{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WZVKSH6DM5OPDS3DOQIJGRPAEB","short_pith_number":"pith:WZVKSH6D","schema_version":"1.0","canonical_sha256":"b66aa91fc3675cf1cb6374109345e02048c8a24961c4c04d68efdc33d52bbc10","source":{"kind":"arxiv","id":"1711.10604","version":1},"attestation_state":"computed","paper":{"title":"TensorFlow Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.PL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Alemi, Brian Patton, Dave Moore, Dustin Tran, Eugene Brevdo, Ian Langmore, Joshua V. Dillon, Matt Hoffman, Rif A. Saurous, Srinivas Vasudevan","submitted_at":"2017-11-28T23:05:15Z","abstract_excerpt":"The TensorFlow Distributions library implements a vision of probability theory adapted to the modern deep-learning paradigm of end-to-end differentiable computation. Building on two basic abstractions, it offers flexible building blocks for probabilistic computation. Distributions provide fast, numerically stable methods for generating samples and computing statistics, e.g., log density. Bijectors provide composable volume-tracking transformations with automatic caching. Together these enable modular construction of high dimensional distributions and transformations not possible with previous "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1711.10604","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-28T23:05:15Z","cross_cats_sorted":["cs.AI","cs.PL","stat.ML"],"title_canon_sha256":"b165a8a7440a14e125ddb41906f9e39930e61a6b1c3bd510d22374d4e715174b","abstract_canon_sha256":"4fb3c29e839c762b1811c99379e24c5215de4bbc9708f7a94b68f5bc44bc91ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:07.826788Z","signature_b64":"pAGNisPP6s3NlH2XCeMIjB2g0YytlBynrW/6QwR4ls+WJMUOQ0Ub1QG/b8P3WMHfl7pwiKezsmlT1BayQ18GBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b66aa91fc3675cf1cb6374109345e02048c8a24961c4c04d68efdc33d52bbc10","last_reissued_at":"2026-05-18T00:29:07.826043Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:07.826043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TensorFlow Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.PL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Alemi, Brian Patton, Dave Moore, Dustin Tran, Eugene Brevdo, Ian Langmore, Joshua V. Dillon, Matt Hoffman, Rif A. Saurous, Srinivas Vasudevan","submitted_at":"2017-11-28T23:05:15Z","abstract_excerpt":"The TensorFlow Distributions library implements a vision of probability theory adapted to the modern deep-learning paradigm of end-to-end differentiable computation. Building on two basic abstractions, it offers flexible building blocks for probabilistic computation. Distributions provide fast, numerically stable methods for generating samples and computing statistics, e.g., log density. Bijectors provide composable volume-tracking transformations with automatic caching. Together these enable modular construction of high dimensional distributions and transformations not possible with previous "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.10604","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1711.10604","created_at":"2026-05-18T00:29:07.826160+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.10604v1","created_at":"2026-05-18T00:29:07.826160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.10604","created_at":"2026-05-18T00:29:07.826160+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZVKSH6DM5OP","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZVKSH6DM5OPDS3D","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZVKSH6D","created_at":"2026-05-18T12:31:53.515858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1912.11554","citing_title":"Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"1912.01603","citing_title":"Dream to Control: Learning Behaviors by Latent Imagination","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05493","citing_title":"A renormalization-group inspired lattice-based framework for piecewise generalized linear models","ref_index":157,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01676","citing_title":"Missingness-aware Data Imputation via AI-powered Bayesian Generative Modeling","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13457","citing_title":"Excited-State Quantum Chemistry on Qumode-Based Processors via Variational Quantum Deflation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20723","citing_title":"Tokenised Flow Matching for Hierarchical Simulation Based Inference","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WZVKSH6DM5OPDS3DOQIJGRPAEB","json":"https://pith.science/pith/WZVKSH6DM5OPDS3DOQIJGRPAEB.json","graph_json":"https://pith.science/api/pith-number/WZVKSH6DM5OPDS3DOQIJGRPAEB/graph.json","events_json":"https://pith.science/api/pith-number/WZVKSH6DM5OPDS3DOQIJGRPAEB/events.json","paper":"https://pith.science/paper/WZVKSH6D"},"agent_actions":{"view_html":"https://pith.science/pith/WZVKSH6DM5OPDS3DOQIJGRPAEB","download_json":"https://pith.science/pith/WZVKSH6DM5OPDS3DOQIJGRPAEB.json","view_paper":"https://pith.science/paper/WZVKSH6D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.10604&json=true","fetch_graph":"https://pith.science/api/pith-number/WZVKSH6DM5OPDS3DOQIJGRPAEB/graph.json","fetch_events":"https://pith.science/api/pith-number/WZVKSH6DM5OPDS3DOQIJGRPAEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZVKSH6DM5OPDS3DOQIJGRPAEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZVKSH6DM5OPDS3DOQIJGRPAEB/action/storage_attestation","attest_author":"https://pith.science/pith/WZVKSH6DM5OPDS3DOQIJGRPAEB/action/author_attestation","sign_citation":"https://pith.science/pith/WZVKSH6DM5OPDS3DOQIJGRPAEB/action/citation_signature","submit_replication":"https://pith.science/pith/WZVKSH6DM5OPDS3DOQIJGRPAEB/action/replication_record"}},"created_at":"2026-05-18T00:29:07.826160+00:00","updated_at":"2026-05-18T00:29:07.826160+00:00"}