{"url":"/sota/lane-detection-on-tusimple","task":{"name":"Lane Detection","url":"/task/lane-detection","note":null},"dataset":{"name":"TuSimple","url":"/dataset/tusimple"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Lane Detection** is a computer vision task that involves identifying the boundaries of driving lanes in a video or image of a road scene. The goal is to accurately locate and track the lane markings in real-time, even in challenging conditions such as poor lighting, glare, or complex road layouts. \r\n\r\nLane detection is an important component of advanced driver assistance systems (ADAS) and autonomous vehicles, as it provides information about the road layout and the position of the vehicle within the lane, which is crucial for navigation and safety. The algorithms typically use a combination of computer vision techniques, such as edge detection, color filtering, and Hough transforms, to identify and track the lane markings in a road scene.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [End-to-end Lane Detection\r\n](https://github.com/wvangansbeke/LaneDetection_End2End) )</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":["Accuracy","F1 score"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher","F1 score":"higher"}},"counts":{"rows":43,"rows_with_code":30,"rows_with_paper_page":40,"rows_dated":40,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"SCNN_UNet_Attention_PL*","metrics":{"Accuracy":"98.38"},"uses_additional_data":true,"paper_date":"2023-05-26","paper":"/paper/robust-lane-detection-through-self-pre","paper_url":"https://arxiv.org/abs/2305.17271v2","paper_title":"Robust Lane Detection through Self Pre-training with Masked Sequential Autoencoders and Fine-tuning with Customized PolyLoss","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"CLRNetV2 (ResNet18)","metrics":{"Accuracy":"96.99","F1 score":"97.90"},"uses_additional_data":false,"paper_date":"2025-03-18","paper":"/paper/clrnetv2-a-faster-and-stronger-lane-detector","paper_url":"https://ieeexplore.ieee.org/abstract/document/10930685","paper_title":"CLRNetV2: A Faster and Stronger Lane Detector","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"PE-RESA","metrics":{"Accuracy":"96.93"},"uses_additional_data":false,"paper_date":"2022-03-23","paper":"/paper/lane-detection-with-position-embedding","paper_url":"https://arxiv.org/abs/2203.12301v1","paper_title":"Lane detection with Position Embedding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"FOLOLane(ERFNet)","metrics":{"Accuracy":"96.92"},"uses_additional_data":false,"paper_date":"2021-05-28","paper":"/paper/focus-on-local-detecting-lane-marker-from","paper_url":"https://arxiv.org/abs/2105.13680v1","paper_title":"Focus on Local: Detecting Lane Marker from Bottom Up via Key Point","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"CLRNet(ResNet-34)","metrics":{"Accuracy":"96.9%","F1 score":"97.82"},"uses_additional_data":false,"paper_date":"2022-03-19","paper":"/paper/clrnet-cross-layer-refinement-network-for","paper_url":"https://arxiv.org/abs/2203.10350v1","paper_title":"CLRNet: Cross Layer Refinement Network for Lane Detection","code":"https://github.com/Turoad/lanedet","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"CLRNetV2 (ResNet34)","metrics":{"Accuracy":"96.88","F1 score":"97.95"},"uses_additional_data":false,"paper_date":"2025-03-18","paper":"/paper/clrnetv2-a-faster-and-stronger-lane-detector","paper_url":"https://ieeexplore.ieee.org/abstract/document/10930685","paper_title":"CLRNetV2: A Faster and Stronger Lane Detector","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"CLRNet(ResNet-18)","metrics":{"Accuracy":"96.82%","F1 score":"97.89"},"uses_additional_data":false,"paper_date":"2022-03-19","paper":"/paper/clrnet-cross-layer-refinement-network-for","paper_url":"https://arxiv.org/abs/2203.10350v1","paper_title":"CLRNet: Cross Layer Refinement Network for Lane Detection","code":"https://github.com/Turoad/lanedet","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"RESA","metrics":{"Accuracy":"96.82","F1 score":"96.93"},"uses_additional_data":false,"paper_date":"2020-08-31","paper":"/paper/resa-recurrent-feature-shift-aggregator-for","paper_url":"https://arxiv.org/abs/2008.13719v2","paper_title":"RESA: Recurrent Feature-Shift Aggregator for Lane Detection","code":"https://github.com/Turoad/lanedet","n_code_links":4,"syntology":null},{"rank_in_archive_order":9,"model":"CLLD","metrics":{"Accuracy":"96.82"},"uses_additional_data":false,"paper_date":"2023-08-16","paper":"/paper/contrastive-learning-for-lane-detection-via","paper_url":"https://arxiv.org/abs/2308.08242v4","paper_title":"Contrastive