{"id":"W3158435984","doi":"10.48550/arxiv.2104.12300","title":"ODDObjects: A Framework for Multiclass Unsupervised Anomaly Detection on Masked Objects","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Autoencoder; Anomaly detection; Artificial intelligence; Computer science; Pattern recognition (psychology); Anomaly (physics); Convolutional neural network; Object (grammar); Unsupervised learning; Deep learning","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000188138,0.0003780034,0.0003759699,0.0003178699,0.0004266285,0.0002681436,0.001264819,0.0005952562,0.00001211674],"category_scores_gemma":[0.00009780418,0.0004584067,0.0004157661,0.0009452705,0.00006883789,0.0002713737,0.0008062262,0.0007064864,0.00002401576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003376637,"about_ca_system_score_gemma":0.0001591837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001182227,"about_ca_topic_score_gemma":0.0001177013,"domain_scores_codex":[0.9976181,0.0001137462,0.0002563511,0.001507544,0.0001102918,0.0003939737],"domain_scores_gemma":[0.9973006,0.0002860499,0.000275891,0.001656561,0.0003064082,0.0001745016],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003488474,0.001321563,0.000631707,0.0006296777,0.0005643172,0.0002974502,0.001771432,0.1017845,0.004643999,0.8533317,0.0001957113,0.03447908],"study_design_scores_gemma":[0.0007719533,0.0003803898,0.0009853907,0.0002608273,0.0001101536,0.000009064685,0.0003810024,0.8700106,0.04264171,0.08237344,0.001093223,0.0009822419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.138525,0.00002099721,0.8586687,0.0001089799,0.0004172352,0.000846473,0.00001617898,0.0007673725,0.000629008],"genre_scores_gemma":[0.9473835,0.00007733033,0.05164051,0.0002177817,0.0001171323,0.00004694513,0.00001687501,0.00003369849,0.0004661815],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8088585,"threshold_uncertainty_score":0.9997868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06926371866493562,"score_gpt":0.2076288915838352,"score_spread":0.1383651729188995,"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."}}