{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:L7YG5WU3YYVMHDC43BOGABLCQZ","short_pith_number":"pith:L7YG5WU3","schema_version":"1.0","canonical_sha256":"5ff06eda9bc62ac38c5cd85c600562865a0593a11bf9e6a7fb450f6192b942dd","source":{"kind":"arxiv","id":"1506.04696","version":2},"attestation_state":"computed","paper":{"title":"A Complete Recipe for Stochastic Gradient MCMC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Emily B. Fox, Tianqi Chen, Yi-An Ma","submitted_at":"2015-06-15T18:32:37Z","abstract_excerpt":"Many recent Markov chain Monte Carlo (MCMC) samplers leverage continuous dynamics to define a transition kernel that efficiently explores a target distribution. In tandem, a focus has been on devising scalable variants that subsample the data and use stochastic gradients in place of full-data gradients in the dynamic simulations. However, such stochastic gradient MCMC samplers have lagged behind their full-data counterparts in terms of the complexity of dynamics considered since proving convergence in the presence of the stochastic gradient noise is non-trivial. Even with simple dynamics, sign"},"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":"1506.04696","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2015-06-15T18:32:37Z","cross_cats_sorted":["stat.ME","stat.ML","stat.TH"],"title_canon_sha256":"b41ba5b056abbe5843f5c2e8dbdf48a864a3dfab7d289bd6e2b70f5513d6b558","abstract_canon_sha256":"1c461c89a3e449d32b02aa2447b893c10b50c20d717e585cbda588b01983f664"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:28:14.068914Z","signature_b64":"gh2vT4huichcA61+kjWZnMnVPz9uwR8/3ymKvQChv+uNYGuKcrmn741pnn1hxSVryL2qsq54zBRoD5IqKvkQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ff06eda9bc62ac38c5cd85c600562865a0593a11bf9e6a7fb450f6192b942dd","last_reissued_at":"2026-05-18T01:28:14.068285Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:28:14.068285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Complete Recipe for Stochastic Gradient MCMC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Emily B. Fox, Tianqi Chen, Yi-An Ma","submitted_at":"2015-06-15T18:32:37Z","abstract_excerpt":"Many recent Markov chain Monte Carlo (MCMC) samplers leverage continuous dynamics to define a transition kernel that efficiently explores a target distribution. In tandem, a focus has been on devising scalable variants that subsample the data and use stochastic gradients in place of full-data gradients in the dynamic simulations. However, such stochastic gradient MCMC samplers have lagged behind their full-data counterparts in terms of the complexity of dynamics considered since proving convergence in the presence of the stochastic gradient noise is non-trivial. Even with simple dynamics, sign"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.04696","kind":"arxiv","version":2},"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":"1506.04696","created_at":"2026-05-18T01:28:14.068386+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.04696v2","created_at":"2026-05-18T01:28:14.068386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.04696","created_at":"2026-05-18T01:28:14.068386+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7YG5WU3YYVM","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7YG5WU3YYVMHDC4","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7YG5WU3","created_at":"2026-05-18T12:29:29.992203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.23350","citing_title":"Irreversibility Enhances Quantum-Enhanced Markov-Chain Monte Carlo","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7YG5WU3YYVMHDC43BOGABLCQZ","json":"https://pith.science/pith/L7YG5WU3YYVMHDC43BOGABLCQZ.json","graph_json":"https://pith.science/api/pith-number/L7YG5WU3YYVMHDC43BOGABLCQZ/graph.json","events_json":"https://pith.science/api/pith-number/L7YG5WU3YYVMHDC43BOGABLCQZ/events.json","paper":"https://pith.science/paper/L7YG5WU3"},"agent_actions":{"view_html":"https://pith.science/pith/L7YG5WU3YYVMHDC43BOGABLCQZ","download_json":"https://pith.science/pith/L7YG5WU3YYVMHDC43BOGABLCQZ.json","view_paper":"https://pith.science/paper/L7YG5WU3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.04696&json=true","fetch_graph":"https://pith.science/api/pith-number/L7YG5WU3YYVMHDC43BOGABLCQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/L7YG5WU3YYVMHDC43BOGABLCQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7YG5WU3YYVMHDC43BOGABLCQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7YG5WU3YYVMHDC43BOGABLCQZ/action/storage_attestation","attest_author":"https://pith.science/pith/L7YG5WU3YYVMHDC43BOGABLCQZ/action/author_attestation","sign_citation":"https://pith.science/pith/L7YG5WU3YYVMHDC43BOGABLCQZ/action/citation_signature","submit_replication":"https://pith.science/pith/L7YG5WU3YYVMHDC43BOGABLCQZ/action/replication_record"}},"created_at":"2026-05-18T01:28:14.068386+00:00","updated_at":"2026-05-18T01:28:14.068386+00:00"}