{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/sota/anomaly-detection-on-visa","task":{"name":"Anomaly Detection","url":"/task/anomaly-detection","note":null},"dataset":{"name":"VisA","url":"/dataset/visa"},"category":"Computer Vision","categories":["Computer Vision","Graphs","Methodology","Miscellaneous"],"category_note":null,"description":"**Anomaly Detection** is a binary classification identifying unusual or unexpected patterns in a dataset, which deviate significantly from the majority of the data. The goal of anomaly detection is to identify such anomalies, which could represent errors, fraud, or other types of unusual events, and flag them for further investigation.\r\n\r\n[Image source]: [GAN-based Anomaly Detection in Imbalance Problems](https://paperswithcode.com/paper/gan-based-anomaly-detection-in-imbalance)","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Detection AUROC","Segmentation AUPRO (until 30% FPR)","F1-Score","Segmentation AUPRO","Segmentation AUROC"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction; the tokens 'score' and 'time' are not used on this page); null = not inferred, chart draws points only","by_metric":{"Detection AUROC":null,"Segmentation AUPRO (until 30% FPR)":null,"F1-Score":"higher","Segmentation AUPRO":null,"Segmentation AUROC":null}},"counts":{"rows":50,"rows_with_code":48,"rows_with_paper_page":49,"rows_dated":49,"rows_using_additional_data":6},"rows":[{"rank_in_archive_order":1,"model":"UniNet","metrics":{"Detection AUROC":"99.8","Segmentation AUPRO":"93.9","Segmentation AUPRO (until 30% FPR)":"93.9","Segmentation AUROC":"98.8"},"uses_additional_data":false,"paper_date":"2025-02-28","paper":"/paper/uninet-a-contrastive-learning-guided-unified","paper_url":"https://pangdatangtt.github.io/#:~:text=guided%20anomaly%20discrimination.-,Abstract,-Anomaly%20detection%20(AD","paper_title":"UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection","code":"https://github.com/pangdatangtt/UniNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":2,"model":"GLAD","metrics":{"Detection AUROC":"99.5","F1-Score":"98.3","Segmentation AUPRO":"94.3","Segmentation AUPRO (until 30% FPR)":"94.3","Segmentation AUROC":"98.6"},"uses_additional_data":false,"paper_date":"2024-06-11","paper":"/paper/glad-towards-better-reconstruction-with","paper_url":"https://arxiv.org/abs/2406.07487v3","paper_title":"GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection","code":"https://github.com/hyao1/glad","n_code_links":1,"official":{"repos":["hyao1/glad"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":2,"n_samples":15,"n_pointer_only_licence":8,"sample_list":"/paper/glad-towards-better-reconstruction-with#ran","syntology_url":"https://syntology.ai/paper/2406.07487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07487"}}}},{"rank_in_archive_order":3,"model":"UniNet(model-unified multi-class)","metrics":{"Detection AUROC":"99.15","F1-Score":"98.29"},"uses_additional_data":false,"paper_date":"2025-02-28","paper":"/paper/uninet-a-contrastive-learning-guided-unified","paper_url":"https://pangdatangtt.github.io/#:~:text=guided%20anomaly%20discrimination.-,Abstract,-Anomaly%20detection%20(AD","paper_title":"UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection","code":"https://github.com/pangdatangtt/UniNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":4,"model":"Dinomaly ViT-L (model-unified multi-class)","metrics":{"Detection AUROC":"98.9","F1-Score":"96.1","Segmentation AUPRO":"94.8","Segmentation AUPRO (until 30% FPR)":"94.8","Segmentation AUROC":"99.1"},"uses_additional_data":false,"paper_date":"2024-05-23","paper":"/paper/dinomaly-the-less-is-more-philosophy-in-multi","paper_url":"https://arxiv.org/abs/2405.14325v4","paper_title":"Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection","code":"https://github.com/guojiajeremy/dinomaly","n_code_links":2,"official":{"repos":["guojiajeremy/dinomaly"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":5,"sample_list":"/paper/dinomaly-the-less-is-more-philosophy-in-multi#ran","syntology_url":"https://syntology.ai/paper/2405.14325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14325"}}}},{"rank_in_archive_order":5,"model":"INP-Former ViT-B (model-unified multi-class)","metrics":{"Detection AUROC":"98.9","F1-Score":"96.6","Segmentation AUPRO":"94.4","Segmentation AUPRO (until 30% FPR)":"94.4","Segmentation AUROC":"98.9"},"uses_additional_data":false,"paper_date":"2025-03-04","paper":"/paper/exploring-intrinsic-normal-prototypes-within","paper_url":"https://arxiv.org/abs/2503.02424v1","paper_title":"Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection","code":"https://github.com/luow23/inp-former","n_code_links":2,"official":{"repos":["luow23/inp-former"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":3,"sample_list":"/paper/exploring-intrinsic-normal-prototypes-within#ran","syntology_url":"https://syntology.ai/paper/2503.02424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.02424"}}}},{"rank_in_archive_order":6,"model":"DDAD","metrics":{"Detection