{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:W5IV2VKZIMBPLWRHEVADBTX7TI","short_pith_number":"pith:W5IV2VKZ","canonical_record":{"source":{"id":"2212.12018","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.CP","submitted_at":"2022-12-22T20:00:11Z","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"title_canon_sha256":"1dced7a6ae6276af69f323349f2987e77435ef58bc8c2ce2b151f79f1f235091","abstract_canon_sha256":"c5a4e78b63380ec55ca672cb73e4771a9d8ef037602949b6b6a58d1126903b4e"},"schema_version":"1.0"},"canonical_sha256":"b7515d55594302f5da27254030ceff9a13bb22b5339fc991f5a54d6dddce74bb","source":{"kind":"arxiv","id":"2212.12018","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.12018","created_at":"2026-07-05T05:32:49Z"},{"alias_kind":"arxiv_version","alias_value":"2212.12018v2","created_at":"2026-07-05T05:32:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.12018","created_at":"2026-07-05T05:32:49Z"},{"alias_kind":"pith_short_12","alias_value":"W5IV2VKZIMBP","created_at":"2026-07-05T05:32:49Z"},{"alias_kind":"pith_short_16","alias_value":"W5IV2VKZIMBPLWRH","created_at":"2026-07-05T05:32:49Z"},{"alias_kind":"pith_short_8","alias_value":"W5IV2VKZ","created_at":"2026-07-05T05:32:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:W5IV2VKZIMBPLWRHEVADBTX7TI","target":"record","payload":{"canonical_record":{"source":{"id":"2212.12018","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.CP","submitted_at":"2022-12-22T20:00:11Z","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"title_canon_sha256":"1dced7a6ae6276af69f323349f2987e77435ef58bc8c2ce2b151f79f1f235091","abstract_canon_sha256":"c5a4e78b63380ec55ca672cb73e4771a9d8ef037602949b6b6a58d1126903b4e"},"schema_version":"1.0"},"canonical_sha256":"b7515d55594302f5da27254030ceff9a13bb22b5339fc991f5a54d6dddce74bb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:49.873454Z","signature_b64":"oh4cTtOTs/EomY5g6IpkVe1tf6/Pk3uyimaC6dW5D7oUtOWVTOH5thiz4v7SCZPitX7qFGt30sOOwXz7MKJqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7515d55594302f5da27254030ceff9a13bb22b5339fc991f5a54d6dddce74bb","last_reissued_at":"2026-07-05T05:32:49.872972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:49.872972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.12018","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:32:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SCC3gLWazi4y1xQEEg4PGZTullBHhMppFn8DUg74EDwgnVLkXkOgMf+CwNM3xuLB9arpxkTgrWwvdJ9Hfyx3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T11:04:52.716933Z"},"content_sha256":"367d6c854602e7d7143573d929b4347d1b78140142b95417eb590084ca134a50","schema_version":"1.0","event_id":"sha256:367d6c854602e7d7143573d929b4347d1b78140142b95417eb590084ca134a50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:W5IV2VKZIMBPLWRHEVADBTX7TI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Langevin algorithms for Markovian Neural Networks and Deep Stochastic control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.ML"],"primary_cat":"q-fin.CP","authors_text":"Gilles Pag\\`es, Pierre Bras","submitted_at":"2022-12-22T20:00:11Z","abstract_excerpt":"Stochastic Gradient Descent Langevin Dynamics (SGLD) algorithms, which add noise to the classic gradient descent, are known to improve the training of neural networks in some cases where the neural network is very deep. In this paper we study the possibilities of training acceleration for the numerical resolution of stochastic control problems through gradient descent, where the control is parametrized by a neural network. If the control is applied at many discretization times then solving the stochastic control problem reduces to minimizing the loss of a very deep neural network. We numerical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.12018","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2212.12018/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":"2026-07-05T05:32:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IAh+VwswMc+PORr+52aQnjJjRi5CAXUQAmVOcOUJMG0DB9NM4eKb+AhGHlx4tXC/beGMQMHwNq0XE5hU37IQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T11:04:52.717508Z"},"content_sha256":"924ca90fd26fbf2d8c7dc7fccee583e1fe4476172d7aef08ce9871829cde3c4b","schema_version":"1.0","event_id":"sha256:924ca90fd26fbf2d8c7dc7fccee583e1fe4476172d7aef08ce9871829cde3c4b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W5IV2VKZIMBPLWRHEVADBTX7TI/bundle.json","state_url":"https://pith.