{"url":"/sota/synthetic-to-real-translation-on-synthia-to-1","task":{"name":"Synthetic-to-Real Translation","url":"/task/synthetic-to-real-translation","note":null},"dataset":{"name":"SYNTHIA-to-Cityscapes","url":"/dataset/synthia"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Synthetic-to-real translation is the task of domain adaptation from synthetic (or virtual) data to real data.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [CYCADA](https://arxiv.org/pdf/1711.03213v3.pdf) )</span>","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":["MIoU (16 classes)","MIoU (13 classes)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"MIoU (16 classes)":null,"MIoU (13 classes)":null}},"counts":{"rows":38,"rows_with_code":33,"rows_with_paper_page":38,"rows_dated":38,"rows_using_additional_data":3},"rows":[{"rank_in_archive_order":1,"model":"DCF","metrics":{"MIoU (13 classes)":"75.9","MIoU (16 classes)":"69.3"},"uses_additional_data":true,"paper_date":"2023-11-21","paper":"/paper/transferring-to-real-world-layouts-a-depth","paper_url":"https://arxiv.org/abs/2311.12682v1","paper_title":"Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation","code":"https://github.com/chen742/PiPa","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"HRDA+PiPa","metrics":{"MIoU (13 classes)":"74.8","MIoU (16 classes)":"68.2"},"uses_additional_data":false,"paper_date":"2022-11-14","paper":"/paper/pipa-pixel-and-patch-wise-self-supervised","paper_url":"https://arxiv.org/abs/2211.07609v1","paper_title":"PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation","code":"https://github.com/chen742/PiPa","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"MIC","metrics":{"MIoU (13 classes)":"74.0","MIoU (16 classes)":"67.3"},"uses_additional_data":false,"paper_date":"2022-12-02","paper":"/paper/mic-masked-image-consistency-for-context","paper_url":"https://arxiv.org/abs/2212.01322v2","paper_title":"MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation","code":"https://github.com/lhoyer/mic","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"CLUDA+HRDA","metrics":{"MIoU (16 classes)":"67.2"},"uses_additional_data":false,"paper_date":"2022-08-27","paper":"/paper/cluda-contrastive-learning-in-unsupervised","paper_url":"https://arxiv.org/abs/2208.14227v2","paper_title":"CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation","code":"https://github.com/user0407/CLUDA","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"HRDA","metrics":{"MIoU (13 classes)":"72.4","MIoU (16 classes)":"65.8"},"uses_additional_data":false,"paper_date":"2022-04-27","paper":"/paper/hrda-context-aware-high-resolution-domain","paper_url":"https://arxiv.org/abs/2204.13132v2","paper_title":"HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation","code":"https://github.com/lhoyer/hrda","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"SePiCo","metrics":{"MIoU (13 classes)":"71.4","MIoU (16 classes)":"64.3"},"uses_additional_data":false,"paper_date":"2022-04-19","paper":"/paper/sepico-semantic-guided-pixel-contrast-for","paper_url":"https://arxiv.org/abs/2204.08808v2","paper_title":"SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation","code":"https://github.com/bit-da/sepico","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":7,"model":"DAFormer + ProCST","metrics":{"MIoU (16 classes)":"61.6"},"uses_additional_data":true,"paper_date":"2022-04-25","paper":"/paper/procst-boosting-semantic-segmentation-using","paper_url":"https://arxiv.org/abs/2204.11891v2","paper_title":"ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer","code":"https://github.com/shahaf1313/procst","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"EHTDI*","metrics":{"MIoU (13 classes)":"69.2","MIoU (16 classes)":"61.3"},"uses_additional_data":false,"paper_date":"2022-08-12","paper":"/paper/exploring-high-quality-target-domain","paper_url":"https://arxiv.org/abs/2208.06100v1","paper_title":"Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentation","code":"https://github.com/ljjcoder/ehtdi","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"DAFormer","metrics":{"MIoU (13 classes)":"67.4","MIoU (16 classes)":"60.9"},"uses_additional_data":false,"paper_date":"2021-11-29","paper":"/paper/daformer-improving-network-architectures-and","paper_url":"https://arxiv.org/abs/2111.14887v2","paper_title":"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation","code":"https://github.com/lhoyer/DAFormer","n_code_links":3,"syntology":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":10,"model":"Sepico + HIAST","metrics":{"MIoU (13 classes)":"68.1","MIoU (16 classes)":"59.6"},"uses_additional_data":false,"paper_date":"2023-02-14","paper":"/paper/hard-aware-instance-adaptive-self-training","paper_url":"https://arxiv.org/abs/2302.06992v1","paper_title":"Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation","code":"https://github.com/bupt-ai-cz/hiast","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"TransDA-B","metrics":{"MIoU (13 classes)":"66.3","MIoU (16 classes)":"59.3"},"uses_additional_data":false,"paper_date":"2022-03-15","paper":"/paper/smoothing-matters-momentum-transformer-for","paper_url":"https://arxiv.org/abs/2203.07988v1","paper_title":"Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation","code":"https://github.com/alpc91/transda","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":2}},{"rank_in_archive_order":12,"model":"SePiCo (ResNet-101)","metrics":{"MIoU (13 classes)":"66.5","MIoU (16 classes)":"58.1"},"uses_additional_data":false,"paper_date":"2022-04-19","paper":"/paper/sepico-semantic-guided-pixel-contrast-for","paper_url":"https://arxiv.org/abs/2204.08808v2","paper_title":"SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation","code":"https://github.com/bit-da/sepico","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":13,"model":"EHTDI","metrics":{"MIoU (13 classes)":"64.6","MIoU (16 classes)":"57.8"},"uses_additional_data":false,"paper_date":"2022-08-12","paper":"/paper/exploring-high-quality-target-domain","paper_url":"https://arxiv.org/abs/2208.06100v1","paper_title":"Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentation","code":"https://github.com/ljjcoder/ehtdi","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"ProDA+CRA","metrics":{"MIoU (13 classes)":"63.7","MIoU (16 classes)":"56.9"},"uses_additional_data":false,"paper_date":"2021-09-14","paper":"/paper/cross-region-domain-adaptation-for-class","paper_url":"https://arxiv.org/abs/2109.06422v2","paper_title":"Cross-Region Domain Adaptation for Class-level Alignment","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"G2L","metrics":{"MIoU (13 classes)":"64.4","MIoU (16 classes)":"56.8"},"uses_additional_data":false,"paper_date":"2022-09-07","paper":"/paper/g2l-a-global-to-local-alignment-method-for","paper_url":"https://www.sciencedirect.com/science/article/pii/S1877050922012170","paper_title":"G2L: A Global to Local Alignment Method for Unsupervised Domain Adaptive Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"ProDA(ResNet-101)","metrics":{"MIoU (13 classes)":"62.0","MIoU (16 classes)":"55.5"},"uses_additional_data":false,"paper_date":"2021-01-26","paper":"/paper/prototypical-pseudo-label-denoising-and","paper_url":"https://arxiv.org/abs/2101.10979v2","paper_title":"Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation","code":"https://github.com/microsoft/ProDA","n_code_links":2,"syntology":{"n_ran":8,"n_unverified":9,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"CorDA(ResNet-101)","metrics":{"MIoU (13 classes)":"62.8","MIoU (16 classes)":"55.0"},"uses_additional_data":true,"paper_date":"2021-04-28","paper":"/paper/domain-adaptive-semantic-segmentation-with","paper_url":"https://arxiv.org/abs/2104.13613v2","paper_title":"Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation","code":"https://github.com/qinenergy/corda","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":18,"model":"AdaptSeg + HIAST","metrics":{"MIoU (13 classes)":"60.3","MIoU (16 classes)":"53.5"},"uses_additional_data":false,"paper_date":"2023-02-14","paper":"/paper/hard-aware-instance-adaptive-self-training","paper_url":"https://arxiv.org/abs/2302.06992v1","paper_title":"Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation","code":"https://github.com/bupt-ai-cz/hiast","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"SAC(ResNet-101)","metrics":{"MIoU (13 classes)":"59.3","MIoU (16 classes)":"52.6"},"uses_additional_data":false,"paper_date":"2021-04-30","paper":"/paper/self-supervised-augmentation-consistency-for","paper_url":"https://arxiv.org/abs/2105.00097v1","paper_title":"Self-supervised Augmentation Consistency for Adapting Semantic