{"url":"/sota/low-light-image-enhancement-on-lol","task":{"name":"Low-Light Image Enhancement","url":"/task/low-light-image-enhancement","note":null},"dataset":{"name":"LOL","url":"/dataset/lol"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Low-Light Image Enhancement** is a computer vision task that involves improving the quality of images captured under low-light conditions. The goal of low-light image enhancement is to make images brighter, clearer, and more visually appealing, without introducing too much noise or distortion.","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":["Average PSNR","LPIPS","SSIM","FLOPS (G)","Params (M)","SSIM (sRGB)","Number of params","BSQ-rate over MS-SSIM","FID"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Average PSNR":"higher","LPIPS":null,"SSIM":"higher","FLOPS (G)":"lower","Params (M)":"lower","SSIM (sRGB)":"higher","Number of params":"lower","BSQ-rate over MS-SSIM":"higher","FID":"lower"}},"counts":{"rows":40,"rows_with_code":39,"rows_with_paper_page":40,"rows_dated":40,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"CFWD","metrics":{"Average PSNR":"29.185","SSIM":"0.872"},"uses_additional_data":false,"paper_date":"2024-01-08","paper":"/paper/low-light-image-enhancement-via-clip-fourier","paper_url":"https://arxiv.org/abs/2401.03788v2","paper_title":"Low-light Image Enhancement via CLIP-Fourier Guided Wavelet Diffusion","code":"https://github.com/hejh8/cfwd","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"BEM_","metrics":{"Average PSNR":"28.80","LPIPS":"0.069","SSIM":"0.884"},"uses_additional_data":false,"paper_date":"2024-10-13","paper":"/paper/bayesian-enhancement-models-for-one-to-many","paper_url":"https://openreview.net/forum?id=jJJOoLVAEm","paper_title":"Bayesian Enhancement Models for One-to-Many Mapping in Image Enhancement","code":"https://github.com/Anonymous1563/Bayesian-Enhancement-Model","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"CIDNet","metrics":{"Average PSNR":"28.141","FLOPS (G)":"7.57","LPIPS":"0.079","Params (M)":"1.88","SSIM":"0.889","SSIM (sRGB)":"0.889"},"uses_additional_data":false,"paper_date":"2024-02-08","paper":"/paper/you-only-need-one-color-space-an-efficient","paper_url":"https://arxiv.org/abs/2402.05809v3","paper_title":"You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement","code":"https://github.com/fediory/hvi-cidnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"GlobalDiff","metrics":{"Average PSNR":"27.83","LPIPS":"0.091","SSIM":"0.877"},"uses_additional_data":false,"paper_date":"2023-10-26","paper":"/paper/global-structure-aware-diffusion-process-for-1","paper_url":"https://arxiv.org/abs/2310.17577v2","paper_title":"Global Structure-Aware Diffusion Process for Low-Light Image Enhancement","code":"https://github.com/jinnh/GSAD","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":5,"model":"GLARE","metrics":{"Average PSNR":"27.35","LPIPS":"0.083","SSIM":"0.883","SSIM (sRGB)":"0.883"},"uses_additional_data":false,"paper_date":"2024-07-17","paper":"/paper/glare-low-light-image-enhancement-via","paper_url":"https://arxiv.org/abs/2407.12431v1","paper_title":"GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval","code":"https://github.com/lowlevelai/glare","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"LYT-Net","metrics":{"Average PSNR":"27.23","FLOPS (G)":"3.49","LPIPS":"0.071","Params (M)":"0.045","SSIM":"0.853"},"uses_additional_data":false,"paper_date":"2024-01-26","paper":"/paper/lyt-net-lightweight-yuv-transformer-based","paper_url":"https://arxiv.org/abs/2401.15204v6","paper_title":"LYT-NET: Lightweight YUV Transformer-based Network for Low-light Image Enhancement","code":"https://github.com/albrateanu/LYT-Net/tree/main/PyTorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":7,"model":"WaveNet-B_","metrics":{"Average