AUROC":"98.9","Segmentation AUPRO (until 30% FPR)":"92.7","Segmentation AUROC":"97.6"},"uses_additional_data":false,"paper_date":"2023-05-25","paper":"/paper/anomaly-detection-with-conditioned-denoising","paper_url":"https://arxiv.org/abs/2305.15956v2","paper_title":"Anomaly Detection with Conditioned Denoising Diffusion Models","code":"https://github.com/arimousa/DDAD","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":7,"model":"DiffusionAD","metrics":{"Detection AUROC":"98.8","Segmentation AUPRO":"96.0","Segmentation AUPRO (until 30% FPR)":"96.0","Segmentation AUROC":"98.9"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/diffusionad-denoising-diffusion-for-anomaly","paper_url":"https://arxiv.org/abs/2303.08730v4","paper_title":"DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection","code":"https://github.com/huizhang0812/diffusionad","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":8,"model":"GLASS","metrics":{"Detection AUROC":"98.8","Segmentation AUPRO (until 30% FPR)":"92.8","Segmentation AUROC":"98.8"},"uses_additional_data":false,"paper_date":"2024-07-12","paper":"/paper/a-unified-anomaly-synthesis-strategy-with","paper_url":"https://arxiv.org/abs/2407.09359v1","paper_title":"A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization","code":"https://github.com/cqylunlun/glass","n_code_links":2,"official":{"repos":["cqylunlun/glass"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":1,"sample_list":"/paper/a-unified-anomaly-synthesis-strategy-with#ran","syntology_url":"https://syntology.ai/paper/2407.09359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.09359"}}}},{"rank_in_archive_order":9,"model":"TransFusion","metrics":{"Detection AUROC":"98.7","Segmentation AUPRO (until 30% FPR)":"94.7"},"uses_additional_data":false,"paper_date":"2023-11-16","paper":"/paper/transfusion-a-transparency-based-diffusion","paper_url":"https://arxiv.org/abs/2311.09999v2","paper_title":"TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection","code":"https://github.com/maticfuc/eccv_transfusion","n_code_links":1,"official":{"repos":["maticfuc/eccv_transfusion"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/transfusion-a-transparency-based-diffusion#ran","syntology_url":"https://syntology.ai/paper/2311.09999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09999"}}}},{"rank_in_archive_order":10,"model":"EfficientAD-M","metrics":{"Detection AUROC":"98.1","Segmentation AUPRO (until 30% FPR)":"94.0"},"uses_additional_data":false,"paper_date":"2023-03-25","paper":"/paper/efficientad-accurate-visual-anomaly-detection","paper_url":"https://arxiv.org/abs/2303.14535v3","paper_title":"EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":33,"official":null,"syntology":{"n_ran":29,"n_constructed":0,"n_ran_checked":29,"n_instrument":0,"n_unverified":6,"n_samples":35,"n_pointer_only_licence":0,"sample_list":"/paper/efficientad-accurate-visual-anomaly-detection#ran","syntology_url":"https://syntology.ai/paper/2303.14535","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14535"}}}},{"rank_in_archive_order":11,"model":"HETMM","metrics":{"Detection AUROC":"98.1","Segmentation AUROC":"99.1"},"uses_additional_data":false,"paper_date":"2023-03-28","paper":"/paper/hard-nominal-example-aware-template-mutual","paper_url":"https://arxiv.org/abs/2303.16191v5","paper_title":"Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly Detection","code":"https://github.com/NarcissusEx/HETMM","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":12,"model":"RealNet","metrics":{"Detection AUROC":"97.8","Segmentation AUROC":"98.8"},"uses_additional_data":true,"paper_date":"2024-03-09","paper":"/paper/realnet-a-feature-selection-network-with","paper_url":"https://arxiv.org/abs/2403.05897v1","paper_title":"RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection","code":"https://github.com/cnulab/realnet","n_code_links":1,"official":{"repos":["cnulab/realnet"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":0,"n_samples":10,"n_pointer_only_licence":1,"sample_list":"/paper/realnet-a-feature-selection-network-with#ran","syntology_url":"https://syntology.ai/paper/2403.05897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05897"}}}},{"rank_in_archive_order":13,"model":"PBAS","metrics":{"Detection AUROC":"97.7","Segmentation AUPRO":"93.3","Segmentation AUROC":"98.6"},"uses_additional_data":false,"paper_date":"2024-12-23","paper":"/paper/progressive-boundary-guided-anomaly-synthesis","paper_url":"https://arxiv.org/abs/2412.17458v1","paper_title":"Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detection","code":"https://github.com/cqylunlun/pbas","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":14,"model":"AnomalyDINO-S (full-shot)","metrics":{"Detection AUROC":"97.6","Segmentation AUPRO (until 30% FPR)":"96.1","Segmentation AUROC":"98.8"},"uses_additional_data":false,"paper_date":"2024-05-23","paper":"/paper/anomalydino-boosting-patch-based-few-shot","paper_url":"https://arxiv.org/abs/2405.14529v2","paper_title":"AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2","code":"https://github.com/dammsi/AnomalyDINO","n_code_links":1,"official":{"repos":["dammsi/AnomalyDINO"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":0,"sample_list":"/paper/anomalydino-boosting-patch-based-few-shot#ran","syntology_url":"https://syntology.ai/paper/2405.14529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14529"}}}},{"rank_in_archive_order":15,"model":"EfficientAD-S","metrics":{"Detection AUROC":"97.5","Segmentation AUPRO (until 30% FPR)":"93.1"},"uses_additional_data":false,"paper_date":"2023-03-25","paper":"/paper/efficientad-accurate-visual-anomaly-detection","paper_url":"https://arxiv.org/abs/2303.14535v3","paper_title":"EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":33,"official":null,"syntology":{"n_ran":29,"n_constructed":0,"n_ran_checked":29,"n_instrument":0,"n_unverified":6,"n_samples":35,"n_pointer_only_licence":0,"sample_list":"/paper/efficientad-accurate-visual-anomaly-detection#ran","syntology_url":"https://syntology.ai/paper/2303.14535","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14535"}}}},{"rank_in_archive_order":16,"model":"ReContrast","metrics":{"Detection AUROC":"97.5","Segmentation AUPRO":"92.6","Segmentation AUROC":"98.2"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":17,"model":"FAIRnoDTD","metrics":{"Detection AUROC":"97.1","Segmentation AUPRO (until 30% FPR)":"91.2","Segmentation AUROC":"98.7"},"uses_additional_data":false,"paper_date":"2023-09-13","paper":"/paper/fair-frequency-aware-image-restoration-for","paper_url":"https://arxiv.org/abs/2309.07068v1","paper_title":"FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection","code":"https://github.com/liutongkun/fair","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":18,"model":"CRAS","metrics":{"Detection AUROC":"97.0","Segmentation AUROC":"98.4"},"uses_additional_data":false,"paper_date":"2025-05-23","paper":"/paper/center-aware-residual-anomaly-synthesis-for","paper_url":"https://arxiv.org/abs/2505.17551v1","paper_title":"Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detection","code":"https://github.com/cqylunlun/CRAS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":19,"model":"URD","metrics":{"Detection AUROC":"96.5","Segmentation AUPRO (until 30% FPR)":"95.1","Segmentation AUROC":"99.1"},"uses_additional_data":true,"paper_date":"2024-12-10","paper":"/paper/unlocking-the-potential-of-reverse","paper_url":"https://arxiv.org/abs/2412.07579v1","paper_title":"Unlocking the Potential of Reverse Distillation for Anomaly Detection","code":"https://github.com/hito2448/urd","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":20,"model":"D3AD","metrics":{"Detection AUROC":"96.0","Segmentation AUPRO (until 30% FPR)":"94.1","Segmentation AUROC":"97.9"},"uses_additional_data":false,"paper_date":"2024-01-09","paper":"/paper/d3ad-dynamic-denoising-diffusion","paper_url":"https://arxiv.org/abs/2401.04463v2","paper_title":"Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection","code":"https://github.com/JustinTebbe/D3AD","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":21,"model":"AST","metrics":{"Detection AUROC":"94.9","Segmentation AUPRO (until 30% FPR)":"81.5"},"uses_additional_data":false,"paper_date":"2022-10-14","paper":"/paper/asymmetric-student-teacher-networks-for","paper_url":"https://arxiv.org/abs/2210.07829v2","paper_title":"Asymmetric Student-Teacher Networks for Industrial Anomaly Detection","code":"https://github.com/marco-rudolph/ast","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":22,"model":"EdgRec","metrics":{"Detection AUROC":"94.2","Segmentation AUPRO (until 30% FPR)":"90.7"},"uses_additional_data":false,"paper_date":"2022-10-26","paper":"/paper/reconstruction-from-edge-image-combined-with","paper_url":"https://arxiv.org/abs/2210.14485v1","paper_title":"Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detection","code":"https://github.com/liutongkun/edgrec","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":23,"model":"SuperSimpleNet","metrics":{"Detection AUROC":"93.4","Segmentation AUPRO":"87.4","Segmentation AUPRO (until 30% FPR)":"87.4"},"uses_additional_data":false,"paper_date":"2024-08-06","paper":"/paper/2408-03143","paper_url":"https://arxiv.org/abs/2408.03143v2","paper_title":"SuperSimpleNet: Unifying Unsupervised and Supervised Learning for Fast and Reliable Surface Defect