{"id":"W4285327104","doi":"10.1109/hpcc-dss-smartcity-dependsys53884.2021.00029","title":"QHash: An efficient hashing algorithm for low-variance image deduplication","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Data deduplication; Computer science; Hash function; Variance (accounting); Algorithm; Image (mathematics); Artificial intelligence; Database; 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":[0.0009466733,0.00062598,0.0008185289,0.001153645,0.0007451309,0.0008673589,0.001429442,0.0006373434,0.003260417],"category_scores_gemma":[0.003011265,0.0003253806,0.0005349873,0.001279175,0.0007702532,0.00186771,0.001706055,0.0008478751,0.001492322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000484032,"about_ca_system_score_gemma":0.001183177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00166241,"about_ca_topic_score_gemma":0.002508454,"domain_scores_codex":[0.9992338,0.0001018345,0.00007434644,0.0001386013,0.0003862957,0.00006507149],"domain_scores_gemma":[0.9987261,0.0003023617,0.0001211426,0.0004214185,0.0003624025,0.00006655259],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005926582,0.000172677,0.001316526,0.0003332742,0.0000987384,0.0002473408,0.0003251627,0.05666244,0.0611257,0.01367371,0.01606706,0.8493848],"study_design_scores_gemma":[0.0001481068,0.0005581831,0.00120148,0.00004910314,0.00004025013,0.0009199361,0.000260827,0.8462776,0.103448,0.01710442,0.02987709,0.0001150405],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02212701,0.00163016,0.970167,0.0002053702,0.0002715583,0.0002314865,0.0003506606,0.003448411,0.001568374],"genre_scores_gemma":[0.2993809,0.0009287887,0.6896156,0.0002560403,0.0001805576,0.0002752935,0.001572577,0.0002864103,0.007503774],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003260417,"threshold_uncertainty_score":0.01090711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01332619600184324,"score_gpt":0.275116293645711,"score_spread":0.2617900976438677,"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."}}