{"id":"W4406482578","doi":"10.62441/nano-ntp.v20i7.4719","title":"Using Autoencoders for Anomaly and Drift Detection in Linguistic Segmentation on Product Review Platforms and Recommendation Systems","year":2024,"lang":"en","type":"article","venue":"Nanotechnology Perceptions","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor; Windsor Clinical Research","funders":"","keywords":"Anomaly (physics); Anomaly detection; Segmentation; Product (mathematics); Natural language processing; Computer science; Artificial intelligence; Physics; Mathematics; Condensed matter physics","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":[0.0002861435,0.000117587,0.0001404386,0.0004100232,0.0002287554,0.00009222038,0.000104075,0.0001286159,0.000003741932],"category_scores_gemma":[0.00006446068,0.0001125186,0.00002822088,0.000536516,0.00006191305,0.0002451409,0.00004632821,0.000187336,0.000004642758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001293937,"about_ca_system_score_gemma":0.00002922047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004791214,"about_ca_topic_score_gemma":0.00003358816,"domain_scores_codex":[0.9990559,0.00001792708,0.0002634522,0.0004557577,0.00005786709,0.0001491496],"domain_scores_gemma":[0.9995946,0.00005705451,0.0000611215,0.0002112321,0.00004930486,0.00002670277],"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":[0.00001191308,0.0001135414,0.0003065489,0.001612835,0.00003724937,0.000003364217,0.0008086502,0.0004579344,0.06956674,0.08624882,0.0003540939,0.8404783],"study_design_scores_gemma":[0.0002791393,0.0003881603,0.0007585752,0.001086806,0.00005913037,0.0002345327,0.0002447829,0.9726015,0.004728276,0.009032565,0.01021285,0.0003736774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06368795,0.001238442,0.9315903,0.001564942,0.0002122411,0.001070697,0.000008306642,0.0005920914,0.00003502761],"genre_scores_gemma":[0.9501615,0.002508606,0.04648269,0.0001221207,0.00004318613,0.000613711,0.00001245494,0.00001307442,0.00004272179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9721436,"threshold_uncertainty_score":0.4588377,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03662168663069268,"score_gpt":0.3321366144362697,"score_spread":0.2955149278055771,"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."}}