{"url":"/sota/person-re-identification-on-msmt17","task":{"name":"Person Re-Identification","url":"/task/person-re-identification","note":null},"dataset":{"name":"MSMT17","url":"/dataset/msmt17"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Person Re-Identification** is a computer vision task in which the goal is to match a person's identity across different cameras or locations in a video or image sequence. It involves detecting and tracking a person and then using features such as appearance, body shape, and clothing to match their identity in different frames. The goal is to associate the same person across multiple non-overlapping camera views in a robust and efficient manner.","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":["mAP","Rank-1","Rank-10","Rank-5"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mAP":"higher","Rank-1":null,"Rank-10":null,"Rank-5":null}},"counts":{"rows":43,"rows_with_code":38,"rows_with_paper_page":43,"rows_dated":43,"rows_using_additional_data":6},"rows":[{"rank_in_archive_order":1,"model":"CLIP-ReID (with re-ranking)","metrics":{"Rank-1":"91.2","mAP":"86.7"},"uses_additional_data":false,"paper_date":"2022-11-25","paper":"/paper/clip-reid-exploiting-vision-language-model","paper_url":"https://arxiv.org/abs/2211.13977v4","paper_title":"CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels","code":"https://github.com/mikel-brostrom/boxmot","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"SOLIDER (with re-ranking)","metrics":{"Rank-1":"91.7","mAP":"86.5"},"uses_additional_data":true,"paper_date":"2023-03-30","paper":"/paper/beyond-appearance-a-semantic-controllable","paper_url":"https://arxiv.org/abs/2303.17602v1","paper_title":"Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks","code":"https://github.com/modelscope/modelscope","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":3,"model":"FlipReID (with re-ranking)","metrics":{"Rank-1":"87.5","mAP":"81.3"},"uses_additional_data":false,"paper_date":"2021-05-12","paper":"/paper/flipreid-closing-the-gap-between-training-and","paper_url":"https://arxiv.org/abs/2105.05639v1","paper_title":"FlipReID: Closing the Gap between Training and Inference in Person Re-Identification","code":"https://github.com/nixingyang/FlipReID","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"ProNet++ (ResNet50+RK)","metrics":{"Rank-1":"88.2","mAP":"80"},"uses_additional_data":false,"paper_date":"2023-08-21","paper":"/paper/rethinking-person-re-identification-from-a","paper_url":"https://arxiv.org/abs/2308.10717v1","paper_title":"Rethinking Person Re-identification from a Projection-on-Prototypes Perspective","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"LDS (ResNet50+RK)","metrics":{"Rank-1":"88.35","mAP":"79.09"},"uses_additional_data":false,"paper_date":"2021-11-10","paper":"/paper/learning-to-disentangle-scenes-for-person-re","paper_url":"https://arxiv.org/abs/2111.05476v2","paper_title":"Learning to Disentangle Scenes for Person Re-identification","code":"https://github.com/deropty/LDS","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"SOLIDER (without re-ranking)","metrics":{"Rank-1":"90.7","mAP":"77.1"},"uses_additional_data":true,"paper_date":"2023-03-30","paper":"/paper/beyond-appearance-a-semantic-controllable","paper_url":"https://arxiv.org/abs/2303.17602v1","paper_title":"Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks","code":"https://github.com/modelscope/modelscope","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":7,"model":"Adaptive L2 Regularization (with re-ranking)","metrics":{"Rank-1":"84.9","mAP":"76.7"},"uses_additional_data":false,"paper_date":"2020-07-15","paper":"/paper/adaptivereid-adaptive-l2-regularization-in","paper_url":"https://arxiv.org/abs/2007.07875v2","paper_title":"Adaptive L2 Regularization in Person Re-Identification","code":"https://github.com/nixingyang/AdaptiveL2Regularization","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"PCL-CLIP (L_pcl+L_id)","metrics":{"Rank-1":"89.8","Rank-10":"96.0","Rank-5":"94.7","mAP":"76.1"},"uses_additional_data":false,"paper_date":"2023-10-26","paper":"/paper/prototypical-contrastive-learning-based-clip","paper_url":"https://arxiv.org/abs/2310.17218v1","paper_title":"Prototypical Contrastive Learning-based CLIP Fine-tuning for Object Re-identification","code":"https://github.com/RikoLi/PCL-CLIP","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"CLIP-ReID (without re-ranking)","metrics":{"Rank-1":"89.7","mAP":"75.8"},"uses_additional_data":false,"paper_date":"2022-11-25","paper":"/paper/clip-reid-exploiting-vision-language-model","paper_url":"https://arxiv.org/abs/2211.13977v4","paper_title":"CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels","code":"https://github.com/mikel-brostrom/boxmot","n_code_links":2,"syntology":null},{"rank_in_archive_order":10,"model":"TransReID-SSL (ViT-B without RK)","metrics":{"Rank-1":"89.5","mAP":"75.0"},"uses_additional_data":false,"paper_date":"2021-11-23","paper":"/paper/self-supervised-pre-training-for-transformer","paper_url":"https://arxiv.org/abs/2111.12084v1","paper_title":"Self-Supervised Pre-Training for Transformer-Based Person Re-Identification","code":"https://github.com/DengpanFu/LUPerson","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":11,"model":"CA-Jaccard","metrics":{"Rank-1":"86.2","Rank-5":"90.5","mAP":"74.1"},"uses_additional_data":false,"paper_date":"2023-11-17","paper":"/paper/ca-jaccard-camera-aware-jaccard-distance-for","paper_url":"https://arxiv.org/abs/2311.10605v2","paper_title":"CA-Jaccard: Camera-aware Jaccard Distance for Person Re-identification","code":"https://github.com/chen960/ca-jaccard","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"PCL-CLIP (L_pcl)","metrics":{"Rank-1":"89.2","Rank-10":"95.8","Rank-5":"94.7","mAP":"73.8"},"uses_additional_data":false,"paper_date":"2023-10-26","paper":"/paper/prototypical-contrastive-learning-based-clip","paper_url":"https://arxiv.org/abs/2310.17218v1","paper_title":"Prototypical Contrastive Learning-based CLIP Fine-tuning for Object Re-identification","code":"https://github.com/RikoLi/PCL-CLIP","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"DiP (without RK)","metrics":{"Rank-1":"87.3","mAP":"71.8"},"uses_additional_data":false,"paper_date":"2022-12-24","paper":"/paper/dip-learning-discriminative-implicit-parts","paper_url":"https://arxiv.org/abs/2212.13906v2","paper_title":"DiP: Learning Discriminative Implicit Parts for Person Re-Identification","code":"https://github.com/siyuch-fdu/DiP","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"TransReID","metrics":{"Rank-1":"86.20","mAP":"69.40"},"uses_additional_data":false,"paper_date":"2021-02-08","paper":"/paper/transreid-transformer-based-object-re","paper_url":"https://arxiv.org/abs/2102.04378v2","paper_title":"TransReID: Transformer-based Object Re-Identification","code":"https://github.com/heshuting555/TransReID","n_code_links":4,"syntology":null},{"rank_in_archive_order":15,"model":"Unsupervised Pre-training (ResNet101+MGN)","metrics":{"Rank-1":"86.6","mAP":"68.8"},"uses_additional_data":true,"paper_date":"2020-12-07","paper":"/paper/unsupervised-pre-training-for-person-re","paper_url":"https://arxiv.org/abs/2012.03753v2","paper_title":"Unsupervised Pre-training for Person Re-identification","code":"https://github.com/DengpanFu/LUPerson","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"Weakly Supervised Pre-training (ResNet50+MGN)","metrics":{"Rank-1":"86.0","mAP":"68.0"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/large-scale-pre-training-for-person-re","paper_url":"https://arxiv.org/abs/2203.16533v2","paper_title":"Large-Scale Pre-training for Person Re-identification with Noisy Labels","code":"https://github.com/DengpanFu/LUPerson","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":4}},{"rank_in_archive_order":17,"model":"FlipReID (without re-ranking)","metrics":{"Rank-1":"85.6","mAP":"68.0"},"uses_additional_data":false,"paper_date":"2021-05-12","paper":"/paper/flipreid-closing-the-gap-between-training-and","paper_url":"https://arxiv.org/abs/2105.05639v1","paper_title":"FlipReID: Closing the Gap between Training and Inference in Person Re-Identification","code":"https://github.com/nixingyang/FlipReID","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"CLIP-ReID Baseline + UFFM +AMC","metrics":{"Rank-1":"83.8","mAP":"67.6"},"uses_additional_data":false,"paper_date":"2024-05-02","paper":"/paper/enhancing-person-re-identification-via","paper_url":"https://arxiv.org/abs/2405.01101v5","paper_title":"Enhancing person re-identification via Uncertainty Feature Fusion Method and Auto-weighted Measure Combination","code":"https://github.com/chequanghuy/Enhancing-Person-Re-Identification-via-UFFM-and-AMC","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"Deep Miner (w/o ReRank)","metrics":{"Rank-1":"85.60","mAP":"67.30"},"uses_additional_data":false,"paper_date":"2021-02-18","paper":"/paper/deep-miner-a-deep-and-multi-branch-network","paper_url":"https://arxiv.org/abs/2102.09321v1","paper_title":"Deep Miner: A Deep and Multi-branch Network which Mines Rich and Diverse Features for Person Re-identification","code":"https://github.com/robin-schneider/cicy-fourfolds","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"UniHCP (finetune)","metrics":{"mAP":"67.3"},"uses_additional_data":false,"paper_date":"2023-03-06","paper":"/paper/unihcp-a-unified-model-for-human-centric","paper_url":"https://arxiv.org/abs/2303.02936v4","paper_title":"UniHCP: A Unified Model for Human-Centric Perceptions","code":"https://github.com/opengvlab/unihcp","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":5,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"RGT&RGPR(without RK)","metrics":{"Rank-1":"86.2","mAP":"65.9"},"uses_additional_data":true,"paper_date":"2021-01-21","paper":"/paper/an-effective-data-augmentation-for-person-re","paper_url":"https://arxiv.org/abs/2101.08533v5","paper_title":"Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method","code":"https://github.com/finger-monkey/Data-Augmentation","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"ProNet++","metrics":{"Rank-1":"85.4","mAP":"65.5"},"uses_additional_data":false,"paper_date":"2023-08-21","paper":"/paper/rethinking-person-re-identification-from-a","paper_url":"https://arxiv.org/abs/2308.10717v1","paper_title":"Rethinking Person Re-identification from a Projection-on-Prototypes Perspective","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"GiT","metrics":{"Rank-1":"85.6","mAP":"64.8"},"uses_additional_data":false,"paper_date":"2021-07-12","paper":"/paper/git-graph-interactive-transformer-for-vehicle","paper_url":"https://arxiv.org/abs/2107.05475v3","paper_title":"GiT: Graph Interactive Transformer for Vehicle Re-identification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":24,"model":"CAL(ResNet50)","metrics":{"Rank-1":"84.2","mAP":"64"},"uses_additional_data":false,"paper_date":"2021-08-19","paper":"/paper/counterfactual-attention-learning-for-fine","paper_url":"https://arxiv.org/abs/2108.08728v2","paper_title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification","code":"https://github.com/raoyongming/CAL","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"ReMix","metrics":{"Rank-1":"84.8","mAP":"63.9"},"uses_additional_data":true,"paper_date":"2024-10-29","paper":"/paper/remix-training-generalized-person-re","paper_url":"https://arxiv.org/abs/2410.21938v1","paper_title":"ReMix: Training Generalized Person Re-identification on a Mixture of Data","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":26,"model":"APNet-C(ResNet50)","metrics":{"Rank-1":"83.7","mAP":"63.5"},"uses_additional_data":false,"paper_date":"2021-08-11","paper":"/paper/person-re-identification-via-attention","paper_url":"https://arxiv.org/abs/2108.05340v1","paper_title":"Person Re-identification via Attention Pyramid","code":"https://github.com/chengy12/apnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"MPN (without