{"url":"/task/video-generation","name":"Video Generation","slug":"video-generation","description_markdown":"<span style=\"color:grey; opacity: 0.6\">( Various Video Generation Tasks.\r\nGif credit: [MaGViT](https://paperswithcode.com/paper/magvit-masked-generative-video-transformer) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1466,"papers_with_code":609,"benchmarks":16,"benchmark_tables_in_archive":16,"benchmark_tables_shown":16,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":24,"subtasks":2,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-generation-on-ucf-101","slug":"video-generation-on-ucf-101","dataset":"UCF-101","dataset_url":"/dataset/ucf101","rows_in_archive":48,"metrics":["FVD16","FVD128","Inception Score","KVD16"],"first_row_in_archive_order":{"model":"W.A.L.T-XL (class-conditional)","paper_title":"Photorealistic Video Generation with Diffusion Models","paper_url":"/paper/photorealistic-video-generation-with","paper_date":"2023-12-11","arxiv_id":"2312.06662","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-generation-on-bair-robot-pushing","slug":"video-generation-on-bair-robot-pushing","dataset":"BAIR Robot Pushing","dataset_url":"/dataset/bair-robot-pushing","rows_in_archive":31,"metrics":["FVD score","SSIM","PSNR","LPIPS","Cond","Train","Pred","Notes"],"first_row_in_archive_order":{"model":"MAGVIT","paper_title":"MAGVIT: Masked Generative Video Transformer","paper_url":"/paper/magvit-masked-generative-video-transformer","paper_date":"2022-12-10","arxiv_id":"2212.05199","code_links":[{"title":"google-research/magvit","url":"https://github.com/google-research/magvit"}],"syntology":{"n":10,"n_ran":1,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/video-generation-on-sky-time-lapse","slug":"video-generation-on-sky-time-lapse","dataset":"Sky Time-lapse","dataset_url":null,"rows_in_archive":9,"metrics":["FVD 16","KVD16"],"first_row_in_archive_order":{"model":"StyleSV (256x256)","paper_title":"Towards Smooth Video Composition","paper_url":"/paper/towards-smooth-video-composition","paper_date":"2022-12-14","arxiv_id":"2212.07413","code_links":[{"title":"genforce/StyleSV","url":"https://github.com/genforce/StyleSV"}],"syntology":null}},{"leaderboard":"/sota/video-generation-on-ucf-101-16-frames","slug":"video-generation-on-ucf-101-16-frames","dataset":"UCF-101 16 frames, Unconditional, Single GPU","dataset_url":"/dataset/ucf101","rows_in_archive":7,"metrics":["Inception Score"],"first_row_in_archive_order":{"model":"TGAN-F","paper_title":"Lower Dimensional Kernels for Video Discriminators","paper_url":"/paper/lower-dimensional-kernels-for-video","paper_date":"2019-12-18","arxiv_id":"1912.08860","code_links":[{"title":"HappyBahman/ldvdGAN","url":"https://github.com/HappyBahman/ldvdGAN"}],"syntology":null}},{"leaderboard":"/sota/video-generation-on-ucf-101-16-frames-64x64","slug":"video-generation-on-ucf-101-16-frames-64x64","dataset":"UCF-101 16 frames, 64x64, Unconditional","dataset_url":"/dataset/ucf101","rows_in_archive":7,"metrics":["Inception Score","FID","FVD"],"first_row_in_archive_order":{"model":"Video Diffusion Model","paper_title":"Video Diffusion Models","paper_url":"/paper/video-diffusion-models","paper_date":"2022-04-07","arxiv_id":"2204.03458","code_links":[{"title":"lucidrains/make-a-video-pytorch","url":"https://github.com/lucidrains/make-a-video-pytorch"},{"title":"lucidrains/video-diffusion-pytorch","url":"https://github.com/lucidrains/video-diffusion-pytorch"},{"title":"coderpiaobozhe/classifier-free-diffusion-guidance-Pytorch","url":"https://github.com/coderpiaobozhe/classifier-free-diffusion-guidance-Pytorch"},{"title":"ndrwmlnk/awesome-video-diffusion-models","url":"https://github.com/ndrwmlnk/awesome-video-diffusion-models"},{"title":"eyeline-research/survey-video-diffusion","url":"https://github.com/eyeline-research/survey-video-diffusion"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/video-generation-on-laion-400m","slug":"video-generation-on-laion-400m","dataset":"LAION-400M","dataset_url":"/dataset/laion-400m","rows_in_archive":6,"metrics":["CLIP