science/pith/W5IV2VKZIMBPLWRHEVADBTX7TI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W5IV2VKZIMBPLWRHEVADBTX7TI/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":"2026-08-11T11:04:52Z","links":{"resolver":"https://pith.science/pith/W5IV2VKZIMBPLWRHEVADBTX7TI","bundle":"https://pith.science/pith/W5IV2VKZIMBPLWRHEVADBTX7TI/bundle.json","state":"https://pith.science/pith/W5IV2VKZIMBPLWRHEVADBTX7TI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W5IV2VKZIMBPLWRHEVADBTX7TI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:W5IV2VKZIMBPLWRHEVADBTX7TI","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":"c5a4e78b63380ec55ca672cb73e4771a9d8ef037602949b6b6a58d1126903b4e","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.CP","submitted_at":"2022-12-22T20:00:11Z","title_canon_sha256":"1dced7a6ae6276af69f323349f2987e77435ef58bc8c2ce2b151f79f1f235091"},"schema_version":"1.0","source":{"id":"2212.12018","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.12018","created_at":"2026-07-05T05:32:49Z"},{"alias_kind":"arxiv_version","alias_value":"2212.12018v2","created_at":"2026-07-05T05:32:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.12018","created_at":"2026-07-05T05:32:49Z"},{"alias_kind":"pith_short_12","alias_value":"W5IV2VKZIMBP","created_at":"2026-07-05T05:32:49Z"},{"alias_kind":"pith_short_16","alias_value":"W5IV2VKZIMBPLWRH","created_at":"2026-07-05T05:32:49Z"},{"alias_kind":"pith_short_8","alias_value":"W5IV2VKZ","created_at":"2026-07-05T05:32:49Z"}],"graph_snapshots":[{"event_id":"sha256:924ca90fd26fbf2d8c7dc7fccee583e1fe4476172d7aef08ce9871829cde3c4b","target":"graph","created_at":"2026-07-05T05:32:49Z","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/2212.12018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stochastic Gradient Descent Langevin Dynamics (SGLD) algorithms, which add noise to the classic gradient descent, are known to improve the training of neural networks in some cases where the neural network is very deep. In this paper we study the possibilities of training acceleration for the numerical resolution of stochastic control problems through gradient descent, where the control is parametrized by a neural network. If the control is applied at many discretization times then solving the stochastic control problem reduces to minimizing the loss of a very deep neural network. We numerical","authors_text":"Gilles Pag\\`es, Pierre Bras","cross_cats":["cs.LG","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.CP","submitted_at":"2022-12-22T20:00:11Z","title":"Langevin algorithms for Markovian Neural Networks and Deep Stochastic control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.12018","kind":"arxiv","version":2},"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":"sha256:367d6c854602e7d7143573d929b4347d1b78140142b95417eb590084ca134a50","target":"record","created_at":"2026-07-05T05:32:49Z","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":"c5a4e78b63380ec55ca672cb73e4771a9d8ef037602949b6b6a58d1126903b4e","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.CP","submitted_at":"2022-12-22T20:00:11Z","title_canon_sha256":"1dced7a6ae6276af69f323349f2987e77435ef58bc8c2ce2b151f79f1f235091"},"schema_version":"1.0","source":{"id":"2212.12018","kind":"arxiv","version":2}},"canonical_sha256":"b7515d55594302f5da27254030ceff9a13bb22b5339fc991f5a54d6dddce74bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7515d55594302f5da27254030ceff9a13bb22b5339fc991f5a54d6dddce74bb","first_computed_at":"2026-07-05T05:32:49.872972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:32:49.872972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oh4cTtOTs/EomY5g6IpkVe1tf6/Pk3uyimaC6dW5D7oUtOWVTOH5thiz4v7SCZPitX7qFGt30sOOwXz7MKJqBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:32:49.873454Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.12018","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:367d6c854602e7d7143573d929b4347d1b78140142b95417eb590084ca134a50","sha256:924ca90fd26fbf2d8c7dc7fccee583e1fe4476172d7aef08ce9871829cde3c4b"],"state_sha256":"014390ee941544fdb146ae5cdd57ba2e75584b0f1052e6be1afc6d3fc476c265"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ug+ISvFeMt2dVc4QwHjz69y+XDh2cjK7rIKKvYpbdbJ0f+EpT4zloUf/eZ7n34X12lf0QUje+0ePrVE5uI4hCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T11:04:52.721870Z","bundle_sha256":"0f5e05477e8c8eb767ed99e50c41bee3e421611fb2e7f799b68bbb3ce55cbe13"}}