{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:K6OOJFEPBGPMI77IVMKP7BTCGP","short_pith_number":"pith:K6OOJFEP","canonical_record":{"source":{"id":"1712.01076","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-04T13:54:45Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"7f505c590c67b552ccabe95603acd8012ef8407cb7a62dd6c11d661f8b1e057b","abstract_canon_sha256":"2a4d0dbe35d3a9e155bef80131f577f3cd2de54e9daca019dbf853b9221f7461"},"schema_version":"1.0"},"canonical_sha256":"579ce4948f099ec47fe8ab14ff866233f27b06168fd56256fccb635eeae41cd2","source":{"kind":"arxiv","id":"1712.01076","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.01076","created_at":"2026-05-18T00:28:59Z"},{"alias_kind":"arxiv_version","alias_value":"1712.01076v1","created_at":"2026-05-18T00:28:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01076","created_at":"2026-05-18T00:28:59Z"},{"alias_kind":"pith_short_12","alias_value":"K6OOJFEPBGPM","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"K6OOJFEPBGPMI77I","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"K6OOJFEP","created_at":"2026-05-18T12:31:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:K6OOJFEPBGPMI77IVMKP7BTCGP","target":"record","payload":{"canonical_record":{"source":{"id":"1712.01076","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-04T13:54:45Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"7f505c590c67b552ccabe95603acd8012ef8407cb7a62dd6c11d661f8b1e057b","abstract_canon_sha256":"2a4d0dbe35d3a9e155bef80131f577f3cd2de54e9daca019dbf853b9221f7461"},"schema_version":"1.0"},"canonical_sha256":"579ce4948f099ec47fe8ab14ff866233f27b06168fd56256fccb635eeae41cd2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:59.596243Z","signature_b64":"giZmi9PLGjMmAI3ikp+10Aay1UkKreXTtG1t1f0uU4tB56IsdEZPWwpccpTuB8D1Kha40cwpLx5c6PlD8JXMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"579ce4948f099ec47fe8ab14ff866233f27b06168fd56256fccb635eeae41cd2","last_reissued_at":"2026-05-18T00:28:59.595864Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:59.595864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.01076","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":"2026-05-18T00:28:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nArch+/J2exIQeRu6gt9xc11+XnuAqq0pwrrmUuSBtupxkQLXFgNe3TwQ+1ECgqBvf4LRQitkLEhTFfawfvvCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T08:20:02.044025Z"},"content_sha256":"171686b922ef881d601f40dbe732422525f8b1251cdbfbefe9b7b793b3d6e9b5","schema_version":"1.0","event_id":"sha256:171686b922ef881d601f40dbe732422525f8b1251cdbfbefe9b7b793b3d6e9b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:K6OOJFEPBGPMI77IVMKP7BTCGP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Natural Langevin Dynamics for Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"stat.ML","authors_text":"Ga\\'etan Marceau-Caron, Yann Ollivier","submitted_at":"2017-12-04T13:54:45Z","abstract_excerpt":"One way to avoid overfitting in machine learning is to use model parameters distributed according to a Bayesian posterior given the data, rather than the maximum likelihood estimator. Stochastic gradient Langevin dynamics (SGLD) is one algorithm to approximate such Bayesian posteriors for large models and datasets. SGLD is a standard stochastic gradient descent to which is added a controlled amount of noise, specifically scaled so that the parameter converges in law to the posterior distribution [WT11, TTV16]. The posterior predictive distribution can be approximated by an ensemble of samples "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01076","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":"2026-05-18T00:28:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dZzaYQX1mActF5Ad2+uMHEP1NBi8oD+XLZmjM1GZt2Jcsqs9UqXeXmUPc1XQMztboWxGiIwwR4+npwaY0ijLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T08:20:02.044787Z"},"content_sha256":"a756964fe6ada5e8e7da66a209bdddcb4b3b4e457bad87ac4a045b748ad2105a","schema_version":"1.0","event_id":"sha256:a756964fe6ada5e8e7da66a209bdddcb4b3b4e457bad87ac4a045b748ad2105a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K6OOJFEPBGPMI77IVMKP7BTCGP/bundle.json","state_url":"https