Detection","code":"https://github.com/open-edge-platform/anomalib","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":24,"model":"Student-Teacher","metrics":{"Detection AUROC":"93.2"},"uses_additional_data":false,"paper_date":"2019-11-06","paper":"/paper/uninformed-students-student-teacher-anomaly","paper_url":"https://arxiv.org/abs/1911.02357v2","paper_title":"Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings","code":"https://github.com/denguir/student-teacher-anomaly-detection","n_code_links":3,"official":null,"syntology":{"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":3,"sample_list":"/paper/uninformed-students-student-teacher-anomaly#ran","syntology_url":"https://syntology.ai/paper/1911.02357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02357"}}}},{"rank_in_archive_order":25,"model":"MuSc (zero-shot)","metrics":{"Detection AUROC":"92.8","Segmentation AUPRO":"92.7","Segmentation AUPRO (until 30% FPR)":"92.7","Segmentation AUROC":"98.8"},"uses_additional_data":false,"paper_date":"2024-01-30","paper":"/paper/musc-zero-shot-industrial-anomaly","paper_url":"https://arxiv.org/abs/2401.16753v1","paper_title":"MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images","code":"https://github.com/xrli-U/MuSc","n_code_links":1,"official":{"repos":["xrli-U/MuSc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/musc-zero-shot-industrial-anomaly#ran","syntology_url":"https://syntology.ai/paper/2401.16753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.16753"}}}},{"rank_in_archive_order":26,"model":"AnomalyDINO-S (4-shot)","metrics":{"Detection AUROC":"92.6","Segmentation AUPRO (until 30% FPR)":"94.1","Segmentation AUROC":"98.2"},"uses_additional_data":false,"paper_date":"2024-05-23","paper":"/paper/anomalydino-boosting-patch-based-few-shot","paper_url":"https://arxiv.org/abs/2405.14529v2","paper_title":"AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2","code":"https://github.com/dammsi/AnomalyDINO","n_code_links":1,"official":{"repos":["dammsi/AnomalyDINO"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":0,"sample_list":"/paper/anomalydino-boosting-patch-based-few-shot#ran","syntology_url":"https://syntology.ai/paper/2405.14529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14529"}}}},{"rank_in_archive_order":27,"model":"CFA","metrics":{"Detection AUROC":"92.0","Segmentation AUPRO (until 30% FPR)":"55.1"},"uses_additional_data":false,"paper_date":"2022-06-09","paper":"/paper/cfa-coupled-hypersphere-based-feature","paper_url":"https://arxiv.org/abs/2206.04325v1","paper_title":"CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":28,"model":"CFLOW","metrics":{"Detection AUROC":"91.5"},"uses_additional_data":false,"paper_date":"2021-07-27","paper":"/paper/cflow-ad-real-time-unsupervised-anomaly","paper_url":"https://arxiv.org/abs/2107.12571v1","paper_title":"CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows","code":"https://github.com/openvinotoolkit/anomalib/tree/development/anomalib/models/cflow","n_code_links":3,"official":{"repos":["gudovskiy/cflow-ad"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":1,"n_samples":12,"n_pointer_only_licence":3,"sample_list":"/paper/cflow-ad-real-time-unsupervised-anomaly#ran","syntology_url":"https://syntology.ai/paper/2107.12571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.12571"}}}},{"rank_in_archive_order":29,"model":"AnomalyDINO-S (2-shot)","metrics":{"Detection AUROC":"89.7","Segmentation AUPRO (until 30% FPR)":"93.4","Segmentation AUROC":"98"},"uses_additional_data":false,"paper_date":"2024-05-23","paper":"/paper/anomalydino-boosting-patch-based-few-shot","paper_url":"https://arxiv.org/abs/2405.14529v2","paper_title":"AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2","code":"https://github.com/dammsi/AnomalyDINO","n_code_links":1,"official":{"repos":["dammsi/AnomalyDINO"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":0,"sample_list":"/paper/anomalydino-boosting-patch-based-few-shot#ran","syntology_url":"https://syntology.ai/paper/2405.14529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14529"}}}},{"rank_in_archive_order":30,"model":"GCAD","metrics":{"Detection AUROC":"89.1","Segmentation AUPRO (until 30% FPR)":"83.7"},"uses_additional_data":false,"paper_date":"2022-02-22","paper":"/paper/beyond-dents-and-scratches-logical","paper_url":"https://link.springer.com/article/10.1007/s11263-022-01578-9","paper_title":"Beyond Dents and Scratches: Logical Constraints in Unsupervised Anomaly Detection and Localization","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":31,"model":"SPD","metrics":{"Detection