Segmentation","code":"https://github.com/visinf/da-sac","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"DSP(ResNet-101)","metrics":{"MIoU (13 classes)":"59.9","MIoU (16 classes)":"51.0"},"uses_additional_data":false,"paper_date":"2021-07-20","paper":"/paper/dsp-dual-soft-paste-for-unsupervised-domain","paper_url":"https://arxiv.org/abs/2107.09600v3","paper_title":"DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation","code":"https://github.com/GaoLii/DSP","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"Uncertainty + Adaboost (ResNet-101)","metrics":{"MIoU (13 classes)":"57.5","MIoU (16 classes)":"50.4"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/adaptive-boosting-for-domain-adaptation","paper_url":"https://arxiv.org/abs/2103.15685v3","paper_title":"Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation","code":"https://github.com/layumi/AdaBoost_Seg","n_code_links":2,"syntology":null},{"rank_in_archive_order":22,"model":"CLST(ResNet-101)","metrics":{"MIoU (13 classes)":"57.8","MIoU (16 classes)":"49.8"},"uses_additional_data":false,"paper_date":"2021-05-05","paper":"/paper/contrastive-learning-and-self-training-for","paper_url":"https://arxiv.org/abs/2105.02001v1","paper_title":"Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"IAST(ResNet-101)","metrics":{"MIoU (13 classes)":"57.0","MIoU (16 classes)":"49.8"},"uses_additional_data":false,"paper_date":"2020-08-27","paper":"/paper/instance-adaptive-self-training-for","paper_url":"https://arxiv.org/abs/2008.12197v1","paper_title":"Instance Adaptive Self-Training for Unsupervised Domain Adaptation","code":"https://github.com/bupt-ai-cz/IAST-ECCV2020","n_code_links":2,"syntology":null},{"rank_in_archive_order":24,"model":"DACS(ResNet-101)","metrics":{"MIoU (13 classes)":"54.81","MIoU (16 classes)":"48.34"},"uses_additional_data":false,"paper_date":"2020-07-17","paper":"/paper/dacs-domain-adaptation-via-cross-domain-mixed","paper_url":"https://arxiv.org/abs/2007.08702v2","paper_title":"DACS: Domain Adaptation via Cross-domain Mixed Sampling","code":"https://github.com/vikolss/DACS","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":25,"model":"Coarse-to-Fine(ResNet-101)","metrics":{"MIoU (13 classes)":"55.5","MIoU (16 classes)":"48.2"},"uses_additional_data":false,"paper_date":"2021-03-24","paper":"/paper/coarse-to-fine-domain-adaptive-semantic","paper_url":"https://arxiv.org/abs/2103.13041v1","paper_title":"Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":26,"model":"MRNet+Rectifying Label(ResNet-101)","metrics":{"MIoU (13 classes)":"54.9","MIoU (16 classes)":"47.9"},"uses_additional_data":false,"paper_date":"2020-03-08","paper":"/paper/rectifying-pseudo-label-learning-via","paper_url":"https://arxiv.org/abs/2003.03773v3","paper_title":"Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation","code":"https://github.com/layumi/Seg-Uncertainty","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":27,"model":"PLCA (ResNet-101)","metrics":{"MIoU (13 classes)":"54.0","MIoU (16 classes)":"46.8"},"uses_additional_data":false,"paper_date":"2020-10-31","paper":"/paper/pixel-level-cycle-association-a-new","paper_url":"https://arxiv.org/abs/2011.00147v1","paper_title":"Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation","code":"https://github.com/kgl-prml/Pixel-Level-Cycle-Association","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"ITEN","metrics":{"MIoU (16 classes)":"46.45"},"uses_additional_data":false,"paper_date":"2021-07-13","paper":"/paper/exploiting-image-translations-via-ensemble","paper_url":"https://arxiv.org/abs/2107.06235v1","paper_title":"Exploiting Image Translations via Ensemble Self-Supervised Learning for Unsupervised Domain Adaptation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":29,"model":"PixMatch(ResNet-101)","metrics":{"MIoU (13 classes)":"54.5","MIoU (16 classes)":"46.1"},"uses_additional_data":false,"paper_date":"2021-05-17","paper":"/paper/pixmatch-unsupervised-domain-adaptation-via","paper_url":"https://arxiv.org/abs/2105.08128v1","paper_title":"PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training","code":"https://github.com/lukemelas/pixmatch","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":30,"model":"MRNet + Adaboost (ResNet-101)","metrics":{"MIoU (13 classes)":"52.9","MIoU (16 