{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/bair-robot-pushing","name":"BAIR Robot Pushing","full_name":null,"description_markdown":"Dataset of 64x64 images of a robot pushing objects on a table top. From Berkeley AI Research (BAIR).\r\n\r\nSource: Self-Supervised Visual Planning with Temporal Skip Connections (https://arxiv.org/abs/1710.05268)\r\n\r\nVideo prediction : Conditioned on 2 frames, predict 14 frames.","description_withheld":null,"homepage":"https://sites.google.com/berkeley.edu/robotic-interaction-datasets","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Video Prediction","url":"/task/video-prediction","datasets_with_task":"/datasets/task/video-prediction"},{"name":"Video Generation","url":"/task/video-generation","datasets_with_task":"/datasets/task/video-generation"}],"languages":[],"variants":["BAIR Robot Pushing"],"data_loaders":[],"num_papers_in_archive":27,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-generation-on-bair-robot-pushing","task":"Video Generation","dataset_variant":"BAIR Robot Pushing","rows":31,"metrics":["FVD score","SSIM","PSNR","LPIPS","Cond","Train","Pred","Notes"],"first_row_in_archive_order":{"model":"MAGVIT","paper":"/paper/magvit-masked-generative-video-transformer","metrics":{"Cond":"1","FVD score":"62","Pred":"15","Train":"15"},"code_links":[{"title":"google-research/magvit","url":"https://github.com/google-research/magvit"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-prediction-on-bair-robot-pushing-1","task":"Video Prediction","dataset_variant":"BAIR Robot Pushing","rows":6,"metrics":["FVD"],"first_row_in_archive_order":{"model":"MAGVIT (-L-FP)","paper":"/paper/magvit-masked-generative-video-transformer","metrics":{"FVD":"62±0.1"},"code_links":[{"title":"google-research/magvit","url":"https://github.com/google-research/magvit"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":24,"of":24,"counts":{"papers_with_a_benchmark_row":24,"with_a_code_link":23,"where_syntology_ran_a_sample":13,"not_listed_spam_title":0,"listed":24,"listed_where_code_ran":13,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":12,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":12,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/magvit-masked-generative-video-transformer","slug":"magvit-masked-generative-video-transformer","title":"MAGVIT: Masked Generative Video Transformer","date":"2022-12-10","arxiv_id":"2212.05199","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["google-research/magvit"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/magvit-masked-generative-video-transformer#ran","syntology_url":"https://syntology.ai/paper/2212.05199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.05199"}}}},{"paper":"/paper/tell-me-what-happened-unifying-text-guided","slug":"tell-me-what-happened-unifying-text-guided","title":"Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation","date":"2022-11-23","arxiv_id":"2211.12824","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/phenaki-variable-length-video-generation-from","slug":"phenaki-variable-length-video-generation-from","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","date":"2022-10-05","arxiv_id":"2210.02399","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/phenaki-variable-length-video-generation-from#ran","syntology_url":"https://syntology.ai/paper/2210.02399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02399"}}}},{"paper":"/paper/diffusion-models-for-video-prediction-and","slug":"diffusion-models-for-video-prediction-and","title":"Diffusion Models for Video Prediction and Infilling","date":"2022-06-15","arxiv_id":"2206.07696","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":8,"samples_unverified":7,"pointer_only_for_licence":11,"official":{"repos":["Tobi-r9/RaMViD"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":7,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/diffusion-models-for-video-prediction-and#ran","syntology_url":"https://syntology.ai/paper/2206.07696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07696"}}}},{"paper":"/paper/masked-conditional-video-diffusion-for","slug":"masked-conditional-video-diffusion-for","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","date":"2022-05-19","arxiv_id":"2205.09853","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":7,"samples_constructed":1,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":9,"pointer_only_for_licence":0,"official":{"repos":["voletiv/mcvd-pytorch"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/masked-conditional-video-diffusion-for#ran","syntology_url":"https://syntology.ai/paper/2205.09853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.09853"}}}},{"paper":"/paper/nuwa-visual-synthesis-pre-training-for-neural","slug":"nuwa-visual-synthesis-pre-training-for-neural","title":"NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion","date":"2021-11-24","arxiv_id":"2111.12417","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/nuwa-visual-synthesis-pre-training-for-neural#ran","syntology_url":"https://syntology.ai/paper/2111.12417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12417"}}}},{"paper":"/paper/slamp-stochastic-latent-appearance-and-motion","slug":"slamp-stochastic-latent-appearance-and-motion","title":"SLAMP: Stochastic Latent Appearance and Motion