re-ranking)","metrics":{"Rank-1":"83.5","mAP":"62.7"},"uses_additional_data":false,"paper_date":"2020-03-18","paper":"/paper/multi-task-learning-with-coarse-priors-for","paper_url":"https://arxiv.org/abs/2003.08069v3","paper_title":"Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification","code":"https://github.com/WangKan0128/MPN","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"BoT+UFFM+AMC","metrics":{"Rank-1":"82.0","mAP":"62.3"},"uses_additional_data":false,"paper_date":"2024-05-02","paper":"/paper/enhancing-person-re-identification-via","paper_url":"https://arxiv.org/abs/2405.01101v5","paper_title":"Enhancing person re-identification via Uncertainty Feature Fusion Method and Auto-weighted Measure Combination","code":"https://github.com/chequanghuy/Enhancing-Person-Re-Identification-via-UFFM-and-AMC","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"Adaptive L2 Regularization (without re-ranking)","metrics":{"Rank-1":"81.7","mAP":"62.2"},"uses_additional_data":false,"paper_date":"2020-07-15","paper":"/paper/adaptivereid-adaptive-l2-regularization-in","paper_url":"https://arxiv.org/abs/2007.07875v2","paper_title":"Adaptive L2 Regularization in Person Re-Identification","code":"https://github.com/nixingyang/AdaptiveL2Regularization","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"CACENET (ResNet50 w/o RR)","metrics":{"Rank-1":"83.54","mAP":"62.00"},"uses_additional_data":false,"paper_date":"2020-09-11","paper":"/paper/devil-s-in-the-detail-graph-based-key-point","paper_url":"https://arxiv.org/abs/2009.05250v2","paper_title":"Devil's in the Details: Aligning Visual Clues for Conditional Embedding in Person Re-Identification","code":"https://github.com/TencentYoutuResearch/PersonReID-CACENET","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"ABD-Net (ResNet-50)","metrics":{"Rank-1":"82.3","mAP":"60.8"},"uses_additional_data":false,"paper_date":"2019-08-03","paper":"/paper/abd-net-attentive-but-diverse-person-re","paper_url":"https://arxiv.org/abs/1908.01114v3","paper_title":"ABD-Net: Attentive but Diverse Person Re-Identification","code":"https://github.com/vita-group/abd-net","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":7,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"MSINet (2.3M w/o RK)","metrics":{"Rank-1":"81","mAP":"59.6"},"uses_additional_data":false,"paper_date":"2023-03-13","paper":"/paper/msinet-twins-contrastive-search-of-multi","paper_url":"https://arxiv.org/abs/2303.07065v1","paper_title":"MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID","code":"https://github.com/vimar-gu/msinet","n_code_links":1,"syntology":null},{"rank_in_archive_order":33,"model":"OSNet","metrics":{"Rank-1":"78.7","mAP":"52.9"},"uses_additional_data":false,"paper_date":"2019-05-02","paper":"/paper/omni-scale-feature-learning-for-person-re","paper_url":"https://arxiv.org/abs/1905.00953v6","paper_title":"Omni-Scale Feature Learning for Person Re-Identification","code":"https://github.com/mikel-brostrom/boxmot","n_code_links":17,"syntology":{"n_ran":9,"n_unverified":17,"n_samples":26,"n_pointer_only_licence":3}},{"rank_in_archive_order":34,"model":"DG-Net","metrics":{"Rank-1":"77.2","Rank-10":"90.5","Rank-5":"87.4","mAP":"52.3"},"uses_additional_data":false,"paper_date":"2019-04-15","paper":"/paper/joint-discriminative-and-generative-learning","paper_url":"https://arxiv.org/abs/1904.07223v3","paper_title":"Joint Discriminative and Generative Learning for Person Re-identification","code":"https://github.com/layumi/Person_reID_baseline_pytorch","n_code_links":12,"syntology":{"n_ran":11,"n_unverified":8,"n_samples":19,"n_pointer_only_licence":0}},{"rank_in_archive_order":35,"model":"MGN + CircleLoss(ours)","metrics":{"Rank-1":"76.9","mAP":"52.1"},"uses_additional_data":false,"paper_date":"2020-02-25","paper":"/paper/circle-loss-a-unified-perspective-of-pair","paper_url":"https://arxiv.org/abs/2002.10857v2","paper_title":"Circle Loss: A Unified Perspective of Pair Similarity