://pith.science/pith/K6OOJFEPBGPMI77IVMKP7BTCGP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K6OOJFEPBGPMI77IVMKP7BTCGP/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":"2026-06-06T08:20:02Z","links":{"resolver":"https://pith.science/pith/K6OOJFEPBGPMI77IVMKP7BTCGP","bundle":"https://pith.science/pith/K6OOJFEPBGPMI77IVMKP7BTCGP/bundle.json","state":"https://pith.science/pith/K6OOJFEPBGPMI77IVMKP7BTCGP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K6OOJFEPBGPMI77IVMKP7BTCGP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:K6OOJFEPBGPMI77IVMKP7BTCGP","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":"2a4d0dbe35d3a9e155bef80131f577f3cd2de54e9daca019dbf853b9221f7461","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-04T13:54:45Z","title_canon_sha256":"7f505c590c67b552ccabe95603acd8012ef8407cb7a62dd6c11d661f8b1e057b"},"schema_version":"1.0","source":{"id":"1712.01076","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.01076","created_at":"2026-05-18T00:28:59Z"},{"alias_kind":"arxiv_version","alias_value":"1712.01076v1","created_at":"2026-05-18T00:28:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01076","created_at":"2026-05-18T00:28:59Z"},{"alias_kind":"pith_short_12","alias_value":"K6OOJFEPBGPM","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"K6OOJFEPBGPMI77I","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"K6OOJFEP","created_at":"2026-05-18T12:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:a756964fe6ada5e8e7da66a209bdddcb4b3b4e457bad87ac4a045b748ad2105a","target":"graph","created_at":"2026-05-18T00:28:59Z","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":"One way to avoid overfitting in machine learning is to use model parameters distributed according to a Bayesian posterior given the data, rather than the maximum likelihood estimator. Stochastic gradient Langevin dynamics (SGLD) is one algorithm to approximate such Bayesian posteriors for large models and datasets. SGLD is a standard stochastic gradient descent to which is added a controlled amount of noise, specifically scaled so that the parameter converges in law to the posterior distribution [WT11, TTV16]. The posterior predictive distribution can be approximated by an ensemble of samples ","authors_text":"Ga\\'etan Marceau-Caron, Yann Ollivier","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-04T13:54:45Z","title":"Natural Langevin Dynamics for Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01076","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":"sha256:171686b922ef881d601f40dbe732422525f8b1251cdbfbefe9b7b793b3d6e9b5","target":"record","created_at":"2026-05-18T00:28:59Z","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":"2a4d0dbe35d3a9e155bef80131f577f3cd2de54e9daca019dbf853b9221f7461","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-04T13:54:45Z","title_canon_sha256":"7f505c590c67b552ccabe95603acd8012ef8407cb7a62dd6c11d661f8b1e057b"},"schema_version":"1.0","source":{"id":"1712.01076","kind":"arxiv","version":1}},"canonical_sha256":"579ce4948f099ec47fe8ab14ff866233f27b06168fd56256fccb635eeae41cd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"579ce4948f099ec47fe8ab14ff866233f27b06168fd56256fccb635eeae41cd2","first_computed_at":"2026-05-18T00:28:59.595864Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:59.595864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"giZmi9PLGjMmAI3ikp+10Aay1UkKreXTtG1t1f0uU4tB56IsdEZPWwpccpTuB8D1Kha40cwpLx5c6PlD8JXMCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:59.596243Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.01076","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:171686b922ef881d601f40dbe732422525f8b1251cdbfbefe9b7b793b3d6e9b5","sha256:a756964fe6ada5e8e7da66a209bdddcb4b3b4e457bad87ac4a045b748ad2105a"],"state_sha256":"2f54b4b745311784f6f58e408805e623cb13621b9dc3798487b4336dc721f26e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RI686W27Lop96r78aqWxRL7ZxJghMegiGRxcOveUdAZ904e85+F7ula/YlhQF+HT33tTCWKctueh9IrAYvzFAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T08:20:02.049202Z","bundle_sha256":"12cfa614b67559d26e16c4ee9510f4c728e2e783f110b8d46df5cb06617bcbe1"}}