{"id":"W2950472498","doi":"10.48550/arxiv.1208.0092","title":"Efficient Indexing and Querying over Syntactically Annotated Trees","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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); Index (typography); Tree (set theory); Natural language; Information retrieval; Artificial intelligence; Natural language processing; Mathematics; Combinatorics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002512206,0.0002879731,0.0002833993,0.0002078289,0.0002215176,0.0002151049,0.0009560817,0.0002429458,0.00002247749],"category_scores_gemma":[0.00003197384,0.0002931907,0.00008972795,0.0003231449,0.00008718522,0.00036825,0.00397271,0.0005451752,0.00002401373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001153077,"about_ca_system_score_gemma":0.00009254162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002149153,"about_ca_topic_score_gemma":0.00001160643,"domain_scores_codex":[0.9982648,0.0001121683,0.000176306,0.0009189034,0.0001232497,0.000404577],"domain_scores_gemma":[0.9983985,0.0001462621,0.0001940418,0.000927365,0.00008366709,0.0002501408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001491939,0.0007955832,0.0273378,0.0003408152,0.0003790329,0.001292389,0.002153276,0.501699,0.00111128,0.4441233,0.0008558108,0.01976248],"study_design_scores_gemma":[0.0003224561,0.00001908172,0.01404477,0.0001613167,0.00004317234,0.000009620625,0.00003088752,0.9815536,0.00006182515,0.002812188,0.000528754,0.0004123623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.408002,0.0001563705,0.5902749,0.00003948645,0.0004291882,0.0001406982,0.00001308444,0.0001763438,0.0007679071],"genre_scores_gemma":[0.9949676,0.00006979335,0.004626765,0.00005946137,0.00007672639,5.172035e-7,0.00001189165,0.00001406896,0.0001732162],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5869656,"threshold_uncertainty_score":0.999952,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05404926755246188,"score_gpt":0.1964002652671958,"score_spread":0.1423509977147339,"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."}}