{"id":"W3102769546","doi":"10.22215/etd/2020-14277","title":"A Graph-Based Indexing Technique for Efficient Searching in Large Scale Textual Documents","year":2020,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Search engine indexing; Hash table; Inverted index; Hash function; Graph; Workload; Information retrieval; Search engine; Latency (audio); Data mining; Theoretical computer science; Operating system; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006925485,0.0003817933,0.0005232213,0.001086198,0.0001670646,0.0001445313,0.001411902,0.0002811017,0.00001207184],"category_scores_gemma":[0.0001061063,0.0003780266,0.0002952138,0.001453408,0.00001981782,0.0002607662,0.000173023,0.0005890132,0.000007528427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001876517,"about_ca_system_score_gemma":0.0002246942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004924169,"about_ca_topic_score_gemma":0.0005662811,"domain_scores_codex":[0.9971516,0.00009327283,0.0005811537,0.001003932,0.000584955,0.000585065],"domain_scores_gemma":[0.9986704,0.0001682112,0.0002733241,0.0006122257,0.0001503606,0.00012547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001116465,0.005344843,0.006306377,0.005392094,0.0006617556,0.0003683429,0.02424515,0.02032529,0.2538449,0.5221885,0.003454902,0.1567513],"study_design_scores_gemma":[0.001642385,0.0003535665,0.0006953133,0.001049132,0.00005526108,0.000002324397,0.0008915013,0.5237631,0.4426739,0.02501643,0.002194492,0.001662586],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001982947,0.00004082461,0.9912568,0.0001143924,0.00006574998,0.00170665,0.000009722971,0.0005979141,0.004224999],"genre_scores_gemma":[0.4552626,0.000004938628,0.5421944,0.000257443,0.00002918516,0.001241052,0.000368672,0.00005151198,0.0005902557],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5034378,"threshold_uncertainty_score":0.9998671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01070877636662772,"score_gpt":0.3233975948074325,"score_spread":0.3126888184408048,"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."}}