classes)":"45.9"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/adaptive-boosting-for-domain-adaptation","paper_url":"https://arxiv.org/abs/2103.15685v3","paper_title":"Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation","code":"https://github.com/layumi/AdaBoost_Seg","n_code_links":2,"syntology":null},{"rank_in_archive_order":31,"model":"FADA(ResNet-101)","metrics":{"MIoU (13 classes)":"52.5","MIoU (16 classes)":"45.2"},"uses_additional_data":false,"paper_date":"2020-07-17","paper":"/paper/classes-matter-a-fine-grained-adversarial","paper_url":"https://arxiv.org/abs/2007.09222v1","paper_title":"Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation","code":"https://github.com/JDAI-CV/FADA","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"MetaCorrection(ResNet-101)","metrics":{"MIoU (13 classes)":"52.5","MIoU (16 classes)":"45.1"},"uses_additional_data":false,"paper_date":"2021-03-09","paper":"/paper/metacorrection-domain-aware-meta-loss","paper_url":"https://arxiv.org/abs/2103.05254v1","paper_title":"MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation","code":"https://github.com/cyang-cityu/MetaCorrection","n_code_links":1,"syntology":null},{"rank_in_archive_order":33,"model":"CAG-UDA","metrics":{"MIoU (13 classes)":"52.6","MIoU (16 classes)":"44.5"},"uses_additional_data":false,"paper_date":"2019-10-29","paper":"/paper/category-anchor-guided-unsupervised-domain","paper_url":"https://arxiv.org/abs/1910.13049v2","paper_title":"Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation","code":"https://github.com/RogerZhangzz/CAG_UDA","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":34,"model":"CAMix (w DAFormer)","metrics":{"MIoU (13 classes)":"69.2"},"uses_additional_data":false,"paper_date":"2021-08-08","paper":"/paper/context-aware-mixup-for-domain-adaptive","paper_url":"https://arxiv.org/abs/2108.03557v3","paper_title":"Context-Aware Mixup for Domain Adaptive Semantic Segmentation","code":"https://github.com/qianyuzqy/CAMix","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":35,"model":"CAMix (ResNet 101)","metrics":{"MIoU (13 classes)":"59.7"},"uses_additional_data":false,"paper_date":"2021-08-08","paper":"/paper/context-aware-mixup-for-domain-adaptive","paper_url":"https://arxiv.org/abs/2108.03557v3","paper_title":"Context-Aware Mixup for Domain Adaptive Semantic Segmentation","code":"https://github.com/qianyuzqy/CAMix","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":36,"model":"MRNet(ResNet-101)","metrics":{"MIoU (13 classes)":"53.8"},"uses_additional_data":false,"paper_date":"2019-12-24","paper":"/paper/unsupervised-scene-adaptation-with-memory","paper_url":"https://arxiv.org/abs/1912.11164v3","paper_title":"Unsupervised Scene Adaptation with Memory Regularization in vivo","code":"https://github.com/layumi/Seg-Uncertainty","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":37,"model":"CLAN","metrics":{"MIoU (13 classes)":"47.8"},"uses_additional_data":false,"paper_date":"2018-09-25","paper":"/paper/taking-a-closer-look-at-domain-shift-category","paper_url":"http://arxiv.org/abs/1809.09478v3","paper_title":"Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation","code":"https://github.com/RoyalVane/CLAN","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":6,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":38,"model":"AdaptSegNet(Multi-level)","metrics":{"MIoU (13 classes)":"46.7"},"uses_additional_data":false,"paper_date":"2018-02-28","paper":"/paper/learning-to-adapt-structured-output-space-for","paper_url":"https://arxiv.org/abs/1802.10349v3","paper_title":"Learning to Adapt Structured Output Space for Semantic Segmentation","code":"https://github.com/wasidennis/AdaptSegNet","n_code_links":12,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":7}}],"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 7,081 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":7081,"papers_extracted_not_yet_verified":217,"boards_without_verdict":27,"papers_not_yet_extracted":2325},"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":17,"rows_with_any_sample_ran":17,"distinct_papers_with_graph_line":15,"distinct_papers_with_any_sample_ran":15,"samples_over_distinct_papers":{"n_ran":54,"n_unverified":30,"n_samples":84,"n_pointer_only_licence":30,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":58,"n_unverified":31,"n_samples":89,"n_pointer_only_licence":32,"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"}}}