{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003860266,0.0006165113,0.0006008243,0.003499278,0.0008468808,0.001356046,0.001166461,0.0004824695,0.004031256],"category_scores_gemma":[0.002708633,0.0002818548,0.0005683007,0.006833958,0.0006260802,0.004216988,0.0009419319,0.000768543,0.001996613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009189371,"about_ca_system_score_gemma":0.001609712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005575947,"about_ca_topic_score_gemma":0.007265229,"domain_scores_codex":[0.9993673,0.00006672793,0.0000542095,0.0001112505,0.0003483784,0.00005219161],"domain_scores_gemma":[0.9983348,0.0005694006,0.0001702755,0.0004234475,0.0004358692,0.00006627702],"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":[0.0004076556,0.0002627275,0.002131537,0.001152161,0.0001113011,0.0003633247,0.0006474818,0.01946017,0.121438,0.05979752,0.03377772,0.7604504],"study_design_scores_gemma":[0.0002309836,0.0009356725,0.00413047,0.0001995308,0.0002525068,0.002729918,0.0009702634,0.5562594,0.1564862,0.1145126,0.1630267,0.000265745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03972537,0.002485621,0.9324942,0.0006697125,0.0002378062,0.0005420628,0.002763343,0.01125813,0.009823722],"genre_scores_gemma":[0.2044715,0.002003866,0.7806152,0.0002624051,0.0001525993,0.0003075881,0.005361562,0.000674435,0.006150858],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005575947,"threshold_uncertainty_score":0.01348597,"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."}}