Optimization","code":"https://github.com/layumi/Person_reID_baseline_pytorch","n_code_links":16,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":36,"model":"ResNet50 + CircleLoss(ours)","metrics":{"Rank-1":"76.3","mAP":"50.2"},"uses_additional_data":false,"paper_date":"2020-02-25","paper":"/paper/circle-loss-a-unified-perspective-of-pair","paper_url":"https://arxiv.org/abs/2002.10857v2","paper_title":"Circle Loss: A Unified Perspective of Pair Similarity Optimization","code":"https://github.com/layumi/Person_reID_baseline_pytorch","n_code_links":16,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":37,"model":"OSNet-IAP 1.0x","metrics":{"Rank-1":"77.97","mAP":"48.66"},"uses_additional_data":false,"paper_date":"2020-03-17","paper":"/paper/building-computationally-efficient-and-well","paper_url":"https://arxiv.org/abs/2003.07618v2","paper_title":"Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning","code":"https://github.com/opencv/openvino_training_extensions","n_code_links":1,"syntology":null},{"rank_in_archive_order":38,"model":"CBN","metrics":{"Rank-1":"72.8","mAP":"42.9"},"uses_additional_data":false,"paper_date":"2020-01-23","paper":"/paper/disassembling-the-dataset-a-camera-alignment","paper_url":"https://arxiv.org/abs/2001.08680v3","paper_title":"Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization","code":"https://github.com/automan000/Camera-based-Person-ReID","n_code_links":1,"syntology":null},{"rank_in_archive_order":39,"model":"DLCE","metrics":{"Rank-1":"60.48","mAP":"31.58"},"uses_additional_data":false,"paper_date":"2016-11-17","paper":"/paper/a-discriminatively-learned-cnn-embedding-for","paper_url":"http://arxiv.org/abs/1611.05666v2","paper_title":"A Discriminatively Learned CNN Embedding for Person Re-identification","code":"https://github.com/layumi/2016_person_re-ID","n_code_links":4,"syntology":null},{"rank_in_archive_order":40,"model":"OGNet","metrics":{"Rank-1":"47.71","mAP":"23.01"},"uses_additional_data":false,"paper_date":"2020-06-08","paper":"/paper/person-re-identification-in-the-3d-space","paper_url":"https://arxiv.org/abs/2006.04569v3","paper_title":"Parameter-Efficient Person Re-identification in the 3D Space","code":"https://github.com/layumi/person-reid-3d","n_code_links":1,"syntology":null},{"rank_in_archive_order":41,"model":"UTAL","metrics":{"Rank-1":"31.4","mAP":"13.1"},"uses_additional_data":false,"paper_date":"2019-03-01","paper":"/paper/unsupervised-tracklet-person-re","paper_url":"http://arxiv.org/abs/1903.00535v1","paper_title":"Unsupervised Tracklet Person Re-Identification","code":"https://github.com/liminxian/DukeMTMC-SI-Tracklet","n_code_links":1,"syntology":null},{"rank_in_archive_order":42,"model":"TAUDL","metrics":{"mAP":"12.5"},"uses_additional_data":false,"paper_date":"2018-09-08","paper":"/paper/unsupervised-person-re-identification-by-deep-1","paper_url":"http://arxiv.org/abs/1809.02874v1","paper_title":"Unsupervised Person Re-identification by Deep Learning Tracklet Association","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":43,"model":"TransReID-SSL (without RK)","metrics":{"Rank-1":"89.6"},"uses_additional_data":true,"paper_date":"2021-11-23","paper":"/paper/self-supervised-pre-training-for-transformer","paper_url":"https://arxiv.org/abs/2111.12084v1","paper_title":"Self-Supervised Pre-Training for Transformer-Based Person Re-Identification","code":"https://github.com/DengpanFu/LUPerson","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":8}}],"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,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N 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).","rows_with_graph_line":13,"rows_with_any_sample_ran":13,"distinct_papers_with_graph_line":10,"distinct_papers_with_any_sample_ran":10,"samples_over_distinct_papers":{"n_ran":54,"n_unverified":51,"n_samples":105,"n_pointer_only_licence":17,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":60,"n_unverified":57,"n_samples":117,"n_pointer_only_licence":27,"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"}}}