{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5PQHKOXXJRQ3MVZS77RP75MGLD","short_pith_number":"pith:5PQHKOXX","canonical_record":{"source":{"id":"1908.11843","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-30T17:12:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d6f8e88041aecf1992d4e778427c15f0f0d1d1094f6c779a6051fd56affac20c","abstract_canon_sha256":"94279266e68cae5bd839234b5ee1cec8926d21789a045dfda685fe77a56c7cb1"},"schema_version":"1.0"},"canonical_sha256":"ebe0753af74c61b65732ffe2fff58658e7b3eba560cd7bc3278eba912f742077","source":{"kind":"arxiv","id":"1908.11843","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.11843","created_at":"2026-07-05T00:29:39Z"},{"alias_kind":"arxiv_version","alias_value":"1908.11843v2","created_at":"2026-07-05T00:29:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.11843","created_at":"2026-07-05T00:29:39Z"},{"alias_kind":"pith_short_12","alias_value":"5PQHKOXXJRQ3","created_at":"2026-07-05T00:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"5PQHKOXXJRQ3MVZS","created_at":"2026-07-05T00:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"5PQHKOXX","created_at":"2026-07-05T00:29:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5PQHKOXXJRQ3MVZS77RP75MGLD","target":"record","payload":{"canonical_record":{"source":{"id":"1908.11843","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-30T17:12:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d6f8e88041aecf1992d4e778427c15f0f0d1d1094f6c779a6051fd56affac20c","abstract_canon_sha256":"94279266e68cae5bd839234b5ee1cec8926d21789a045dfda685fe77a56c7cb1"},"schema_version":"1.0"},"canonical_sha256":"ebe0753af74c61b65732ffe2fff58658e7b3eba560cd7bc3278eba912f742077","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:29:39.817338Z","signature_b64":"9sDZd6zGKa24K0SlfI+/G0jBcZWljwZYaoyku7IMetdSUPZX3ONVSZCQq6KQpSJwxgVQyZ9GN8pZitgXpkYWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebe0753af74c61b65732ffe2fff58658e7b3eba560cd7bc3278eba912f742077","last_reissued_at":"2026-07-05T00:29:39.816907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:29:39.816907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.11843","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":"2026-07-05T00:29:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mJ8Y3Nc18Je5tr4Xu0C4th0E6FOP4xKEu0ZKXvfgSFY3dH+LUouBlH17xL3TNVDtpdrCtQ2GQNS4C8Nk55lDDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:23:54.472390Z"},"content_sha256":"4f07b02c6c5a2c98495ed328565fa6f3a40e35798db79d71b2c69e62af63f1d4","schema_version":"1.0","event_id":"sha256:4f07b02c6c5a2c98495ed328565fa6f3a40e35798db79d71b2c69e62af63f1d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5PQHKOXXJRQ3MVZS77RP75MGLD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Partitioned integrators for thermodynamic parameterization of neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Benedict Leimkuhler, Charles Matthews, Tiffany Vlaar","submitted_at":"2019-08-30T17:12:56Z","abstract_excerpt":"Traditionally, neural networks are parameterized using optimization procedures such as stochastic gradient descent, RMSProp and ADAM. These procedures tend to drive the parameters of the network toward a local minimum. In this article, we employ alternative \"sampling\" algorithms (referred to here as \"thermodynamic parameterization methods\") which rely on discretized stochastic differential equations for a defined target distribution on parameter space. We show that the thermodynamic perspective already improves neural network training. Moreover, by partitioning the parameters based on natural "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.11843","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/1908.11843/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":"2026-07-05T00:29:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T7QTuiPsQAxBFLAR41xn8E6uuZ9SPjKdMTBwuOQfkxq0i5WamqoOHA7B0JxOr18Ddd1q0pi+Ctt8flu4sgZPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:23:54.473405Z"},"content_sha256":"ed4ff8794c06fb3825f3fa42a2236e90472b3854a220f538045f6cc2937886da","schema_version":"1.0","event_id":"sha256:ed4ff8794c06fb3825f3fa42a2236e90472b3854a220f538045f6cc2937886da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5PQHKOXXJRQ3MVZS77RP75MGLD/bundle.json","state_url":"https://pith