{"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":"/paper/tensorflow-distributions","title":"TensorFlow Distributions","arxiv_id":"1711.10604","date":"2017-11-28","proceeding":null,"authors":["Joshua V. Dillon","Ian Langmore","Dustin Tran","Eugene Brevdo","Srinivas Vasudevan","Dave Moore","Brian Patton","Alex Alemi","Matt Hoffman","Rif A. Saurous"],"abstract":"The TensorFlow Distributions library implements a vision of probability\ntheory adapted to the modern deep-learning paradigm of end-to-end\ndifferentiable computation. Building on two basic abstractions, it offers\nflexible building blocks for probabilistic computation. Distributions provide\nfast, numerically stable methods for generating samples and computing\nstatistics, e.g., log density. Bijectors provide composable volume-tracking\ntransformations with automatic caching. Together these enable modular\nconstruction of high dimensional distributions and transformations not possible\nwith previous libraries (e.g., pixelCNNs, autoregressive flows, and reversible\nresidual networks). They are the workhorse behind deep probabilistic\nprogramming systems like Edward and empower fast black-box inference in\nprobabilistic models built on deep-network components. TensorFlow Distributions\nhas proven an important part of the TensorFlow toolkit within Google and in the\nbroader deep learning community.","url_abs":"http://arxiv.org/abs/1711.10604v1","url_pdf":"http://arxiv.org/pdf/1711.10604v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"tensorflow-distributions","repo_url":"https://github.com/acr42/Neural-Variational-Knowledge-Graphs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tensorflow-distributions","repo_url":"https://github.com/hongseok-yang/probprog19","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"tensorflow-distributions","repo_url":"https://github.com/kampta/pytorch-distributions","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"tensorflow-distributions","repo_url":"https://github.com/mukehvier/tensorflow-prob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"tensorflow-distributions","repo_url":"https://github.com/nicola-decao/s-vae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tensorflow-distributions","repo_url":"https://github.com/nicola-decao/s-vae-tf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tensorflow-distributions","repo_url":"https://github.com/tensorflow/probability","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"tensorflow-distributions","repo_url":"https://github.com/zhoudoao-bayes/tf-probability","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"probabilistic-programming","task_name":"Probabilistic Programming"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.10604","atlas_url":"https://app.syntology.ai/?focus=1711.10604","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1711.10604"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1711.10604\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1711.10604"},"call":"get_concepts_for_paper(arxiv_id=\"1711.10604\")"}],"by_repo":[{"repo":"acr42/Neural-Variational-Knowledge-Graphs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1804.00891"],"harvested_for_calls":[{"arxiv_id":"1804.00891","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1804.00891"},"call":"get_harvested_code_for_paper(arxiv_id=\"1804.00891\")"}]},{"repo":"hongseok-yang/probprog19","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"kampta/pytorch-distributions","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1312.6114","1611.01144"],"harvested_for_calls":[{"arxiv_id":"1312.6114","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1312.6114"},"call":"get_harvested_code_for_paper(arxiv_id=\"1312.6114\")"},{"arxiv_id":"1611.01144","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1611.01144"},"call":"get_harvested_code_for_paper(arxiv_id=\"1611.01144\")"}]},{"repo":"mukehvier/tensorflow-prob","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"nicola-decao/s-vae","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1804.00891"],"harvested_for_calls":[{"arxiv_id":"1804.00891","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1804.00891"},"call":"get_harvested_code_for_paper(arxiv_id=\"1804.00891\")"}]},{"repo":"nicola-decao/s-vae-tf","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"tensorflow/probability","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2402.01915"],"harvested_for_calls":[{"arxiv_id":"2402.01915","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.01915"},"call":"get_harvested_code_for_paper(arxiv_id=\"2402.01915\")"}]},{"repo":"zhoudoao-bayes/tf-probability","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"85a05c5ec57e874f6fe6621e63de968836e3e5bab40f9ebe62ca315234d01d81","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}