Learning for Lane Detection via cross-similarity","code":"https://github.com/zkyntu/UnLanedet","n_code_links":2,"syntology":null},{"rank_in_archive_order":10,"model":"CANet-L(ResNet101)","metrics":{"Accuracy":"96.76%","F1 score":"97.77"},"uses_additional_data":false,"paper_date":"2023-04-23","paper":"/paper/canet-curved-guide-line-network-with-adaptive","paper_url":"https://arxiv.org/abs/2304.11546v1","paper_title":"CANet: Curved Guide Line Network with Adaptive Decoder for Lane Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"CANet-M","metrics":{"Accuracy":"96.66%","F1 score":"97.44"},"uses_additional_data":false,"paper_date":"2023-04-23","paper":"/paper/canet-curved-guide-line-network-with-adaptive","paper_url":"https://arxiv.org/abs/2304.11546v1","paper_title":"CANet: Curved Guide Line Network with Adaptive Decoder for Lane Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"ENet-SAD","metrics":{"Accuracy":"96.64%","F1 score":"95.92"},"uses_additional_data":false,"paper_date":"2019-08-02","paper":"/paper/learning-lightweight-lane-detection-cnns-by","paper_url":"https://arxiv.org/abs/1908.00821v1","paper_title":"Learning Lightweight Lane Detection CNNs by Self Attention Distillation","code":"https://github.com/cardwing/Codes-for-Lane-Detection","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"HarD-SP","metrics":{"Accuracy":"96.58%","F1 score":"96.38"},"uses_additional_data":false,"paper_date":"2020-08-19","paper":"/paper/towards-lightweight-lane-detection-by","paper_url":"https://arxiv.org/abs/2008.08311v2","paper_title":"Towards Lightweight Lane Detection by Optimizing Spatial Embedding","code":"https://github.com/JungSeokWoo/Lightweight-LaneDetection","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"CANet-S","metrics":{"Accuracy":"96.56%","F1 score":"97.51"},"uses_additional_data":false,"paper_date":"2023-04-23","paper":"/paper/canet-curved-guide-line-network-with-adaptive","paper_url":"https://arxiv.org/abs/2304.11546v1","paper_title":"CANet: Curved Guide Line Network with Adaptive Decoder for Lane Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"CondLaneNet-L(ResNet-101)","metrics":{"Accuracy":"96.54%","F1 score":"97.24"},"uses_additional_data":false,"paper_date":"2021-05-11","paper":"/paper/condlanenet-a-top-to-down-lane-detection","paper_url":"https://arxiv.org/abs/2105.05003v3","paper_title":"CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution","code":"https://github.com/Turoad/lanedet","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"Oblique Convolution","metrics":{"Accuracy":"96.50%","F1 score":"97.42"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"Pairwise pixel supervision + FCN","metrics":{"Accuracy":"96.50%","F1 score":"94.31"},"uses_additional_data":false,"paper_date":"2018-03-17","paper":"/paper/learning-to-cluster-for-proposal-free","paper_url":"http://arxiv.org/abs/1803.06459v1","paper_title":"Learning to Cluster for Proposal-Free Instance Segmentation","code":"https://github.com/GT-RIPL/L2C","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"EL-GAN","metrics":{"Accuracy":"96.40%","F1 score":"96.26"},"uses_additional_data":false,"paper_date":"2018-06-14","paper":"/paper/el-gan-embedding-loss-driven-generative","paper_url":"http://arxiv.org/abs/1806.05525v2","paper_title":"EL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"LaneNet","metrics":{"Accuracy":"96.4%","F1 score":"94.80"},"uses_additional_data":false,"paper_date":"2018-02-15","paper":"/paper/towards-end-to-end-lane-detection-an-instance","paper_url":"http://arxiv.org/abs/1802.05591v1","paper_title":"Towards End-to-End Lane Detection: an Instance Segmentation Approach","code":"https://github.com/MaybeShewill-CV/lanenet-lane-detection","n_code_links":22,"syntology":{"n_ran":3,"n_unverified":31,"n_samples":34,"n_pointer_only_licence":1}},{"rank_in_archive_order":20,"model":"Discriminative loss function","metrics":{"Accuracy":"96.40%"},"uses_additional_data":false,"paper_date":"2017-08-08","paper":"/paper/semantic-instance-segmentation-with-a","paper_url":"http://arxiv.org/abs/1708.02551v1","paper_title":"Semantic Instance Segmentation with a Discriminative Loss Function","code":"https://github.com/Wizaron/instance-segmentation-pytorch","n_code_links":8,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":21,"model":"ENet-Label","metrics":{"Accuracy":"96.29%","F1 score":"95.23"},"uses_additional_data":false,"paper_date":"2019-05-02","paper":"/paper/190503704","paper_url":"http://arxiv.org/abs/1905.03704v1","paper_title":"Agnostic