R-Precision","CLIP"],"first_row_in_archive_order":{"model":"Imagen original (constant=6)","paper_title":"Imagen Video: High Definition Video Generation with Diffusion Models","paper_url":"/paper/imagen-video-high-definition-video-generation","paper_date":"2022-10-05","arxiv_id":"2210.02303","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-generation-on-taichi","slug":"video-generation-on-taichi","dataset":"Taichi","dataset_url":null,"rows_in_archive":6,"metrics":["FVD16","KVD16"],"first_row_in_archive_order":{"model":"StyleSV (256x256)","paper_title":"Towards Smooth Video Composition","paper_url":"/paper/towards-smooth-video-composition","paper_date":"2022-12-14","arxiv_id":"2212.07413","code_links":[{"title":"genforce/StyleSV","url":"https://github.com/genforce/StyleSV"}],"syntology":null}},{"leaderboard":"/sota/video-generation-on-ucf-101-16-frames-128x128","slug":"video-generation-on-ucf-101-16-frames-128x128","dataset":"UCF-101 16 frames, 128x128, Unconditional","dataset_url":"/dataset/ucf101","rows_in_archive":6,"metrics":["Inception Score"],"first_row_in_archive_order":{"model":"TGANv2 (2020)","paper_title":"Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN","paper_url":"/paper/tganv2-efficient-training-of-large-models-for","paper_date":"2018-11-22","arxiv_id":"1811.09245","code_links":[{"title":"pfnet-research/tgan2","url":"https://github.com/pfnet-research/tgan2"},{"title":"Zasder3/Tganv2-PyTorch-Train-Sparsely--Generate-Densely","url":"https://github.com/Zasder3/Tganv2-PyTorch-Train-Sparsely--Generate-Densely"}],"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/video-generation-on-kinetics-600-12-frames","slug":"video-generation-on-kinetics-600-12-frames","dataset":"Kinetics-600 12 frames, 64x64","dataset_url":"/dataset/kinetics","rows_in_archive":4,"metrics":["FVD"],"first_row_in_archive_order":{"model":"W.A.L.T-L","paper_title":"Photorealistic Video Generation with Diffusion Models","paper_url":"/paper/photorealistic-video-generation-with","paper_date":"2023-12-11","arxiv_id":"2312.06662","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-generation-on-how2sign","slug":"video-generation-on-how2sign","dataset":"How2Sign","dataset_url":"/dataset/how2sign","rows_in_archive":1,"metrics":["FVD16"],"first_row_in_archive_order":{"model":"INR-V","paper_title":"INR-V: A Continuous Representation Space for Video-based Generative Tasks","paper_url":"/paper/inr-v-a-continuous-representation-space-for","paper_date":"2022-10-29","arxiv_id":"2210.16579","code_links":[{"title":"bipashasen/INRV","url":"https://github.com/bipashasen/INRV"},{"title":"MindSpore-scientific-2/code-5","url":"https://github.com/MindSpore-scientific-2/code-5/tree/main/INR-Implicit-Neural-Representations-with-Periodic-Activation-Functions"},{"title":"MindSpore-scientific/code-11","url":"https://github.com/MindSpore-scientific/code-11/tree/main/INR-Implicit-Neural-Representations-with-Periodic-Activation-Functions"}],"syntology":null}},{"leaderboard":"/sota/video-generation-on-kinetics-600-12-frames-1","slug":"video-generation-on-kinetics-600-12-frames-1","dataset":"Kinetics-600 12 frames, 128x128","dataset_url":"/dataset/kinetics","rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"DVD-GAN","paper_title":"Adversarial Video Generation on Complex Datasets","paper_url":"/paper/efficient-video-generation-on-complex","paper_date":"2019-07-15","arxiv_id":"1907.06571","code_links":[{"title":"Harrypotterrrr/DVD-GAN","url":"https://github.com/Harrypotterrrr/DVD-GAN"}],"syntology":null}},{"leaderboard":"/sota/video-generation-on-kinetics-600-48-frames","slug":"video-generation-on-kinetics-600-48-frames","dataset":"Kinetics-600 48 frames, 64x64","dataset_url":"/dataset/kinetics","rows_in_archive":1,"metrics":["FID","Inception Score"],"first_row_in_archive_order":{"model":"DVD-GAN","paper_title":"Adversarial Video Generation on Complex