Prediction","date":"2021-08-05","arxiv_id":"2108.02760","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["kaanakan/slamp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/slamp-stochastic-latent-appearance-and-motion#ran","syntology_url":"https://syntology.ai/paper/2108.02760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.02760"}}}},{"paper":"/paper/ccvs-context-aware-controllable-video","slug":"ccvs-context-aware-controllable-video","title":"CCVS: Context-aware Controllable Video Synthesis","date":"2021-07-16","arxiv_id":"2107.08037","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["16lemoing/ccvs"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ccvs-context-aware-controllable-video#ran","syntology_url":"https://syntology.ai/paper/2107.08037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.08037"}}}},{"paper":"/paper/diverse-video-generation-using-a-gaussian-1","slug":"diverse-video-generation-using-a-gaussian-1","title":"Diverse Video Generation using a Gaussian Process Trigger","date":"2021-07-09","arxiv_id":"2107.04619","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fitvid-overfitting-in-pixel-level-video","slug":"fitvid-overfitting-in-pixel-level-video","title":"FitVid: Overfitting in Pixel-Level Video Prediction","date":"2021-06-24","arxiv_id":"2106.13195","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["google-research/fitvid"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fitvid-overfitting-in-pixel-level-video#ran","syntology_url":"https://syntology.ai/paper/2106.13195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13195"}}}},{"paper":"/paper/videogpt-video-generation-using-vq-vae-and","slug":"videogpt-video-generation-using-vq-vae-and","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","date":"2021-04-20","arxiv_id":"2104.10157","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/latent-video-transformer","slug":"latent-video-transformer","title":"Latent Video Transformer","date":"2020-06-18","arxiv_id":"2006.10704","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["rakhimovv/lvt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/latent-video-transformer#ran","syntology_url":"https://syntology.ai/paper/2006.10704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.10704"}}}},{"paper":"/paper/transformation-based-adversarial-video","slug":"transformation-based-adversarial-video","title":"Transformation-based Adversarial Video Prediction on Large-Scale Data","date":"2020-03-09","arxiv_id":"2003.04035","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/exploring-spatial-temporal-multi-frequency","slug":"exploring-spatial-temporal-multi-frequency","title":"Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction","date":"2020-02-23","arxiv_id":"2002.09905","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/stochastic-latent-residual-video-prediction-1","slug":"stochastic-latent-residual-video-prediction-1","title":"Stochastic Latent Residual Video Prediction","date":"2020-02-21","arxiv_id":"2002.09219","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["edouardelasalles/srvp"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/stochastic-latent-residual-video-prediction-1#ran","syntology_url":"https://syntology.ai/paper/2002.09219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.09219"}}}},{"paper":"/paper/efficient-video-generation-on-complex","slug":"efficient-video-generation-on-complex","title":"Adversarial Video Generation on Complex Datasets","date":"2019-07-15","arxiv_id":"1907.06571","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/scaling-autoregressive-video-models","slug":"scaling-autoregressive-video-models","title":"Scaling Autoregressive Video Models","date":"2019-06-06","arxiv_id":"1906.02634","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improved-conditional-vrnns-for-video","slug":"improved-conditional-vrnns-for-video","title":"Improved Conditional VRNNs for Video Prediction","date":"2019-04-27","arxiv_id":"1904.12165","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/videoflow-a-flow-based-generative-model-for","slug":"videoflow-a-flow-based-generative-model-for","title":"VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation","date":"2019-03-04","arxiv_id":"1903.01434","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/stochastic-adversarial-video-prediction","slug":"stochastic-adversarial-video-prediction","title":"Stochastic Adversarial Video Prediction","date":"2018-04-04","arxiv_id":"1804.01523","rows_on_this_dataset":4,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":6,"pointer_only_for_licence":3,"official":{"repos":["alexlee-gk/video_prediction"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/stochastic-adversarial-video-prediction#ran","syntology_url":"https://syntology.ai/paper/1804.01523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.01523"}}}},{"paper":"/paper/stochastic-video-generation-with-a-learned","slug":"stochastic-video-generation-with-a-learned","title":"Stochastic Video Generation with a Learned Prior","date":"2018-02-21","arxiv_id":"1802.07687","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["edenton/svg"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/stochastic-video-generation-with-a-learned#ran","syntology_url":"https://syntology.ai/paper/1802.07687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.07687"}}}},{"paper":"/paper/stochastic-variational-video-prediction","slug":"stochastic-variational-video-prediction","title":"Stochastic Variational Video