AUROC":"87.8"},"uses_additional_data":false,"paper_date":"2022-07-28","paper":"/paper/spot-the-difference-self-supervised-pre","paper_url":"https://arxiv.org/abs/2207.14315v1","paper_title":"SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation","code":"https://github.com/amazon-science/spot-diff","n_code_links":1,"official":null,"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/spot-the-difference-self-supervised-pre#ran","syntology_url":"https://syntology.ai/paper/2207.14315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.14315"}}}},{"rank_in_archive_order":32,"model":"AnomalyDINO-S (1-shot)","metrics":{"Detection AUROC":"87.4","Segmentation AUPRO (until 30% FPR)":"92.5","Segmentation AUROC":"97.8"},"uses_additional_data":false,"paper_date":"2024-05-23","paper":"/paper/anomalydino-boosting-patch-based-few-shot","paper_url":"https://arxiv.org/abs/2405.14529v2","paper_title":"AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2","code":"https://github.com/dammsi/AnomalyDINO","n_code_links":1,"official":{"repos":["dammsi/AnomalyDINO"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":0,"sample_list":"/paper/anomalydino-boosting-patch-based-few-shot#ran","syntology_url":"https://syntology.ai/paper/2405.14529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14529"}}}},{"rank_in_archive_order":33,"model":"WinCLIP+ (4-shot)","metrics":{"Detection AUROC":"87.3","Segmentation AUPRO":"87.6","Segmentation AUPRO (until 30% FPR)":"87.6"},"uses_additional_data":false,"paper_date":"2023-03-26","paper":"/paper/winclip-zero-few-shot-anomaly-classification","paper_url":"https://arxiv.org/abs/2303.14814v1","paper_title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":4,"official":null,"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":5,"n_samples":12,"n_pointer_only_licence":6,"sample_list":"/paper/winclip-zero-few-shot-anomaly-classification#ran","syntology_url":"https://syntology.ai/paper/2303.14814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14814"}}}},{"rank_in_archive_order":34,"model":"AdaCLIP","metrics":{"Detection AUROC":"85.8","Segmentation AUROC":"95.5"},"uses_additional_data":true,"paper_date":"2024-07-22","paper":"/paper/adaclip-adapting-clip-with-hybrid-learnable","paper_url":"https://arxiv.org/abs/2407.15795v1","paper_title":"AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection","code":"https://github.com/caoyunkang/adaclip","n_code_links":1,"official":{"repos":["caoyunkang/adaclip"],"state":"official (archive's flag): 20 ran","n_ran":20,"n_constructed":10,"n_ran_no_instrument_failure":12,"n_unverified":8,"ran_from_kinds":["official"]},"syntology":{"n_ran":20,"n_constructed":10,"n_ran_checked":12,"n_instrument":8,"n_unverified":8,"n_samples":28,"n_pointer_only_licence":4,"sample_list":"/paper/adaclip-adapting-clip-with-hybrid-learnable#ran","syntology_url":"https://syntology.ai/paper/2407.15795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15795"}}}},{"rank_in_archive_order":35,"model":"WinCLIP+ (2-shot)","metrics":{"Detection AUROC":"84.6","Segmentation AUPRO":"86.2","Segmentation AUPRO (until 30% FPR)":"86.2"},"uses_additional_data":false,"paper_date":"2023-03-26","paper":"/paper/winclip-zero-few-shot-anomaly-classification","paper_url":"https://arxiv.org/abs/2303.14814v1","paper_title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":4,"official":null,"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":5,"n_samples":12,"n_pointer_only_licence":6,"sample_list":"/paper/winclip-zero-few-shot-anomaly-classification#ran","syntology_url":"https://syntology.ai/paper/2303.14814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14814"}}}},{"rank_in_archive_order":36,"model":"WinCLIP+ (1-shot)","metrics":{"Detection AUROC":"83.8","Segmentation AUPRO":"85.1","Segmentation AUPRO (until 30% FPR)":"85.1"},"uses_additional_data":false,"paper_date":"2023-03-26","paper":"/paper/winclip-zero-few-shot-anomaly-classification","paper_url":"https://arxiv.org/abs/2303.14814v1","paper_title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":4,"official":null,"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":5,"n_samples":12,"n_pointer_only_licence":6,"sample_list":"/paper/winclip-zero-few-shot-anomaly-classification#ran","syntology_url":"https://syntology.ai/paper/2303.14814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14814"}}}},{"rank_in_archive_order":37,"model":"STPM","metrics":{"Detection AUROC":"83.3","Segmentation AUPRO (until 30% FPR)":"62.0"},"uses_additional_data":false,"paper_date":"2021-03-07","paper":"/paper/student-teacher-feature-pyramid-matching-for","paper_url":"https://arxiv.org/abs/2103.04257v3","paper_title":"Student-Teacher Feature Pyramid Matching for Anomaly Detection","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":10,"official":null,"syntology":null},{"rank_in_archive_order":38,"model":"SPADE","metrics":{"Detection AUROC":"82.1","Segmentation AUPRO (until 30% FPR)":"65.9"},"uses_additional_data":false,"paper_date":"2020-05-05","paper":"/paper/sub-image-anomaly-detection-with-deep-pyramid","paper_url":"https://arxiv.org/abs/2005.02357v3","paper_title":"Sub-Image