Datasets","paper_url":"/paper/efficient-video-generation-on-complex","paper_date":"2019-07-15","arxiv_id":"1907.06571","code_links":[{"title":"Harrypotterrrr/DVD-GAN","url":"https://github.com/Harrypotterrrr/DVD-GAN"}],"syntology":null}},{"leaderboard":"/sota/video-generation-on-kinetics-700","slug":"video-generation-on-kinetics-700","dataset":"Kinetics-700","dataset_url":"/dataset/kinetics-700","rows_in_archive":1,"metrics":["FID","FVD"],"first_row_in_archive_order":{"model":"DiT-XL/2 + CVAE-FT-SE","paper_title":"Improving the Diffusability of Autoencoders","paper_url":"/paper/improving-the-diffusability-of-autoencoders","paper_date":"2025-02-20","arxiv_id":"2502.14831","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-generation-on-msr-vtt","slug":"video-generation-on-msr-vtt","dataset":"MSR-VTT","dataset_url":"/dataset/msr-vtt","rows_in_archive":1,"metrics":["FVD16","Inception score"],"first_row_in_archive_order":{"model":"VideoAssembler (Zero-Shot, 256x256, class-conditional)","paper_title":"MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing","paper_url":"/paper/videoassembler-identity-consistent-video","paper_date":"2023-11-29","arxiv_id":"2311.17338","code_links":[{"title":"gulucaptain/videoassembler","url":"https://github.com/gulucaptain/videoassembler"}],"syntology":{"n":12,"n_ran":10,"n_unverified":2,"n_pointer_only":12}}},{"leaderboard":"/sota/video-generation-on-trailerfaces","slug":"video-generation-on-trailerfaces","dataset":"TrailerFaces","dataset_url":null,"rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"PG-SWGAN-3D","paper_title":"Sliced Wasserstein Generative Models","paper_url":"/paper/sliced-wasserstein-generative-models-1","paper_date":"2019-04-10","arxiv_id":"1904.05408","code_links":[{"title":"musikisomorphie/swd","url":"https://github.com/musikisomorphie/swd"}],"syntology":null}},{"leaderboard":"/sota/video-generation-on-youtube-driving","slug":"video-generation-on-youtube-driving","dataset":"YouTube Driving","dataset_url":"/dataset/youtube-driving","rows_in_archive":1,"metrics":["FVD16"],"first_row_in_archive_order":{"model":"StyleSV","paper_title":"Towards Smooth Video Composition","paper_url":"/paper/towards-smooth-video-composition","paper_date":"2022-12-14","arxiv_id":"2212.07413","code_links":[{"title":"genforce/StyleSV","url":"https://github.com/genforce/StyleSV"}],"syntology":null}}],"datasets":[{"url":"/dataset/ucf101","name":"UCF101","full_name":"UCF101 Human Actions dataset","num_papers_in_archive":1863},{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"url":"/dataset/msr-vtt","name":"MSR-VTT","full_name":"","num_papers_in_archive":640},{"url":"/dataset/webvid","name":"WebVid","full_name":"","num_papers_in_archive":257},{"url":"/dataset/laion-400m","name":"LAION-400M","full_name":"","num_papers_in_archive":169},{"url":"/dataset/kinetics-600","name":"Kinetics-600","full_name":"","num_papers_in_archive":148},{"url":"/dataset/kinetics-700","name":"Kinetics-700","full_name":"Kinetics-700","num_papers_in_archive":95},{"url":"/dataset/internvid","name":"InternVid","full_name":"","num_papers_in_archive":46},{"url":"/dataset/how2sign","name":"How2Sign","full_name":"A Large-scale Multimodal Dataset for Continuous American Sign Language","num_papers_in_archive":44},{"url":"/dataset/bair-robot-pushing","name":"BAIR Robot Pushing","full_name":"","num_papers_in_archive":27},{"url":"/dataset/celebv-text","name":"CelebV-Text","full_name":"","num_papers_in_archive":15},{"url":"/dataset/opens2v-eval","name":"OpenS2V-Eval","full_name":"","num_papers_in_archive":8},{"url":"/dataset/youtube-driving","name":"YouTube Driving","full_name":"","num_papers_in_archive":6},{"url":"/dataset/chronomagic","name":"ChronoMagic","full_name":"","num_papers_in_archive":5},{"url":"/dataset/deep-fakes-dataset","name":"Deep Fakes Dataset","full_name":"inamibora","num_papers_in_archive":3},{"url":"/dataset/qst","name":"QST","full_name":"Quick Sky