Prediction","date":"2017-10-30","arxiv_id":"1710.11252","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/mocogan-decomposing-motion-and-content-for","slug":"mocogan-decomposing-motion-and-content-for","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","date":"2017-07-17","arxiv_id":"1707.04993","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/unsupervised-learning-for-physical","slug":"unsupervised-learning-for-physical","title":"Unsupervised Learning for Physical Interaction through Video Prediction","date":"2016-05-23","arxiv_id":"1605.07157","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unsupervised-learning-for-physical#ran","syntology_url":"https://syntology.ai/paper/1605.07157","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.07157"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/magvit-masked-generative-video-transformer","slug":"magvit-masked-generative-video-transformer","title":"MAGVIT: Masked Generative Video Transformer","date":"2022-12-10","arxiv_id":"2212.05199","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["google-research/magvit"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/magvit-masked-generative-video-transformer#ran","syntology_url":"https://syntology.ai/paper/2212.05199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.05199"}}}},{"paper":"/paper/tell-me-what-happened-unifying-text-guided","slug":"tell-me-what-happened-unifying-text-guided","title":"Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation","date":"2022-11-23","arxiv_id":"2211.12824","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/phenaki-variable-length-video-generation-from","slug":"phenaki-variable-length-video-generation-from","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","date":"2022-10-05","arxiv_id":"2210.02399","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/phenaki-variable-length-video-generation-from#ran","syntology_url":"https://syntology.ai/paper/2210.02399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02399"}}}},{"paper":"/paper/diffusion-models-for-video-prediction-and","slug":"diffusion-models-for-video-prediction-and","title":"Diffusion Models for Video Prediction and Infilling","date":"2022-06-15","arxiv_id":"2206.07696","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":8,"samples_unverified":7,"pointer_only_for_licence":11,"official":{"repos":["Tobi-r9/RaMViD"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":7,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/diffusion-models-for-video-prediction-and#ran","syntology_url":"https://syntology.ai/paper/2206.07696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07696"}}}},{"paper":"/paper/masked-conditional-video-diffusion-for","slug":"masked-conditional-video-diffusion-for","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","date":"2022-05-19","arxiv_id":"2205.09853","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":7,"samples_constructed":1,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":9,"pointer_only_for_licence":0,"official":{"repos":["voletiv/mcvd-pytorch"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/masked-conditional-video-diffusion-for#ran","syntology_url":"https://syntology.ai/paper/2205.09853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.09853"}}}},{"paper":"/paper/nuwa-visual-synthesis-pre-training-for-neural","slug":"nuwa-visual-synthesis-pre-training-for-neural","title":"NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion","date":"2021-11-24","arxiv_id":"2111.12417","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/nuwa-visual-synthesis-pre-training-for-neural#ran","syntology_url":"https://syntology.ai/paper/2111.12417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12417"}}}},{"paper":"/paper/slamp-stochastic-latent-appearance-and-motion","slug":"slamp-stochastic-latent-appearance-and-motion","title":"SLAMP: Stochastic Latent Appearance and Motion Prediction","date":"2021-08-05","arxiv_id":"2108.02760","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["kaanakan/slamp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/slamp-stochastic-latent-appearance-and-motion#ran","syntology_url":"https://syntology.ai/paper/2108.02760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.02760"}}}},{"paper":"/paper/ccvs-context-aware-controllable-video","slug":"ccvs-context-aware-controllable-video","title":"CCVS: Context-aware Controllable Video Synthesis","date":"2021-07-16","arxiv_id":"2107.08037","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["16lemoing/ccvs"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ccvs-context-aware-controllable-video#ran","syntology_url":"https://syntology.ai/paper/2107.08037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.08037"}}}},{"paper":"/paper/diverse-video-generation-using-a-gaussian-1","slug":"diverse-video-generation-using-a-gaussian-1","title":"Diverse Video Generation using a Gaussian Process Trigger","date":"2021-07-09","arxiv_id":"2107.04619","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fitvid-overfitting-in-pixel-level-video","slug":"fitvid-overfitting-in-pixel-level-video","title":"FitVid: Overfitting in Pixel-Level Video Prediction","date":"2021-06-24","arxiv_id":"2106.13195","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["google-research/fitvid"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fitvid-overfitting-in-pixel-level-video#ran","syntology_url":"https://syntology.ai/paper/2106.13195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13195"}}}},{"paper":"/paper/videogpt-video-generation-using-vq-vae-and","slug":"videogpt-video-generation-using-vq-vae-and","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","date":"2021-04-20","arxiv_id":"2104.10157","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/latent-video-transformer","slug":"latent-video-transformer","title":"Latent