{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4I55PYB3U53RAVPAVQJLR27MZP","short_pith_number":"pith:4I55PYB3","canonical_record":{"source":{"id":"1811.10072","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-11-25T18:58:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a508c14b5a2466ed9ac102cfd9bfe865a6d94756ec3b686dee1910b99d7e3542","abstract_canon_sha256":"5caf1c4e644e621145acb58bde7a4644ddac7727f5feba0d6e7aca135288149d"},"schema_version":"1.0"},"canonical_sha256":"e23bd7e03ba7771055e0ac12b8ebeccbc4b41d3dba59323892e1acc1289f9ba8","source":{"kind":"arxiv","id":"1811.10072","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10072","created_at":"2026-05-17T23:59:58Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10072v1","created_at":"2026-05-17T23:59:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10072","created_at":"2026-05-17T23:59:58Z"},{"alias_kind":"pith_short_12","alias_value":"4I55PYB3U53R","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4I55PYB3U53RAVPA","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4I55PYB3","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4I55PYB3U53RAVPAVQJLR27MZP","target":"record","payload":{"canonical_record":{"source":{"id":"1811.10072","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-11-25T18:58:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a508c14b5a2466ed9ac102cfd9bfe865a6d94756ec3b686dee1910b99d7e3542","abstract_canon_sha256":"5caf1c4e644e621145acb58bde7a4644ddac7727f5feba0d6e7aca135288149d"},"schema_version":"1.0"},"canonical_sha256":"e23bd7e03ba7771055e0ac12b8ebeccbc4b41d3dba59323892e1acc1289f9ba8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:58.746753Z","signature_b64":"50HWQjk+NTU9cbf464ONchOJr1zZqc9ylfBmKDBL3bTzSozK5Ve1RGyKevQ4ji1pQBUTUrrrENHCw3xLZGnVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e23bd7e03ba7771055e0ac12b8ebeccbc4b41d3dba59323892e1acc1289f9ba8","last_reissued_at":"2026-05-17T23:59:58.746188Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:58.746188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.10072","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OYnZAStBAhpUd1/zygxpOPJKUOJS6+GqJMO7uhg/eEE6HWWeW84I6GXW+ZAH1/LsBvLVp21kwryPLHGIr7TiAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T22:21:37.791805Z"},"content_sha256":"bf232aadddb56024c09f9d894de45f873ac8c3fc067574a7bfb5e0ca9307a0da","schema_version":"1.0","event_id":"sha256:bf232aadddb56024c09f9d894de45f873ac8c3fc067574a7bfb5e0ca9307a0da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4I55PYB3U53RAVPAVQJLR27MZP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The promises and pitfalls of Stochastic Gradient Langevin Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alain Durmus, Eric Moulines, Nicolas Brosse","submitted_at":"2018-11-25T18:58:39Z","abstract_excerpt":"Stochastic Gradient Langevin Dynamics (SGLD) has emerged as a key MCMC algorithm for Bayesian learning from large scale datasets. While SGLD with decreasing step sizes converges weakly to the posterior distribution, the algorithm is often used with a constant step size in practice and has demonstrated successes in machine learning tasks. The current practice is to set the step size inversely proportional to $N$ where $N$ is the number of training samples. As $N$ becomes large, we show that the SGLD algorithm has an invariant probability measure which significantly departs from the target poste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10072","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WbV+VACkQZAfUnsht7FROffP9v11zOsJVtdV0cDe/XOg9FapLL/K8gnaNZ2luOhvYqa0roDZ3n7MHr8MmLLzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T22:21:37.792155Z"},"content_sha256":"7629e333003b43d95d7783728956edaa96b6ab24762eb19850d9601d4b04bbe2","schema_version":"1.0","event_id":"sha256:7629e333003b43d95d7783728956edaa96b6ab24762eb19850d9601d4b04bbe2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4I55PYB3U53RAVPAVQJLR27MZP/bundle.json","state_url":"https://pith.science/pith/4I55PYB3U53RAVPAVQJLR27MZP