Time","num_papers_in_archive":3},{"url":"/dataset/avsync15","name":"AVSync15","full_name":"","num_papers_in_archive":2},{"url":"/dataset/chronomagic-pro","name":"ChronoMagic-Pro","full_name":"","num_papers_in_archive":2},{"url":"/dataset/dropletvideo-10m","name":"DropletVideo-10M","full_name":"","num_papers_in_archive":2},{"url":"/dataset/chronomagic-proh","name":"ChronoMagic-ProH","full_name":"","num_papers_in_archive":1},{"url":"/dataset/consisid-preview-data","name":"ConsisID-preview-Data","full_name":"","num_papers_in_archive":1},{"url":"/dataset/open-hypermotionx","name":"Open-HypermotionX","full_name":"","num_papers_in_archive":1},{"url":"/dataset/opens2v-5m","name":"OpenS2V-5M","full_name":"","num_papers_in_archive":1},{"url":"/dataset/tlfm-dataset","name":"TLFM dataset","full_name":"TLFM dataset for microscopy image sequence generation","num_papers_in_archive":1}],"subtasks":[{"url":"/task/image-to-video","name":"Image to Video Generation"},{"url":"/task/unconditional-video-generation","name":"Unconditional Video Generation"}],"parent_tasks":[{"url":"/task/video","name":"Video"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":609,"tagged_in_all":1466,"items":[{"url":"/paper/gans-trained-by-a-two-time-scale-update-rule","title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","date":"2017-06-26","arxiv_id":"1706.08500","repositories_listed":71,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/consistency-models","title":"Consistency Models","date":"2023-03-02","arxiv_id":"2303.01469","repositories_listed":15,"syntology":{"n":57,"n_ran":28,"n_unverified":29,"n_pointer_only":8}},{"url":"/paper/everybody-dance-now","title":"Everybody Dance Now","date":"2018-08-22","arxiv_id":"1808.07371","repositories_listed":14,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/temporally-coherent-gans-for-video-super","title":"Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation","date":"2018-11-23","arxiv_id":"1811.09393","repositories_listed":13,"syntology":{"n":25,"n_ran":2,"n_unverified":23,"n_pointer_only":0}},{"url":"/paper/video-diffusion-models","title":"Video Diffusion Models","date":"2022-04-07","arxiv_id":"2204.03458","repositories_listed":5,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/mocogan-decomposing-motion-and-content-for","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","date":"2017-07-17","arxiv_id":"1707.04993","repositories_listed":5,"syntology":null},{"url":"/paper/open-sora-plan-open-source-large-video","title":"Open-Sora Plan: Open-Source Large Video Generation Model","date":"2024-11-28","arxiv_id":"2412.00131","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/latte-latent-diffusion-transformer-for-video","title":"Latte: Latent Diffusion Transformer for Video Generation","date":"2024-01-05","arxiv_id":"2401.03048","repositories_listed":4,"syntology":{"n":13,"n_ran":10,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/align-your-latents-high-resolution-video","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","date":"2023-04-18","arxiv_id":"2304.08818","repositories_listed":4,"syntology":{"n":26,"n_ran":18,"n_unverified":8,"n_pointer_only":1}},{"url":"/paper/collaborative-neural-rendering-using-anime","title":"Collaborative Neural Rendering using Anime Character Sheets","date":"2022-07-12","arxiv_id":"2207.05378","repositories_listed":4,"syntology":null},{"url":"/paper/stochastic-adversarial-video-prediction","title":"Stochastic Adversarial Video Prediction","date":"2018-04-04","arxiv_id":"1804.01523","repositories_listed":4,"syntology":{"n":16,"n_ran":4,"n_unverified":12,"n_pointer_only":3}},{"url":"/paper/temporal-generative-adversarial-nets-with","title":"Temporal Generative Adversarial Nets with Singular Value Clipping","date":"2016-11-21","arxiv_id":"1611.06624","repositories_listed":4,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/step-video-t2v-technical-report-the-practice","title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","date":"2025-02-14","arxiv_id":"2502.10248","repositories_listed":3,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/benchmark-evaluations-applications-and","title":"A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges","date":"2025-01-04","arxiv_id":"2501.02189","repositories_listed":3,"syntology":null},{"url":"/paper/accelerating-diffusion-transformers-with-dual","title":"Accelerating