.science/pith/5PQHKOXXJRQ3MVZS77RP75MGLD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5PQHKOXXJRQ3MVZS77RP75MGLD/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":"2026-08-16T22:23:54Z","links":{"resolver":"https://pith.science/pith/5PQHKOXXJRQ3MVZS77RP75MGLD","bundle":"https://pith.science/pith/5PQHKOXXJRQ3MVZS77RP75MGLD/bundle.json","state":"https://pith.science/pith/5PQHKOXXJRQ3MVZS77RP75MGLD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5PQHKOXXJRQ3MVZS77RP75MGLD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5PQHKOXXJRQ3MVZS77RP75MGLD","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":"94279266e68cae5bd839234b5ee1cec8926d21789a045dfda685fe77a56c7cb1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-30T17:12:56Z","title_canon_sha256":"d6f8e88041aecf1992d4e778427c15f0f0d1d1094f6c779a6051fd56affac20c"},"schema_version":"1.0","source":{"id":"1908.11843","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.11843","created_at":"2026-07-05T00:29:39Z"},{"alias_kind":"arxiv_version","alias_value":"1908.11843v2","created_at":"2026-07-05T00:29:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.11843","created_at":"2026-07-05T00:29:39Z"},{"alias_kind":"pith_short_12","alias_value":"5PQHKOXXJRQ3","created_at":"2026-07-05T00:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"5PQHKOXXJRQ3MVZS","created_at":"2026-07-05T00:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"5PQHKOXX","created_at":"2026-07-05T00:29:39Z"}],"graph_snapshots":[{"event_id":"sha256:ed4ff8794c06fb3825f3fa42a2236e90472b3854a220f538045f6cc2937886da","target":"graph","created_at":"2026-07-05T00:29:39Z","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/1908.11843/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditionally, neural networks are parameterized using optimization procedures such as stochastic gradient descent, RMSProp and ADAM. These procedures tend to drive the parameters of the network toward a local minimum. In this article, we employ alternative \"sampling\" algorithms (referred to here as \"thermodynamic parameterization methods\") which rely on discretized stochastic differential equations for a defined target distribution on parameter space. We show that the thermodynamic perspective already improves neural network training. Moreover, by partitioning the parameters based on natural ","authors_text":"Benedict Leimkuhler, Charles Matthews, Tiffany Vlaar","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-30T17:12:56Z","title":"Partitioned integrators for thermodynamic parameterization of neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.11843","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":"sha256:4f07b02c6c5a2c98495ed328565fa6f3a40e35798db79d71b2c69e62af63f1d4","target":"record","created_at":"2026-07-05T00:29:39Z","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":"94279266e68cae5bd839234b5ee1cec8926d21789a045dfda685fe77a56c7cb1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-30T17:12:56Z","title_canon_sha256":"d6f8e88041aecf1992d4e778427c15f0f0d1d1094f6c779a6051fd56affac20c"},"schema_version":"1.0","source":{"id":"1908.11843","kind":"arxiv","version":2}},"canonical_sha256":"ebe0753af74c61b65732ffe2fff58658e7b3eba560cd7bc3278eba912f742077","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebe0753af74c61b65732ffe2fff58658e7b3eba560cd7bc3278eba912f742077","first_computed_at":"2026-07-05T00:29:39.816907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:29:39.816907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9sDZd6zGKa24K0SlfI+/G0jBcZWljwZYaoyku7IMetdSUPZX3ONVSZCQq6KQpSJwxgVQyZ9GN8pZitgXpkYWAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:29:39.817338Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.11843","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f07b02c6c5a2c98495ed328565fa6f3a40e35798db79d71b2c69e62af63f1d4","sha256:ed4ff8794c06fb3825f3fa42a2236e90472b3854a220f538045f6cc2937886da"],"state_sha256":"d343213563abbe615ba1bf22cb60a8d5baaafe5dd47d7f8bbe924429a5a9b1cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c8baJ7fOzPhjqHGEIKRBZGqsCQWDjYjaH7q5Q3TFTOf+oAzKtiu0EZxeSnLY07xbCuRy77hYOOaBtNuvMNdhCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T22:23:54.481103Z","bundle_sha256":"db1504741aa549e3e9e94f01e65fa4faa76d5d36e52b17272744a50a47e1bf15"}}