Anomaly Detection with Deep Pyramid Correspondences","code":"https://github.com/byungjae89/SPADE-pytorch","n_code_links":5,"official":null,"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/sub-image-anomaly-detection-with-deep-pyramid#ran","syntology_url":"https://syntology.ai/paper/2005.02357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.02357"}}}},{"rank_in_archive_order":39,"model":"AnomalyCLIP","metrics":{"Detection AUROC":"82.1","Segmentation AUPRO":"87.0","Segmentation AUROC":"95.5"},"uses_additional_data":true,"paper_date":"2023-10-29","paper":"/paper/anomalyclip-object-agnostic-prompt-learning","paper_url":"https://arxiv.org/abs/2310.18961v9","paper_title":"AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection","code":"https://github.com/zqhang/anomalyclip","n_code_links":3,"official":{"repos":["zqhang/anomalyclip"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":19,"n_constructed":0,"n_ran_checked":12,"n_instrument":7,"n_unverified":13,"n_samples":32,"n_pointer_only_licence":15,"sample_list":"/paper/anomalyclip-object-agnostic-prompt-learning#ran","syntology_url":"https://syntology.ai/paper/2310.18961","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18961"}}}},{"rank_in_archive_order":40,"model":"AnoDDPM","metrics":{"Detection AUROC":"78.2","Segmentation AUPRO (until 30% FPR)":"60.5"},"uses_additional_data":false,"paper_date":"2022-06-30","paper":"/paper/anoddpm-anomaly-detection-with-denoising","paper_url":"https://openaccess.thecvf.com/content/CVPR2022W/NTIRE/html/Wyatt_AnoDDPM_Anomaly_Detection_With_Denoising_Diffusion_Probabilistic_Models_Using_Simplex_CVPRW_2022_paper.html","paper_title":"AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise","code":"https://github.com/julian-wyatt/anoddpm","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":41,"model":"WinCLIP (0-shot)","metrics":{"Detection AUROC":"78.1","Segmentation AUPRO":"56.8","Segmentation AUPRO (until 30% FPR)":"56.8"},"uses_additional_data":false,"paper_date":"2023-03-26","paper":"/paper/winclip-zero-few-shot-anomaly-classification","paper_url":"https://arxiv.org/abs/2303.14814v1","paper_title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":4,"official":null,"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":5,"n_samples":12,"n_pointer_only_licence":6,"sample_list":"/paper/winclip-zero-few-shot-anomaly-classification#ran","syntology_url":"https://syntology.ai/paper/2303.14814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14814"}}}},{"rank_in_archive_order":42,"model":"APRIL-GAN","metrics":{"Detection AUROC":"78.0","F1-Score":"32.3","Segmentation AUPRO":"86.8","Segmentation AUROC":"94.2"},"uses_additional_data":true,"paper_date":"2023-05-27","paper":"/paper/a-zero-few-shot-anomaly-classification-and","paper_url":"https://arxiv.org/abs/2305.17382v3","paper_title":"APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD","code":"https://github.com/bychelsea/vand-april-gan","n_code_links":2,"official":{"repos":["bychelsea/vand-april-gan"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":4,"n_samples":10,"n_pointer_only_licence":7,"sample_list":"/paper/a-zero-few-shot-anomaly-classification-and#ran","syntology_url":"https://syntology.ai/paper/2305.17382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17382"}}}},{"rank_in_archive_order":43,"model":"PaDiM","metrics":{"Segmentation AUPRO (until 30% FPR)":"85.9"},"uses_additional_data":false,"paper_date":"2020-11-17","paper":"/paper/padim-a-patch-distribution-modeling-framework","paper_url":"https://arxiv.org/abs/2011.08785v1","paper_title":"PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization","code":"https://github.com/openvinotoolkit/anomalib","n_code_links":26,"official":null,"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":3,"sample_list":"/paper/padim-a-patch-distribution-modeling-framework#ran","syntology_url":"https://syntology.ai/paper/2011.08785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.08785"}}}},{"rank_in_archive_order":44,"model":"DRAEM","metrics":{"Segmentation AUPRO (until 30% FPR)":"73.1"},"uses_additional_data":false,"paper_date":"2021-08-17","paper":"/paper/draem-a-discriminatively-trained","paper_url":"https://arxiv.org/abs/2108.07610v2","paper_title":"DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection","code":"https://github.com/openvinotoolkit/anomalib/tree/development/anomalib/models/draem","n_code_links":3,"official":{"repos":["vitjanz/draem"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":6,"sample_list":"/paper/draem-a-discriminatively-trained#ran","syntology_url":"https://syntology.ai/paper/2108.07610","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.07610"}}}},{"rank_in_archive_order":45,"model":"Reverse Distillation","metrics":{"Segmentation AUPRO (until 