{"id":"W4319349118","doi":"10.1145/3563040","title":"DeltaShield: Information Theory for Human- Trafficking Detection","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Science Foundation","keywords":"Computer science; Interpretability; Scalability; Spotting; Domain (mathematical analysis); Law enforcement; Laptop; Information retrieval; Data mining; Matching (statistics); Artificial intelligence; Database","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":[0.0006332241,0.0001864712,0.0001557928,0.0003763043,0.0006806618,0.0005933723,0.002010606,0.0001313036,0.00001615228],"category_scores_gemma":[0.0001544485,0.0001884134,0.0001036413,0.0008425924,0.00003364773,0.006602312,0.00008667887,0.000229214,0.0003382978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007100953,"about_ca_system_score_gemma":0.00005987423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009401159,"about_ca_topic_score_gemma":0.0004845151,"domain_scores_codex":[0.9986272,0.00009537957,0.0003150055,0.0004896586,0.0001946755,0.0002780675],"domain_scores_gemma":[0.996879,0.0007663606,0.0000954904,0.002125558,0.00007054691,0.00006303997],"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":[0.00008668934,0.0001351518,0.000008893056,0.00003999065,0.0001042914,9.80983e-7,0.002211351,0.0014339,0.002689994,0.003465039,0.001486737,0.988337],"study_design_scores_gemma":[0.005684058,0.001329409,0.006331579,0.0004413805,0.0004941474,0.0000232048,0.002527423,0.4810002,0.1280696,0.2296849,0.141801,0.002613155],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0232463,0.00003823528,0.9724162,0.0001899207,0.002057566,0.0003279022,0.0008128742,0.000727051,0.0001839567],"genre_scores_gemma":[0.9949484,0.00003112354,0.003158568,0.0001020658,0.0001910333,0.0001110334,0.001203721,0.00001859898,0.0002353959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9857239,"threshold_uncertainty_score":0.7683275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05985050683720564,"score_gpt":0.3110097719310146,"score_spread":0.2511592650938089,"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."}}