{"id":"W2425458534","doi":"10.1145/2882903.2914838","title":"Searching Web Data using MinHash LSH","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Locality-sensitive hashing; Computer science; Search engine indexing; Index (typography); Information retrieval; Hash function; World Wide Web; Hash table; Computer security","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":[0.001190499,0.0004584675,0.0009698421,0.002548608,0.0008717955,0.001386905,0.001460716,0.0006888299,0.006602877],"category_scores_gemma":[0.00575785,0.0003599365,0.000424504,0.003532494,0.0007847104,0.003712872,0.001543252,0.0005977676,0.002381816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006440437,"about_ca_system_score_gemma":0.001186839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002328163,"about_ca_topic_score_gemma":0.00379421,"domain_scores_codex":[0.9988117,0.000208971,0.0001157481,0.0001671677,0.0005890187,0.0001073848],"domain_scores_gemma":[0.9971307,0.0009503341,0.0002125559,0.00100797,0.0006165343,0.00008189314],"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":[0.0006890182,0.0002225842,0.003951459,0.0004931539,0.00009949601,0.000171292,0.0003224306,0.01830797,0.04081972,0.01959921,0.01180069,0.903523],"study_design_scores_gemma":[0.0001420794,0.0009410548,0.003666939,0.00006524918,0.00005991862,0.001418663,0.0005411555,0.793911,0.09434339,0.07620058,0.0285505,0.0001594536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08696111,0.002345584,0.8967841,0.0006364398,0.0003077776,0.0003011108,0.001338603,0.006637528,0.004687786],"genre_scores_gemma":[0.4395608,0.0006946329,0.5514839,0.0004859259,0.000258488,0.0002651562,0.001989857,0.0002521875,0.00500904],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006602877,"threshold_uncertainty_score":0.02208883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1440010960189437,"score_gpt":0.3833650304849872,"score_spread":0.2393639344660435,"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."}}