{"id":"W2123553648","doi":"10.1109/crv.2006.9","title":"An Efficient Match-based Duplication Detection Algorithm","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"Laurentian University","funders":"","keywords":"Sorting; Block (permutation group theory); Computer science; Matching (statistics); Tree (set theory); Set (abstract data type); Algorithm; Process (computing); Image (mathematics); Pattern recognition (psychology); Pattern matching; Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001237566,0.00008200786,0.00005728782,0.0001205136,0.0001256855,0.00008721431,0.0003279705,0.0000431004,0.000002266301],"category_scores_gemma":[0.000001019266,0.0000716237,0.00003880054,0.0003203755,0.00002357224,0.0002214082,0.00002280633,0.00005001922,0.000007332228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002311311,"about_ca_system_score_gemma":0.000008271752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007623852,"about_ca_topic_score_gemma":0.000008235685,"domain_scores_codex":[0.9993045,0.00002885742,0.0001241459,0.0002597172,0.0001332862,0.0001494387],"domain_scores_gemma":[0.9994122,0.00001359439,0.00004641688,0.00044634,0.00004962859,0.00003176379],"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":[0.000007052115,0.0003937029,0.0003574849,0.000009240195,0.000003298782,0.000005897162,0.00005019484,0.01519099,0.0488131,0.052631,0.0001208927,0.8824171],"study_design_scores_gemma":[0.00007736171,0.00005692963,0.002352785,0.00000296174,0.000001100485,0.000002946976,0.000001277424,0.6737295,0.3122589,0.01065591,0.0007606655,0.000099659],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01079737,0.000008812806,0.986702,0.0001038665,0.00007539058,0.0001168279,6.510712e-7,0.00129178,0.0009033038],"genre_scores_gemma":[0.6045025,3.033286e-7,0.3953612,0.00006810689,0.00002457394,0.00001940267,0.00000314727,0.00000325338,0.00001744601],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8823175,"threshold_uncertainty_score":0.292073,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005601988642990031,"score_gpt":0.230800204207591,"score_spread":0.225198215564601,"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."}}