Video Transformer","date":"2020-06-18","arxiv_id":"2006.10704","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["rakhimovv/lvt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/latent-video-transformer#ran","syntology_url":"https://syntology.ai/paper/2006.10704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.10704"}}}},{"paper":"/paper/transformation-based-adversarial-video","slug":"transformation-based-adversarial-video","title":"Transformation-based Adversarial Video Prediction on Large-Scale Data","date":"2020-03-09","arxiv_id":"2003.04035","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/exploring-spatial-temporal-multi-frequency","slug":"exploring-spatial-temporal-multi-frequency","title":"Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction","date":"2020-02-23","arxiv_id":"2002.09905","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/stochastic-latent-residual-video-prediction-1","slug":"stochastic-latent-residual-video-prediction-1","title":"Stochastic Latent Residual Video Prediction","date":"2020-02-21","arxiv_id":"2002.09219","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["edouardelasalles/srvp"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/stochastic-latent-residual-video-prediction-1#ran","syntology_url":"https://syntology.ai/paper/2002.09219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.09219"}}}},{"paper":"/paper/efficient-video-generation-on-complex","slug":"efficient-video-generation-on-complex","title":"Adversarial Video Generation on Complex Datasets","date":"2019-07-15","arxiv_id":"1907.06571","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/scaling-autoregressive-video-models","slug":"scaling-autoregressive-video-models","title":"Scaling Autoregressive Video Models","date":"2019-06-06","arxiv_id":"1906.02634","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improved-conditional-vrnns-for-video","slug":"improved-conditional-vrnns-for-video","title":"Improved Conditional VRNNs for Video Prediction","date":"2019-04-27","arxiv_id":"1904.12165","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/videoflow-a-flow-based-generative-model-for","slug":"videoflow-a-flow-based-generative-model-for","title":"VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation","date":"2019-03-04","arxiv_id":"1903.01434","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/stochastic-adversarial-video-prediction","slug":"stochastic-adversarial-video-prediction","title":"Stochastic Adversarial Video Prediction","date":"2018-04-04","arxiv_id":"1804.01523","rows_on_this_dataset":4,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":6,"pointer_only_for_licence":3,"official":{"repos":["alexlee-gk/video_prediction"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/stochastic-adversarial-video-prediction#ran","syntology_url":"https://syntology.ai/paper/1804.01523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.01523"}}}},{"paper":"/paper/stochastic-video-generation-with-a-learned","slug":"stochastic-video-generation-with-a-learned","title":"Stochastic Video Generation with a Learned Prior","date":"2018-02-21","arxiv_id":"1802.07687","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["edenton/svg"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/stochastic-video-generation-with-a-learned#ran","syntology_url":"https://syntology.ai/paper/1802.07687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.07687"}}}},{"paper":"/paper/stochastic-variational-video-prediction","slug":"stochastic-variational-video-prediction","title":"Stochastic Variational Video Prediction","date":"2017-10-30","arxiv_id":"1710.11252","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/mocogan-decomposing-motion-and-content-for","slug":"mocogan-decomposing-motion-and-content-for","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","date":"2017-07-17","arxiv_id":"1707.04993","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/unsupervised-learning-for-physical","slug":"unsupervised-learning-for-physical","title":"Unsupervised Learning for Physical Interaction through Video Prediction","date":"2016-05-23","arxiv_id":"1605.07157","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unsupervised-learning-for-physical#ran","syntology_url":"https://syntology.ai/paper/1605.07157","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.07157"}}}}],"papers_where_code_ran":13,"papers_where_code_ran_first_page":"/dataset/bair-robot-pushing/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/bair-robot-pushing/papers/ran/1","json":"/dataset/bair-robot-pushing/papers/ran/1.json","rows":13}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":13,"samples_harvested":109,"samples_ran":79,"samples_constructed":3,"samples_ran_checked":57,"samples_ran_instrument_failed":22,"samples_unverified":30,"pointer_only_for_licence":27,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":13,"papers_with_a_run_with_no_instrument_failure":12,"papers_where_every_run_was_an_instrument_failure":1,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"75a119b3108ad11fd3415c826b71a17cc4132019e10449d5a1d344947f108676","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}