{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:D4ZGSPGJTJ4RKC4HK5UKRL5KXJ","short_pith_number":"pith:D4ZGSPGJ","canonical_record":{"source":{"id":"1512.07666","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-12-23T23:45:03Z","cross_cats_sorted":[],"title_canon_sha256":"8cab0048f123945966e104b1a870f6638a5ac45b239b980faa347c0184333f87","abstract_canon_sha256":"eae36f902d3bacbc52f102a1272737bc3d467312c0ba039985691e9b78c90cfc"},"schema_version":"1.0"},"canonical_sha256":"1f32693cc99a79150b875768a8afaaba593856f48759733ae2681af2ecedf424","source":{"kind":"arxiv","id":"1512.07666","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.07666","created_at":"2026-05-18T01:23:48Z"},{"alias_kind":"arxiv_version","alias_value":"1512.07666v1","created_at":"2026-05-18T01:23:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.07666","created_at":"2026-05-18T01:23:48Z"},{"alias_kind":"pith_short_12","alias_value":"D4ZGSPGJTJ4R","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"D4ZGSPGJTJ4RKC4H","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"D4ZGSPGJ","created_at":"2026-05-18T12:29:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:D4ZGSPGJTJ4RKC4HK5UKRL5KXJ","target":"record","payload":{"canonical_record":{"source":{"id":"1512.07666","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-12-23T23:45:03Z","cross_cats_sorted":[],"title_canon_sha256":"8cab0048f123945966e104b1a870f6638a5ac45b239b980faa347c0184333f87","abstract_canon_sha256":"eae36f902d3bacbc52f102a1272737bc3d467312c0ba039985691e9b78c90cfc"},"schema_version":"1.0"},"canonical_sha256":"1f32693cc99a79150b875768a8afaaba593856f48759733ae2681af2ecedf424","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:23:48.812727Z","signature_b64":"88IisQrxgBq2zrmvIf9xKhCXS/xlGHu4SUa+dpEIQ6ZSshSADHOsPmjKOWN8K7neQRAJUzHs7yBaS7JaKrn1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f32693cc99a79150b875768a8afaaba593856f48759733ae2681af2ecedf424","last_reissued_at":"2026-05-18T01:23:48.812037Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:23:48.812037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.07666","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":"2026-05-18T01:23:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"no1mK7o+7Qst0z3dNqWhEFn6hsZSswmgjcHmG6i3L5PoOt14lo59jb6JzTRbb82b7g6Mx9IAuSH2Sgaal8S7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T06:07:54.473451Z"},"content_sha256":"b377c5074107e7e667ab910781af2e61d6b1efe283433b1bc7b43fe08c4db10c","schema_version":"1.0","event_id":"sha256:b377c5074107e7e667ab910781af2e61d6b1efe283433b1bc7b43fe08c4db10c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:D4ZGSPGJTJ4RKC4HK5UKRL5KXJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Changyou Chen, Chunyuan Li, David Carlson, Lawrence Carin","submitted_at":"2015-12-23T23:45:03Z","abstract_excerpt":"Effective training of deep neural networks suffers from two main issues. The first is that the parameter spaces of these models exhibit pathological curvature. Recent methods address this problem by using adaptive preconditioning for Stochastic Gradient Descent (SGD). These methods improve convergence by adapting to the local geometry of parameter space. A second issue is overfitting, which is typically addressed by early stopping. However, recent work has demonstrated that Bayesian model averaging mitigates this problem. The posterior can be sampled by using Stochastic Gradient Langevin Dynam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.07666","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":"2026-05-18T01:23:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+0+TidH1MjitP87wcrHHyekk16Oudtc8ZUarkLw6K0kZMFD24vntG1A+DQEoV2UTeOmdfDBDt4AWv9OkIioPAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T06:07:54.473871Z"},"content_sha256":"869176e47a125ac30e079c1c49b794f7dfa02201cdeec0554d7300a447818c35","schema_version":"1.0","event_id":"sha256:869176e47a125ac30e079c1c49b794f7dfa02201cdeec0554d7300a447818c35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D4ZGSPGJTJ4RKC4HK5UKRL5KXJ/bundle.json","state_url":"https://pith.science/pith/D4ZGSPGJTJ4