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4I55PYB3U53RAVPAVQJLR27MZP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-24T22:21:37Z","links":{"resolver":"https://pith.science/pith/4I55PYB3U53RAVPAVQJLR27MZP","bundle":"https://pith.science/pith/4I55PYB3U53RAVPAVQJLR27MZP/bundle.json","state":"https://pith.science/pith/4I55PYB3U53RAVPAVQJLR27MZP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4I55PYB3U53RAVPAVQJLR27MZP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4I55PYB3U53RAVPAVQJLR27MZP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5caf1c4e644e621145acb58bde7a4644ddac7727f5feba0d6e7aca135288149d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-11-25T18:58:39Z","title_canon_sha256":"a508c14b5a2466ed9ac102cfd9bfe865a6d94756ec3b686dee1910b99d7e3542"},"schema_version":"1.0","source":{"id":"1811.10072","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10072","created_at":"2026-05-17T23:59:58Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10072v1","created_at":"2026-05-17T23:59:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10072","created_at":"2026-05-17T23:59:58Z"},{"alias_kind":"pith_short_12","alias_value":"4I55PYB3U53R","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4I55PYB3U53RAVPA","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4I55PYB3","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:7629e333003b43d95d7783728956edaa96b6ab24762eb19850d9601d4b04bbe2","target":"graph","created_at":"2026-05-17T23:59:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Stochastic Gradient Langevin Dynamics (SGLD) has emerged as a key MCMC algorithm for Bayesian learning from large scale datasets. While SGLD with decreasing step sizes converges weakly to the posterior distribution, the algorithm is often used with a constant step size in practice and has demonstrated successes in machine learning tasks. The current practice is to set the step size inversely proportional to $N$ where $N$ is the number of training samples. As $N$ becomes large, we show that the SGLD algorithm has an invariant probability measure which significantly departs from the target poste","authors_text":"Alain Durmus, Eric Moulines, Nicolas Brosse","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-11-25T18:58:39Z","title":"The promises and pitfalls of Stochastic Gradient Langevin Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10072","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bf232aadddb56024c09f9d894de45f873ac8c3fc067574a7bfb5e0ca9307a0da","target":"record","created_at":"2026-05-17T23:59:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5caf1c4e644e621145acb58bde7a4644ddac7727f5feba0d6e7aca135288149d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-11-25T18:58:39Z","title_canon_sha256":"a508c14b5a2466ed9ac102cfd9bfe865a6d94756ec3b686dee1910b99d7e3542"},"schema_version":"1.0","source":{"id":"1811.10072","kind":"arxiv","version":1}},"canonical_sha256":"e23bd7e03ba7771055e0ac12b8ebeccbc4b41d3dba59323892e1acc1289f9ba8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e23bd7e03ba7771055e0ac12b8ebeccbc4b41d3dba59323892e1acc1289f9ba8","first_computed_at":"2026-05-17T23:59:58.746188Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:58.746188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"50HWQjk+NTU9cbf464ONchOJr1zZqc9ylfBmKDBL3bTzSozK5Ve1RGyKevQ4ji1pQBUTUrrrENHCw3xLZGnVCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:58.746753Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.10072","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf232aadddb56024c09f9d894de45f873ac8c3fc067574a7bfb5e0ca9307a0da","sha256:7629e333003b43d95d7783728956edaa96b6ab24762eb19850d9601d4b04bbe2"],"state_sha256":"6ee60a21ecff8297ceb24135b483840ec18110418d98db3a4ab178627eacfeb7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1XAdZ2HDOsRC3ps2JrtPLC9vK/hMXP2teVrAHEEW9/h9X1hMR1EXl97HFQglPcWy6ulQJENuUVmoCXbBwul0BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T22:21:37.794157Z","bundle_sha256":"2761ba8302eb1b45f7430b2fd78c2c01e9d73b44390ed2065c7b372c36d5ab0e"}}