30% FPR)":"70.9"},"uses_additional_data":false,"paper_date":"2022-01-26","paper":"/paper/anomaly-detection-via-reverse-distillation","paper_url":"https://arxiv.org/abs/2201.10703v2","paper_title":"Anomaly Detection via Reverse Distillation from One-Class Embedding","code":"https://github.com/openvinotoolkit/anomalib/tree/development/anomalib/models/reverse_distillation","n_code_links":5,"official":{"repos":["hq-deng/RD4AD"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official","unlocated"]},"syntology":{"n_ran":14,"n_constructed":8,"n_ran_checked":10,"n_instrument":4,"n_unverified":4,"n_samples":18,"n_pointer_only_licence":15,"sample_list":"/paper/anomaly-detection-via-reverse-distillation#ran","syntology_url":"https://syntology.ai/paper/2201.10703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.10703"}}}},{"rank_in_archive_order":46,"model":"DSR","metrics":{"Segmentation AUPRO (until 30% FPR)":"68.1"},"uses_additional_data":false,"paper_date":"2022-08-02","paper":"/paper/dsr-a-dual-subspace-re-projection-network-for","paper_url":"https://arxiv.org/abs/2208.01521v2","paper_title":"DSR -- A dual subspace re-projection network for surface anomaly detection","code":"https://github.com/vitjanz/dsr_anomaly_detection","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":47,"model":"FAVAE","metrics":{"Segmentation AUPRO (until 30% FPR)":"67.9"},"uses_additional_data":false,"paper_date":"2020-08-12","paper":"/paper/anomaly-localization-by-modeling-perceptual","paper_url":"https://arxiv.org/abs/2008.05369v1","paper_title":"Anomaly localization by modeling perceptual features","code":"https://github.com/xiahaifeng1995/FAVAE-anomaly-detection-localization-master","n_code_links":1,"official":null,"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":1,"sample_list":"/paper/anomaly-localization-by-modeling-perceptual#ran","syntology_url":"https://syntology.ai/paper/2008.05369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.05369"}}}},{"rank_in_archive_order":48,"model":"FastFlow","metrics":{"Segmentation AUPRO (until 30% FPR)":"59.8"},"uses_additional_data":false,"paper_date":"2021-11-15","paper":"/paper/fastflow-unsupervised-anomaly-detection-and","paper_url":"https://arxiv.org/abs/2111.07677v2","paper_title":"FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows","code":"https://github.com/openvinotoolkit/anomalib/tree/main/src/anomalib/models/fastflow","n_code_links":5,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/fastflow-unsupervised-anomaly-detection-and#ran","syntology_url":"https://syntology.ai/paper/2111.07677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.07677"}}}},{"rank_in_archive_order":49,"model":"SAA+","metrics":{"F1-Score":"27.07"},"uses_additional_data":false,"paper_date":"2023-05-18","paper":"/paper/segment-any-anomaly-without-training-via","paper_url":"https://arxiv.org/abs/2305.10724v1","paper_title":"Segment Any Anomaly without Training via Hybrid Prompt Regularization","code":"https://github.com/caoyunkang/groundedsam-zero-shot-anomaly-detection","n_code_links":2,"official":{"repos":["caoyunkang/segment-any-anomaly"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":5,"sample_list":"/paper/segment-any-anomaly-without-training-via#ran","syntology_url":"https://syntology.ai/paper/2305.10724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10724"}}}},{"rank_in_archive_order":50,"model":"VCP-CLIP","metrics":{"Segmentation AUPRO":"90.7","Segmentation AUROC":"95.7"},"uses_additional_data":true,"paper_date":"2024-07-17","paper":"/paper/vcp-clip-a-visual-context-prompting-model-for","paper_url":"https://arxiv.org/abs/2407.12276v1","paper_title":"VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation","code":"https://github.com/xiaozhen228/vcp-clip","n_code_links":1,"official":null,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 11 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,592 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 6 proposed a result; of those 6, 5 gave no cell that passed the extractor's own checks, 0 were rejected by the independent check, 0 await a verdict and 1 was placed.","note":"papers, from the extractor's own records, over the newer papers whose tables were read; proposed = no_cell_passed_checks + rejected_by_independent_check + accepted_not_placed + awaiting_verdict + placed; counts, never a rate","eligible":true,"eligible_note":"false when the extractor never considers this board: it loads only boards with archive rows and at least one metric column (lb_extract.py Boards), so no newer paper can be proposed here; archive_rows and metric_columns say