Diffusion Transformers with Dual Feature Caching","date":"2024-12-25","arxiv_id":"2412.18911","repositories_listed":3,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/evaluating-text-to-visual-generation-with","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","date":"2024-04-01","arxiv_id":"2404.01291","repositories_listed":3,"syntology":null},{"url":"/paper/stylecrafter-enhancing-stylized-text-to-video","title":"StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter","date":"2023-12-01","arxiv_id":"2312.00330","repositories_listed":3,"syntology":{"n":23,"n_ran":13,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/stable-video-diffusion-scaling-latent-video-1","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","date":"2023-11-25","arxiv_id":"2311.15127","repositories_listed":3,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/videocrafter1-open-diffusion-models-for-high","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","date":"2023-10-30","arxiv_id":"2310.19512","repositories_listed":3,"syntology":{"n":12,"n_ran":7,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/freenoise-tuning-free-longer-video-diffusion","title":"FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling","date":"2023-10-23","arxiv_id":"2310.15169","repositories_listed":3,"syntology":{"n":24,"n_ran":9,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/language-model-beats-diffusion-tokenizer-is","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","date":"2023-10-09","arxiv_id":"2310.05737","repositories_listed":3,"syntology":{"n":20,"n_ran":12,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/tune-a-video-one-shot-tuning-of-image","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","date":"2022-12-22","arxiv_id":"2212.11565","repositories_listed":3,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/disentangling-aesthetic-and-technical-effects","title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","date":"2022-11-09","arxiv_id":"2211.04894","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/inr-v-a-continuous-representation-space-for","title":"INR-V: A Continuous Representation Space for Video-based Generative Tasks","date":"2022-10-29","arxiv_id":"2210.16579","repositories_listed":3,"syntology":null},{"url":"/paper/videogpt-video-generation-using-vq-vae-and","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","date":"2021-04-20","arxiv_id":"2104.10157","repositories_listed":3,"syntology":null},{"url":"/paper/hierarchical-patch-vae-gan-generating-diverse","title":"Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample","date":"2020-06-22","arxiv_id":"2006.12226","repositories_listed":3,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/dwnet-dense-warp-based-network-for-pose","title":"DwNet: Dense warp-based network for pose-guided human video generation","date":"2019-10-21","arxiv_id":"1910.09139","repositories_listed":3,"syntology":null},{"url":"/paper/point-to-point-video-generation","title":"Point-to-Point Video Generation","date":"2019-04-05","arxiv_id":"1904.02912","repositories_listed":3,"syntology":null},{"url":"/paper/stochastic-video-generation-with-a-learned","title":"Stochastic Video Generation with a Learned Prior","date":"2018-02-21","arxiv_id":"1802.07687","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/hierarchical-video-generation-from-orthogonal","title":"Hierarchical Video Generation from Orthogonal Information: Optical Flow and Texture","date":"2017-11-27","arxiv_id":"1711.09618","repositories_listed":3,"syntology":null}],"syntology_records":21,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":1,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}