{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TGNYGJIQPWITOFFOZX3GAMXSJM","short_pith_number":"pith:TGNYGJIQ","canonical_record":{"source":{"id":"2102.01691","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2021-02-02T18:59:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"01800179ce15aa5409e916cea36b300b8e57c7c83c53e482a6cc4f7813b10e4d","abstract_canon_sha256":"190d7cab2c494e0972aef6cb0190f731f88c7978998b4938b4cf305e4689454c"},"schema_version":"1.0"},"canonical_sha256":"999b8325107d913714aecdf66032f24b1590db16b1f0fcd99b7c9fc0fef7123b","source":{"kind":"arxiv","id":"2102.01691","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.01691","created_at":"2026-07-05T02:11:32Z"},{"alias_kind":"arxiv_version","alias_value":"2102.01691v1","created_at":"2026-07-05T02:11:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.01691","created_at":"2026-07-05T02:11:32Z"},{"alias_kind":"pith_short_12","alias_value":"TGNYGJIQPWIT","created_at":"2026-07-05T02:11:32Z"},{"alias_kind":"pith_short_16","alias_value":"TGNYGJIQPWITOFFO","created_at":"2026-07-05T02:11:32Z"},{"alias_kind":"pith_short_8","alias_value":"TGNYGJIQ","created_at":"2026-07-05T02:11:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TGNYGJIQPWITOFFOZX3GAMXSJM","target":"record","payload":{"canonical_record":{"source":{"id":"2102.01691","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2021-02-02T18:59:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"01800179ce15aa5409e916cea36b300b8e57c7c83c53e482a6cc4f7813b10e4d","abstract_canon_sha256":"190d7cab2c494e0972aef6cb0190f731f88c7978998b4938b4cf305e4689454c"},"schema_version":"1.0"},"canonical_sha256":"999b8325107d913714aecdf66032f24b1590db16b1f0fcd99b7c9fc0fef7123b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:11:32.694531Z","signature_b64":"FmEhMPWo9t+6q9Ns5wbRueyMQY0jTUtnekbcgwL6weJcgz7LWvNJybp40VdMAAh6+28lko1vTWtbJOL8K8xYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"999b8325107d913714aecdf66032f24b1590db16b1f0fcd99b7c9fc0fef7123b","last_reissued_at":"2026-07-05T02:11:32.694117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:11:32.694117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.01691","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":"2026-07-05T02:11:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Iu+jACQnXNhQ1n9ci8TcuRUMciO7K0j6yYKs7Pw5anh9JqTbF+MdXptcqHjj+trhH4oSPGigoIlSkihstnuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:46:22.371391Z"},"content_sha256":"5f3f0143349b385f430962692312ef69452689b34bb9837afab75bf8fbcefc18","schema_version":"1.0","event_id":"sha256:5f3f0143349b385f430962692312ef69452689b34bb9837afab75bf8fbcefc18"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TGNYGJIQPWITOFFOZX3GAMXSJM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exact Langevin Dynamics with Stochastic Gradients","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Adri\\`a Garriga-Alonso, Vincent Fortuin","submitted_at":"2021-02-02T18:59:31Z","abstract_excerpt":"Stochastic gradient Markov Chain Monte Carlo algorithms are popular samplers for approximate inference, but they are generally biased. We show that many recent versions of these methods (e.g. Chen et al. (2014)) cannot be corrected using Metropolis-Hastings rejection sampling, because their acceptance probability is always zero. We can fix this by employing a sampler with realizable backwards trajectories, such as Gradient-Guided Monte Carlo (Horowitz, 1991), which generalizes stochastic gradient Langevin dynamics (Welling and Teh, 2011) and Hamiltonian Monte Carlo. We show that this sampler c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.01691","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2102.01691/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:11:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5kYJo2oBb4o8Oyr37P1ndvCCwtiswCVD41eDINsMQdtcjtBhSY+CFKAF+Bd51Ra0doNMnStQH56A6tRJsqzCCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:46:22.371950Z"},"content_sha256":"200d328d42c0ad7322547890e972cbea8d6c673545ca14f73e8c03d1dd26d3e3","schema_version":"1.0","event_id":"sha256:200d328d42c0ad7322547890e972cbea8d6c673545ca14f73e8c03d1dd26d3e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TGNYGJIQPWITOFFOZX3GAMXSJM/bundle.json","state_url":"https://pith.science