which","archive_rows":50,"metric_columns":5,"papers_read":8888,"papers_read_checked":8886,"papers_read_awaiting_verdict":2,"papers_read_verified":8888,"papers_read_not_yet_verified":0,"papers_read_at_candidate_cap":1596,"papers_read_list_full_without_this_board":1592,"candidates":11,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":6,"no_cell_passed_checks":5,"rejected_by_independent_check":0,"accepted_not_placed":0,"awaiting_verdict":0,"placed":1,"placed_entries_listed":1,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): 1 placed; 6 newer papers judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"a_record_without_a_model":false,"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":6,"shown_on_page":6,"no_cell_split":{"no_cell_passed_checks_in_ledger":5,"rows_refused_by_rule":5,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2602.23013","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2602.03594","outcome":"refused_by_rule","reason":"the model pointed at a header row"},{"arxiv_id":"2602.00522","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2511.05245","outcome":"refused_by_rule","reason":"the model pointed at a header row; the row label the model quoted is not the row's label"},{"arxiv_id":"2510.00495","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric; the quoted value appears more than once in the row"},{"arxiv_id":"2509.02101","outcome":"placed","reason":null}]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":["Detection AUROC"],"entries":[{"paper":"/paper/arxiv-2509-02101","paper_title":"SALAD -- Semantics-Aware Logical Anomaly Detection","arxiv_id":"2509.02101","model":"SALAD ✓","row_label":"SALAD ✓","configuration":null,"configuration_in_model":false,"configuration_not_shown_because":null,"values":{"Detection AUROC":"97.9"},"date":"2025-09-02","month_from_arxiv_id":null,"where_in_paper":"Table 3, row “SALAD ✓”","table_label":"3","table_label_from":"the caption's own label","table_position_1based":3,"caption_head":"Table 3 : Anomaly detection (AUROC) on MVTec AD [ 2 ] and VisA [ 46 ] .","caption_on_page":"shown","cells":[{"column":"Detection AUROC","cell_text":"97.9","column_header":"VisA","value":97.9,"table_index_0based":2,"row":11,"col":3}],"code":"8 harvested: 7 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","samples_harvested":8,"sample_list":"/paper/arxiv-2509-02101#ran","syntology":{"syntology_url":"https://syntology.ai/paper/2509.02101","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2509.02101"}}}}]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"rows_with_graph_line":30,"rows_with_any_sample_ran":30,"rows_with_a_run_with_no_instrument_failure":27,"official":{"state_rule":"the archive's official repositories have samples for this paper that ran: 'official (archive's flag): N ran' (N counts them, instrument failures included); they have samples, none ran: 'official: harvested, nothing ran'; they have no sample for this paper and another sample ran: 'community repositories only' when every sample that ran came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, else 'official: no sample here; runs from other or unrecorded repositories' (a repository named in the paper or found in its text by Syntology, or no repository recorded); otherwise 'official: harvested for another paper' or 'official: not harvested'. Absent when the archive marks no repository official. Official is the archive's is_official flag, not an authorship verdict","flag":"the archive's is_official flag for the paper's code link; not a verdict on who wrote the code","rows_with_an_archive_official_repository":18,"rows_whose_official_repository_has_a_sample_that_ran":18,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":15,"rows_community_repositories_only":0,"rows_runs_from_other_or_unrecorded_repositories":0,"note":"rows[].official, per row with a graph line: repos (marked official in the archive), state, n_ran and n_unverified (samples from those repositories), and ran_from_kinds (the kinds of repository the paper's samples that ran came from; 'unlocated' is no repository recorded)"},"filters":{"ran_modes":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"the page's filters hide rows and never renumber them; they read the Ran cell's counts, the same figures rows[].syntology and rows[].official carry"},"row_route":"rows[].syntology carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","distinct_papers_with_graph_line":23,"distinct_papers_with_any_sample_ran":23,"distinct_papers_with_a_run_with_no_instrument_failure":20,"samples_over_distinct_papers":{"n_ran":202,"n_constructed":19,"n_ran_checked":138,"n_instrument":64,"n_unverified":56,"n_samples":258,"n_pointer_only_licence":86,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":279,"n_constructed":19,"n_ran_checked":200,"n_instrument":79,"n_unverified":86,"n_samples":365,"n_pointer_only_licence":104,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}},"record_sha256":"740773711b5f2fae2f529e184c10b073ffe6ba466c3829c660e73682b0e1f6e9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}