RKC4HK5UKRL5KXJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D4ZGSPGJTJ4RKC4HK5UKRL5KXJ/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":"2026-05-24T06:07:54Z","links":{"resolver":"https://pith.science/pith/D4ZGSPGJTJ4RKC4HK5UKRL5KXJ","bundle":"https://pith.science/pith/D4ZGSPGJTJ4RKC4HK5UKRL5KXJ/bundle.json","state":"https://pith.science/pith/D4ZGSPGJTJ4RKC4HK5UKRL5KXJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D4ZGSPGJTJ4RKC4HK5UKRL5KXJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:D4ZGSPGJTJ4RKC4HK5UKRL5KXJ","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":"eae36f902d3bacbc52f102a1272737bc3d467312c0ba039985691e9b78c90cfc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-12-23T23:45:03Z","title_canon_sha256":"8cab0048f123945966e104b1a870f6638a5ac45b239b980faa347c0184333f87"},"schema_version":"1.0","source":{"id":"1512.07666","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.07666","created_at":"2026-05-18T01:23:48Z"},{"alias_kind":"arxiv_version","alias_value":"1512.07666v1","created_at":"2026-05-18T01:23:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.07666","created_at":"2026-05-18T01:23:48Z"},{"alias_kind":"pith_short_12","alias_value":"D4ZGSPGJTJ4R","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"D4ZGSPGJTJ4RKC4H","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"D4ZGSPGJ","created_at":"2026-05-18T12:29:17Z"}],"graph_snapshots":[{"event_id":"sha256:869176e47a125ac30e079c1c49b794f7dfa02201cdeec0554d7300a447818c35","target":"graph","created_at":"2026-05-18T01:23:48Z","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":"Effective training of deep neural networks suffers from two main issues. The first is that the parameter spaces of these models exhibit pathological curvature. Recent methods address this problem by using adaptive preconditioning for Stochastic Gradient Descent (SGD). These methods improve convergence by adapting to the local geometry of parameter space. A second issue is overfitting, which is typically addressed by early stopping. However, recent work has demonstrated that Bayesian model averaging mitigates this problem. The posterior can be sampled by using Stochastic Gradient Langevin Dynam","authors_text":"Changyou Chen, Chunyuan Li, David Carlson, Lawrence Carin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-12-23T23:45:03Z","title":"Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.07666","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:b377c5074107e7e667ab910781af2e61d6b1efe283433b1bc7b43fe08c4db10c","target":"record","created_at":"2026-05-18T01:23:48Z","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":"eae36f902d3bacbc52f102a1272737bc3d467312c0ba039985691e9b78c90cfc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-12-23T23:45:03Z","title_canon_sha256":"8cab0048f123945966e104b1a870f6638a5ac45b239b980faa347c0184333f87"},"schema_version":"1.0","source":{"id":"1512.07666","kind":"arxiv","version":1}},"canonical_sha256":"1f32693cc99a79150b875768a8afaaba593856f48759733ae2681af2ecedf424","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f32693cc99a79150b875768a8afaaba593856f48759733ae2681af2ecedf424","first_computed_at":"2026-05-18T01:23:48.812037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:23:48.812037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"88IisQrxgBq2zrmvIf9xKhCXS/xlGHu4SUa+dpEIQ6ZSshSADHOsPmjKOWN8K7neQRAJUzHs7yBaS7JaKrn1BA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:23:48.812727Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.07666","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b377c5074107e7e667ab910781af2e61d6b1efe283433b1bc7b43fe08c4db10c","sha256:869176e47a125ac30e079c1c49b794f7dfa02201cdeec0554d7300a447818c35"],"state_sha256":"bcb934f57f0a1a3723a9c6146d7cbeeb4bbeeaa7e3a59278003f5fb42b79850c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ApE9uVxlz/dtm4kbu5lYqjCa9Q4xcdtIMBtwYe4kjtf7CSKL5iEZo9DHm/KVMiaYLA72n8NPN6Q1zDOYVFI1AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T06:07:54.477044Z","bundle_sha256":"c1ddce37f639495e40db8a97dede09ec163d8bf71319200cb3b7c8d7200d7261"}}