{"id":"W2113673066","doi":"10.1109/hicss.2008.129","title":"Document Retrieval Using Proximity-Based Phrase Searching","year":2008,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Phrase; Computer science; Section (typography); Information retrieval; Vector space model; Phrase search; Space (punctuation); Matching (statistics); Natural language processing; Artificial intelligence; Search engine; Web search query; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001787403,0.0006540954,0.001650142,0.004941037,0.000875283,0.001788605,0.001128098,0.001171269,0.005360343],"category_scores_gemma":[0.007351538,0.00037211,0.0008384587,0.006159962,0.0006554474,0.003478409,0.001728929,0.0006019794,0.004849879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004578597,"about_ca_system_score_gemma":0.0007710198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002310074,"about_ca_topic_score_gemma":0.001785062,"domain_scores_codex":[0.9978333,0.0005341019,0.0002277109,0.0004264256,0.000859366,0.0001190334],"domain_scores_gemma":[0.9975939,0.001223501,0.0002556223,0.0004455505,0.0004183923,0.00006300673],"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":[0.0009128754,0.0002646683,0.002193966,0.0007724536,0.0002022623,0.0003722743,0.0005323716,0.01810165,0.09091999,0.01820109,0.009811529,0.8577149],"study_design_scores_gemma":[0.0005294721,0.001852541,0.00615947,0.0001292388,0.0003294351,0.004020183,0.0005562206,0.7371859,0.150548,0.05664087,0.0416837,0.0003648814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03893954,0.002049031,0.9485933,0.0001542773,0.00009730574,0.0004992398,0.0005357909,0.004427772,0.004703775],"genre_scores_gemma":[0.2557648,0.001204418,0.7365171,0.0001185847,0.0002396404,0.0003732327,0.001294712,0.0001975088,0.004290063],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005360343,"threshold_uncertainty_score":0.01793212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06451732651132608,"score_gpt":0.2951161408177277,"score_spread":0.2305988143064017,"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."}}