/pith/TGNYGJIQPWITOFFOZX3GAMXSJM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TGNYGJIQPWITOFFOZX3GAMXSJM/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":"2026-08-08T04:46:22Z","links":{"resolver":"https://pith.science/pith/TGNYGJIQPWITOFFOZX3GAMXSJM","bundle":"https://pith.science/pith/TGNYGJIQPWITOFFOZX3GAMXSJM/bundle.json","state":"https://pith.science/pith/TGNYGJIQPWITOFFOZX3GAMXSJM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TGNYGJIQPWITOFFOZX3GAMXSJM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TGNYGJIQPWITOFFOZX3GAMXSJM","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":"190d7cab2c494e0972aef6cb0190f731f88c7978998b4938b4cf305e4689454c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2021-02-02T18:59:31Z","title_canon_sha256":"01800179ce15aa5409e916cea36b300b8e57c7c83c53e482a6cc4f7813b10e4d"},"schema_version":"1.0","source":{"id":"2102.01691","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.01691","created_at":"2026-07-05T02:11:32Z"},{"alias_kind":"arxiv_version","alias_value":"2102.01691v1","created_at":"2026-07-05T02:11:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.01691","created_at":"2026-07-05T02:11:32Z"},{"alias_kind":"pith_short_12","alias_value":"TGNYGJIQPWIT","created_at":"2026-07-05T02:11:32Z"},{"alias_kind":"pith_short_16","alias_value":"TGNYGJIQPWITOFFO","created_at":"2026-07-05T02:11:32Z"},{"alias_kind":"pith_short_8","alias_value":"TGNYGJIQ","created_at":"2026-07-05T02:11:32Z"}],"graph_snapshots":[{"event_id":"sha256:200d328d42c0ad7322547890e972cbea8d6c673545ca14f73e8c03d1dd26d3e3","target":"graph","created_at":"2026-07-05T02:11:32Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2102.01691/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stochastic gradient Markov Chain Monte Carlo algorithms are popular samplers for approximate inference, but they are generally biased. We show that many recent versions of these methods (e.g. Chen et al. (2014)) cannot be corrected using Metropolis-Hastings rejection sampling, because their acceptance probability is always zero. We can fix this by employing a sampler with realizable backwards trajectories, such as Gradient-Guided Monte Carlo (Horowitz, 1991), which generalizes stochastic gradient Langevin dynamics (Welling and Teh, 2011) and Hamiltonian Monte Carlo. We show that this sampler c","authors_text":"Adri\\`a Garriga-Alonso, Vincent Fortuin","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2021-02-02T18:59:31Z","title":"Exact Langevin Dynamics with Stochastic Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.01691","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":"sha256:5f3f0143349b385f430962692312ef69452689b34bb9837afab75bf8fbcefc18","target":"record","created_at":"2026-07-05T02:11:32Z","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":"190d7cab2c494e0972aef6cb0190f731f88c7978998b4938b4cf305e4689454c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2021-02-02T18:59:31Z","title_canon_sha256":"01800179ce15aa5409e916cea36b300b8e57c7c83c53e482a6cc4f7813b10e4d"},"schema_version":"1.0","source":{"id":"2102.01691","kind":"arxiv","version":1}},"canonical_sha256":"999b8325107d913714aecdf66032f24b1590db16b1f0fcd99b7c9fc0fef7123b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"999b8325107d913714aecdf66032f24b1590db16b1f0fcd99b7c9fc0fef7123b","first_computed_at":"2026-07-05T02:11:32.694117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:11:32.694117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FmEhMPWo9t+6q9Ns5wbRueyMQY0jTUtnekbcgwL6weJcgz7LWvNJybp40VdMAAh6+28lko1vTWtbJOL8K8xYAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:11:32.694531Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.01691","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f3f0143349b385f430962692312ef69452689b34bb9837afab75bf8fbcefc18","sha256:200d328d42c0ad7322547890e972cbea8d6c673545ca14f73e8c03d1dd26d3e3"],"state_sha256":"50e254f10859f2f7f0337b09f39d7d1e375e78f4dee7581128390d4c4d64d635"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ygwDwuq7gL/C+VenbeMLyvvh8ilLXrxES9vt/mFVehAUKzmeGkTYYitrWfjIq4qAfvP3FOVBnGZTG27SOxX8CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:46:22.376845Z","bundle_sha256":"e1fef8d37f055a81a8bed73f2db7b773fb382846dd03cf2fd5bd845fc525f92b"}}