PSNR":"27.22","LPIPS":"0.083","SSIM":"0.873"},"uses_additional_data":false,"paper_date":"2023-10-10","paper":"/paper/wavenet-wave-aware-image-enhancement","paper_url":"https://diglib.eg.org/bitstream/handle/10.2312/pg20231267/021-029.pdf","paper_title":"WaveNet: Wave-Aware Image Enhancement","code":"https://github.com/DeniJsonC/WaveNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"KAN-T","metrics":{"Average PSNR":"27.18","Params (M)":"2.80","SSIM":"0.864"},"uses_additional_data":false,"paper_date":"2024-11-07","paper":"/paper/enhancing-low-light-images-with-kolmogorov","paper_url":"https://ieeexplore.ieee.org/abstract/document/10797300","paper_title":"Enhancing Low-Light Images with Kolmogorov–Arnold Networks in Transformer Attention","code":"https://github.com/albrateanu/KANT","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"Retinexformer_","metrics":{"Average PSNR":"27.18","FLOPS (G)":"15.57","Params (M)":"1.61","SSIM":"0.850"},"uses_additional_data":false,"paper_date":"2023-03-12","paper":"/paper/retinexformer-one-stage-retinex-based","paper_url":"https://arxiv.org/abs/2303.06705v3","paper_title":"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement","code":"https://github.com/cmhungsteve/Awesome-Transformer-Attention","n_code_links":5,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"PyDiff","metrics":{"Average PSNR":"27.09","LPIPS":"0.10","SSIM":"0.93"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/pyramid-diffusion-models-for-low-light-image","paper_url":"https://arxiv.org/abs/2305.10028v1","paper_title":"Pyramid Diffusion Models For Low-light Image Enhancement","code":"https://github.com/limuloo/pydiff","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":11,"model":"DPEC_","metrics":{"Average PSNR":"27.01","SSIM":"0.872"},"uses_additional_data":false,"paper_date":"2024-06-28","paper":"/paper/resvmunetx-a-low-light-enhancement-network","paper_url":"https://arxiv.org/abs/2407.09553v4","paper_title":"DPEC: Dual-Path Error Compensation Method for Enhanced Low-Light Image Clarity","code":"https://github.com/wangshuang233/DPEC-VM","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"BEM","metrics":{"Average PSNR":"26.83","LPIPS":"0.072","SSIM":"0.877"},"uses_additional_data":false,"paper_date":"2024-10-13","paper":"/paper/bayesian-enhancement-models-for-one-to-many","paper_url":"https://openreview.net/forum?id=jJJOoLVAEm","paper_title":"Bayesian Enhancement Models for One-to-Many Mapping in Image Enhancement","code":"https://github.com/Anonymous1563/Bayesian-Enhancement-Model","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"DiffLL","metrics":{"Average PSNR":"26.336","SSIM":"0.845"},"uses_additional_data":false,"paper_date":"2023-06-01","paper":"/paper/low-light-image-enhancement-with-wavelet","paper_url":"https://arxiv.org/abs/2306.00306v3","paper_title":"Low-Light Image Enhancement with Wavelet-based Diffusion Models","code":"https://github.com/JianghaiSCU/Diffusion-Low-Light","n_code_links":1,"syntology":{"n_ran":12,"n_unverified":1,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"ExpoMamba","metrics":{"Average PSNR":"25.770","LPIPS":"0.212","SSIM":"0.860"},"uses_additional_data":false,"paper_date":"2024-08-19","paper":"/paper/expomamba-exploiting-frequency-ssm-blocks-for","paper_url":"https://arxiv.org/abs/2408.09650v1","paper_title":"ExpoMamba: Exploiting Frequency SSM Blocks for Efficient and Effective Image Enhancement","code":"https://github.com/eashanadhikarla/expomamba","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"WaveNet-B","metrics":{"Average PSNR":"25.44","LPIPS":"0.09","SSIM":"0.864"},"uses_additional_data":false,"paper_date":"2023-10-10","paper":"/paper/wavenet-wave-aware-image-enhancement","paper_url":"https://diglib.eg.org/bitstream/handle/10.2312/pg20231267/021-029.pdf","paper_title":"WaveNet: Wave-Aware Image Enhancement","code":"https://github.com/DeniJsonC/WaveNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"EMNet","metrics":{"Average PSNR":"25.37","LPIPS":"0.086","SSIM":"0.8686"},"uses_additional_data":false,"paper_date":"2023-07-10","paper":"/paper/glow-in-the-dark-low-light-image-enhancement","paper_url":"https://doi.org/10.1109/TMM.2023.3293736","paper_title":"Glow in the Dark: Low-Light Image Enhancement with External Memory","code":"https://github.com/Lineves7/EMNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"LLFlow","metrics":{"Average PSNR":"25.19","LPIPS":"0.11","SSIM":"0.93"},"uses_additional_data":false,"paper_date":"2021-09-13","paper":"/paper/low-light-image-enhancement-with-normalizing","paper_url":"https://arxiv.org/abs/2109.05923v1","paper_title":"Low-Light Image Enhancement with Normalizing Flow","code":"https://github.com/wyf0912/LLFlow","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"Retinexformer","metrics":{"Average PSNR":"25.16","FLOPS (G)":"15.57","Params (M)":"1.61","SSIM":"0.845"},"uses_additional_data":false,"paper_date":"2023-03-12","paper":"/paper/retinexformer-one-stage-retinex-based","paper_url":"https://arxiv.org/abs/2303.06705v3","paper_title":"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement","code":"https://github.com/cmhungsteve/Awesome-Transformer-Attention","n_code_links":5,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"FLIGHTNet","metrics":{"Average PSNR":"24.96","Number of params":"0.025","SSIM":"0.85"},"uses_additional_data":false,"paper_date":"2023-05-18","paper":"/paper/flight-mode-on-a-feather-light-network-for","paper_url":"https://arxiv.org/abs/2305.10889v1","paper_title":"FLIGHT Mode On: A Feather-Light Network for Low-Light Image Enhancement","code":"https://github.com/aselsan-research-imaging-team/flight-net","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"DPEC","metrics":{"Average PSNR":"24.80","SSIM":"0.855"},"uses_additional_data":false,"paper_date":"2024-06-28","paper":"/paper/resvmunetx-a-low-light-enhancement-network","paper_url":"https://arxiv.org/abs/2407.09553v4","paper_title":"DPEC: Dual-Path Error Compensation Method for Enhanced Low-Light Image Clarity","code":"https://github.com/wangshuang233/DPEC-VM","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"Resfusion","metrics":{"Average PSNR":"24.63","LPIPS":"0.107","SSIM":"0.860"},"uses_additional_data":false,"paper_date":"2023-11-25","paper":"/paper/resfusion-prior-residual-noise-embedded","paper_url":"https://arxiv.org/abs/2311.14900v4","paper_title":"Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise","code":"https://github.com/nkicsl/resfusion","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":22,"model":"WaveNet-S","metrics":{"Average PSNR":"24.54","LPIPS":"0.1","SSIM":"0.856"},"uses_additional_data":true,"paper_date":"2023-10-10","paper":"/paper/wavenet-wave-aware-image-enhancement","paper_url":"https://diglib.eg.org/bitstream/handle/10.2312/pg20231267/021-029.pdf","paper_title":"WaveNet: Wave-Aware Image Enhancement","code":"https://github.com/DeniJsonC/WaveNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"HG-MTFE","metrics":{"Average PSNR":"24.26"},"uses_additional_data":false,"paper_date":"2024-10-08","paper":"/paper/image-enhancement-based-on-histogram-guided","paper_url":"https://ieeexplore.ieee.org/abstract/document/10707348","paper_title":"Image Enhancement Based on Histogram-Guided Multiple Transformation Function Estimation","code":"https://github.com/PJaemin/HG-MTFE","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"OneRestore","metrics":{"Average PSNR":"24.25","SSIM":"0.8564"},"uses_additional_data":false,"paper_date":"2024-07-05","paper":"/paper/onerestore-a-universal-restoration-framework","paper_url":"https://arxiv.org/abs/2407.04621v4","paper_title":"OneRestore: A Universal Restoration Framework for Composite Degradation","code":"https://github.com/gy65896/onerestore","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":6,"n_samples":13,"n_pointer_only_licence":13}},{"rank_in_archive_order":25,"model":"HWMNet","metrics":{"Average PSNR":"24.24","LPIPS":"0.12","SSIM":"0.852"},"uses_additional_data":false,"paper_date":"2022-03-02","paper":"/paper/half-wavelet-attention-on-m-net-for-low-light","paper_url":"https://arxiv.org/abs/2203.01296v1","paper_title":"Half Wavelet Attention on M-Net+ for Low-Light Image Enhancement","code":"https://github.com/fanchimao/hwmnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"PPformer","metrics":{"Average PSNR":"23.91","LPIPS":"0.12","SSIM":"0.841"},"uses_additional_data":false,"paper_date":"2024-01-15","paper":"/paper/ppformer-using-pixel-wise-and-patch-wise","paper_url":"https://www.sciencedirect.com/science/article/abs/pii/S1077314224000110","paper_title":"PPformer: Using pixel-wise and patch-wise cross-attention for low-light image enhancement","code":"https://github.com/DeniJsonC/PPformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"DA-CLIP","metrics":{"Average PSNR":"23.77","LPIPS":"0.083","SSIM":"0.830"},"uses_additional_data":false,"paper_date":"2023-10-02","paper":"/paper/controlling-vision-language-models-for","paper_url":"https://arxiv.org/abs/2310.01018v2","paper_title":"Controlling Vision-Language Models for Multi-Task Image Restoration","code":"https://github.com/algolzw/daclip-uir","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"WaveNet-T (80k parameters)","metrics":{"Average PSNR":"23.59","LPIPS":"0.14","SSIM":"0.839"},"uses_additional_data":false,"paper_date":"2023-10-10","paper":"/paper/wavenet-wave-aware-image-enhancement","paper_url":"https://diglib.eg.org/bitstream/handle/10.2312/pg20231267/021-029.pdf","paper_title":"WaveNet: Wave-Aware Image Enhancement","code":"https://github.com/DeniJsonC/WaveNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"CIDNet-Normal","metrics":{"Average PSNR":"23.500","FLOPS (G)":"7.57","LPIPS":"0.086","Params (M)":"1.88","SSIM":"0.870","SSIM (sRGB)":"0.870"},"uses_additional_data":false,"paper_date":"2024-02-08","paper":"/paper/you-only-need-one-color-space-an-efficient","paper_url":"https://arxiv.org/abs/2402.05809v3","paper_title":"You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement","code":"https://github.com/fediory/hvi-cidnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"MAXIM","metrics":{"Average PSNR":"23.43","SSIM":"0.863"},"uses_additional_data":false,"paper_date":"2022-01-09","paper":"/paper/maxim-multi-axis-mlp-for-image-processing","paper_url":"https://arxiv.org/abs/2201.02973v2","paper_title":"MAXIM: Multi-Axis MLP for Image Processing","code":"https://github.com/google-research/maxim","n_code_links":3,"syntology":{"n_ran":31,"n_unverified":15,"n_samples":46,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"IAT (90k parameter)","metrics":{"Average PSNR":"23.38","SSIM":"0.809"},"uses_additional_data":false,"paper_date":"2022-05-30","paper":"/paper/illumination-adaptive-transformer","paper_url":"https://arxiv.org/abs/2205.14871v4","paper_title":"You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction","code":"https://github.com/cuiziteng/illumination-adaptive-transformer","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"Bread","metrics":{"Average PSNR":"22.96","SSIM":"0.838"},"uses_additional_data":false,"paper_date":"2021-11-30","paper":"/paper/low-light-image-enhancement-via-breaking-down","paper_url":"https://arxiv.org/abs/2111.15557v1","paper_title":"Low-light Image Enhancement via Breaking Down the Darkness","code":"https://github.com/mingcv/bread","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"MTFE","metrics":{"Average