0.0004067391,0.0003062612,0.0000035041,0.00008972422,0.002613914],"genre_scores_gemma":[0.9878318,0.00001380165,0.01193899,0.0001041264,0.00005436618,0.0000110665,2.184975e-7,0.000006298212,0.0000393116],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3497278,"threshold_uncertainty_score":0.3009374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01058726132777864,"score_gpt":0.2312921184450198,"score_spread":0.2207048571172411,"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."}}