Lane Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"R-34-E2E","metrics":{"Accuracy":"96.22%","F1 score":"96.58"},"uses_additional_data":false,"paper_date":"2020-05-06","paper":"/paper/end-to-end-lane-marker-detection-via-row-wise","paper_url":"https://arxiv.org/abs/2005.08630v1","paper_title":"End-to-End Lane Marker Detection via Row-wise Classification","code":"https://github.com/Vipermdl/E2E-ERFNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"LSTR","metrics":{"Accuracy":"96.18","F1 score":"96.68"},"uses_additional_data":false,"paper_date":"2020-11-09","paper":"/paper/end-to-end-lane-shape-prediction-with","paper_url":"https://arxiv.org/abs/2011.04233v2","paper_title":"End-to-end Lane Shape Prediction with Transformers","code":"https://github.com/liuruijin17/LSTR","n_code_links":2,"syntology":null},{"rank_in_archive_order":24,"model":"R-50-E2E","metrics":{"Accuracy":"96.11%","F1 score":"96.37"},"uses_additional_data":false,"paper_date":"2020-05-06","paper":"/paper/end-to-end-lane-marker-detection-via-row-wise","paper_url":"https://arxiv.org/abs/2005.08630v1","paper_title":"End-to-End Lane Marker Detection via Row-wise Classification","code":"https://github.com/Vipermdl/E2E-ERFNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"LaneATT (ResNet-122)","metrics":{"Accuracy":"96.10%","F1 score":"96.06"},"uses_additional_data":false,"paper_date":"2020-10-22","paper":"/paper/keep-your-eyes-on-the-lane-attention-guided","paper_url":"https://arxiv.org/abs/2010.12035v2","paper_title":"Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection","code":"https://github.com/lucastabelini/LaneATT","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"ERF-E2E","metrics":{"Accuracy":"96.02%","F1 score":"96.25"},"uses_additional_data":false,"paper_date":"2020-05-06","paper":"/paper/end-to-end-lane-marker-detection-via-row-wise","paper_url":"https://arxiv.org/abs/2005.08630v1","paper_title":"End-to-End Lane Marker Detection via Row-wise Classification","code":"https://github.com/Vipermdl/E2E-ERFNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"Lane-LSQ","metrics":{"Accuracy":"95.84%"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"BézierLaneNet (ResNet-34)","metrics":{"Accuracy":"95.65%"},"uses_additional_data":false,"paper_date":"2022-03-04","paper":"/paper/rethinking-efficient-lane-detection-via-curve","paper_url":"https://arxiv.org/abs/2203.02431v2","paper_title":"Rethinking Efficient Lane Detection via Curve Modeling","code":"https://github.com/voldemortX/pytorch-auto-drive","n_code_links":2,"syntology":{"n_ran":12,"n_unverified":0,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":29,"model":"LaneAF","metrics":{"Accuracy":"95.64%","F1 score":"96.49"},"uses_additional_data":false,"paper_date":"2021-03-22","paper":"/paper/laneaf-robust-multi-lane-detection-with","paper_url":"https://arxiv.org/abs/2103.12040v4","paper_title":"LaneAF: Robust Multi-Lane Detection with Affinity Fields","code":"https://github.com/sel118/LaneAF","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"LaneATT (ResNet-34)","metrics":{"Accuracy":"95.63%","F1 score":"96.77"},"uses_additional_data":false,"paper_date":"2020-10-22","paper":"/paper/keep-your-eyes-on-the-lane-attention-guided","paper_url":"https://arxiv.org/abs/2010.12035v2","paper_title":"Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection","code":"https://github.com/lucastabelini/LaneATT","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"Eigenlanes (ResNet-18)","metrics":{"Accuracy":"95.62%"},"uses_additional_data":false,"paper_date":"2022-03-29","paper":"/paper/eigenlanes-data-driven-lane-descriptors-for","paper_url":"https://arxiv.org/abs/2203.15302v1","paper_title":"Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes","code":"https://github.com/dongkwonjin/eigenlanes","n_code_links":2,"syntology":{"n_ran":10,"n_unverified":5,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"LaneATT (ResNet-18)","metrics":{"Accuracy":"95.57%","F1 score":"96.71"},"uses_additional_data":false,"paper_date":"2020-10-22","paper":"/paper/keep-your-eyes-on-the-lane-attention-guided","paper_url":"https://arxiv.org/abs/2010.12035v2","paper_title":"Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection","code":"https://github.com/lucastabelini/LaneATT","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"CondLaneNet(ResNet-18)","metrics":{"Accuracy":"95.48%"},"uses_additional_data":false,"paper_date":"2021-05-11","paper":"/paper/condlanenet-a-top-to-down-lane-detection","paper_url":"https://arxiv.org/abs/2105.05003v3","paper_title":"CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution","code":"https://github.com/Turoad/lanedet","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":34,"model":"BézierLaneNet (ResNet-18)","metrics":{"Accuracy":"95.41%"},"uses_additional_data":false,"paper_date":"2022-03-04","paper":"/paper/rethinking-efficient-lane-detection-via-curve","paper_url":"https://arxiv.org/abs/2203.02431v2","paper_title":"Rethinking Efficient Lane Detection via Curve Modeling","code":"https://github.com/voldemortX/pytorch-auto-drive","n_code_links":2,"syntology":{"n_ran":12,"n_unverified":0,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":35,"model":"CondLaneNet-M(ResNet-34)","metrics":{"Accuracy":"95.37%","F1 score":"96.98"},"uses_additional_data":false,"paper_date":"2021-05-11","paper":"/paper/condlanenet-a-top-to-down-lane-detection","paper_url":"https://arxiv.org/abs/2105.05003v3","paper_title":"CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution","code":"https://github.com/Turoad/lanedet","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":36,"model":"End-to-end ERFNet","metrics":{"Accuracy":"95.24%","F1 score":"90.82"},"uses_additional_data":false,"paper_date":"2019-07-02","paper":"/paper/lane-detection-and-classification-using","paper_url":"https://arxiv.org/abs/1907.01294v2","paper_title":"Lane Detection and Classification using Cascaded CNNs","code":"https://github.com/fabvio/Cascade-LD","n_code_links":2,"syntology":null},{"rank_in_archive_order":37,"model":"ERFNet","metrics":{"Accuracy":"94.5%"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":38,"model":"PolyLaneNet","metrics":{"Accuracy":"93.36%","F1 score":"90.62"},"uses_additional_data":false,"paper_date":"2020-04-23","paper":"/paper/polylanenet-lane-estimation-via-deep","paper_url":"https://arxiv.org/abs/2004.10924v2","paper_title":"PolyLaneNet: Lane Estimation via Deep Polynomial Regression","code":"https://github.com/lucastabelini/PolyLaneNet","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":4,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":39,"model":"GANet(ResNet-34)","metrics":{"F1 score":"97.71"},"uses_additional_data":false,"paper_date":"2022-04-15","paper":"/paper/a-keypoint-based-global-association-network","paper_url":"https://arxiv.org/abs/2204.07335v1","paper_title":"A Keypoint-based Global Association Network for Lane Detection","code":"https://github.com/wolfwjs/ganet","n_code_links":2,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":40,"model":"GANet(ResNet-18)","metrics":{"F1 score":"97.68"},"uses_additional_data":false,"paper_date":"2022-04-15","paper":"/paper/a-keypoint-based-global-association-network","paper_url":"https://arxiv.org/abs/2204.07335v1","paper_title":"A Keypoint-based Global Association Network for Lane Detection","code":"https://github.com/wolfwjs/ganet","n_code_links":2,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":41,"model":"CLRNet(ResNet-101)","metrics":{"F1 score":"97.62"},"uses_additional_data":false,"paper_date":"2022-03-19","paper":"/paper/clrnet-cross-layer-refinement-network-for","paper_url":"https://arxiv.org/abs/2203.10350v1","paper_title":"CLRNet: Cross Layer Refinement Network for Lane Detection","code":"https://github.com/Turoad/lanedet","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":42,"model":"GANet(ResNet-101)","metrics":{"F1 score":"97.45"},"uses_additional_data":false,"paper_date":"2022-04-15","paper":"/paper/a-keypoint-based-global-association-network","paper_url":"https://arxiv.org/abs/2204.07335v1","paper_title":"A Keypoint-based Global Association Network for Lane Detection","code":"https://github.com/wolfwjs/ganet","n_code_links":2,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":43,"model":"CondLaneNet(ResNet-34)","metrics":{"F1 score":"97.01"},"uses_additional_data":false,"paper_date":"2021-05-11","paper":"/paper/condlanenet-a-top-to-down-lane-detection","paper_url":"https://arxiv.org/abs/2105.05003v3","paper_title":"CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution","code":"https://github.com/Turoad/lanedet","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}}],"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":20,"rows_with_any_sample_ran":16,"distinct_papers_with_graph_line":10,"distinct_papers_with_any_sample_ran":8,"samples_over_distinct_papers":{"n_ran":46,"n_unverified":53,"n_samples":99,"n_pointer_only_licence":3,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":75,"n_unverified":75,"n_samples":150,"n_pointer_only_licence":3,"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"}}}