PSNR":"22.86"},"uses_additional_data":false,"paper_date":"2023-09-01","paper":"/paper/multiple-transformation-function-estimation","paper_url":"https://doi.org/10.1016/j.jvcir.2023.103863","paper_title":"Multiple transformation function estimation for image enhancement","code":"https://github.com/PJaemin/MTFE","n_code_links":1,"syntology":null},{"rank_in_archive_order":34,"model":"TreEnhance","metrics":{"Average PSNR":"21.96","SSIM":"0.81"},"uses_additional_data":false,"paper_date":"2022-05-25","paper":"/paper/treenhance-an-automatic-tree-search-based","paper_url":"https://arxiv.org/abs/2205.12639v2","paper_title":"TreEnhance: A Tree Search Method For Low-Light Image Enhancement","code":"https://github.com/ocram17/treenhance","n_code_links":1,"syntology":null},{"rank_in_archive_order":35,"model":"FoD","metrics":{"Average PSNR":"21.61","FID":"41.31","LPIPS":"0.105","SSIM":"0.819"},"uses_additional_data":false,"paper_date":"2025-05-22","paper":"/paper/forward-only-diffusion-probabilistic-models","paper_url":"https://arxiv.org/abs/2505.16733v1","paper_title":"Forward-only Diffusion Probabilistic Models","code":"https://github.com/Algolzw/FoD","n_code_links":1,"syntology":null},{"rank_in_archive_order":36,"model":"night-enhancement","metrics":{"Average PSNR":"21.52","SSIM":"0.763"},"uses_additional_data":false,"paper_date":"2022-07-21","paper":"/paper/unsupervised-night-image-enhancement-when","paper_url":"https://arxiv.org/abs/2207.10564v2","paper_title":"Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression","code":"https://github.com/jinyeying/night-enhancement","n_code_links":1,"syntology":null},{"rank_in_archive_order":37,"model":"KinD","metrics":{"Average PSNR":"20.8665"},"uses_additional_data":false,"paper_date":"2019-05-04","paper":"/paper/190504161","paper_url":"https://arxiv.org/abs/1905.04161v1","paper_title":"Kindling the Darkness: A Practical Low-light Image Enhancer","code":"https://github.com/zhangyhuaee/KinD","n_code_links":4,"syntology":null},{"rank_in_archive_order":38,"model":"HEP","metrics":{"Average PSNR":"20.23"},"uses_additional_data":false,"paper_date":"2021-12-03","paper":"/paper/unsupervised-low-light-image-enhancement-via","paper_url":"https://arxiv.org/abs/2112.01766v1","paper_title":"Unsupervised Low-Light Image Enhancement via Histogram Equalization Prior","code":"https://github.com/fengzhang427/hep","n_code_links":1,"syntology":null},{"rank_in_archive_order":39,"model":"CDAN","metrics":{"Average PSNR":"20.102","LPIPS":"0.167","SSIM":"0.816"},"uses_additional_data":false,"paper_date":"2023-08-24","paper":"/paper/cdan-convolutional-dense-attention-guided","paper_url":"https://arxiv.org/abs/2308.12902v3","paper_title":"CDAN: Convolutional dense attention-guided network for low-light image enhancement","code":"https://github.com/SinaRaoufi/CDAN","n_code_links":1,"syntology":null},{"rank_in_archive_order":40,"model":"rr","metrics":{"BSQ-rate over MS-SSIM":"0.2"},"uses_additional_data":false,"paper_date":"2022-06-19","paper":"/paper/0-1-deep-neural-networks-via-block-coordinate","paper_url":"https://arxiv.org/abs/2206.09379v2","paper_title":"0/1 Deep Neural Networks via Block Coordinate Descent","code":null,"n_code_links":0,"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,"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 6,821 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":6821,"papers_extracted_not_yet_verified":65,"boards_without_verdict":29,"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":11,"rows_with_any_sample_ran":11,"distinct_papers_with_graph_line":10,"distinct_papers_with_any_sample_ran":10,"samples_over_distinct_papers":{"n_ran":78,"n_unverified":30,"n_samples":108,"n_pointer_only_licence":27,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":83,"n_unverified":35,"n_samples":118,"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"}}}