{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QD35S7M4XPK67HXE3HXUL4DBZ6","short_pith_number":"pith:QD35S7M4","canonical_record":{"source":{"id":"2505.13397","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T17:34:32Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"60b628d91d31f5d7b259f70e5a7472d85b7be38dbfeb497ec5161dbc81a268b9","abstract_canon_sha256":"5b1c9ef9e573ab4403541c78d2e003135e630794cc8bf4056057dc31fe5ca967"},"schema_version":"1.0"},"canonical_sha256":"80f7d97d9cbbd5ef9ee4d9ef45f061cfaf82200cf9df35de2a47ed9ba9c9b31c","source":{"kind":"arxiv","id":"2505.13397","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13397","created_at":"2026-07-05T11:05:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13397v1","created_at":"2026-07-05T11:05:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13397","created_at":"2026-07-05T11:05:29Z"},{"alias_kind":"pith_short_12","alias_value":"QD35S7M4XPK6","created_at":"2026-07-05T11:05:29Z"},{"alias_kind":"pith_short_16","alias_value":"QD35S7M4XPK67HXE","created_at":"2026-07-05T11:05:29Z"},{"alias_kind":"pith_short_8","alias_value":"QD35S7M4","created_at":"2026-07-05T11:05:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QD35S7M4XPK67HXE3HXUL4DBZ6","target":"record","payload":{"canonical_record":{"source":{"id":"2505.13397","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T17:34:32Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"60b628d91d31f5d7b259f70e5a7472d85b7be38dbfeb497ec5161dbc81a268b9","abstract_canon_sha256":"5b1c9ef9e573ab4403541c78d2e003135e630794cc8bf4056057dc31fe5ca967"},"schema_version":"1.0"},"canonical_sha256":"80f7d97d9cbbd5ef9ee4d9ef45f061cfaf82200cf9df35de2a47ed9ba9c9b31c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:29.452543Z","signature_b64":"Sa5QaK7lHHxIGSJCLIEPGXlu+Nc37tSHLs9cyRhAa6vqKX3M+nJejayD8EIiHv/k3t4Z8+PhBlgSex47EyAmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80f7d97d9cbbd5ef9ee4d9ef45f061cfaf82200cf9df35de2a47ed9ba9c9b31c","last_reissued_at":"2026-07-05T11:05:29.452056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:29.452056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.13397","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":"2026-07-05T11:05:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jn/iSCm9qy4MadKg//KFzGeLYIWQWPkOsvDXiSYJEhaFyg+hEB4FMENSL8mHHqk+J8Iwzp9hYtR6FNUFP1sgAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:06:47.564621Z"},"content_sha256":"cd4db173caf8103d522a493336ed63547b3bf4c44ae00455007ece97118339e8","schema_version":"1.0","event_id":"sha256:cd4db173caf8103d522a493336ed63547b3bf4c44ae00455007ece97118339e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QD35S7M4XPK67HXE3HXUL4DBZ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning by solving differential equations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benoit Dherin, Hanna Mazzawi, Javier Gonzalvo, Michael Munn, Michael Wunder, Sourabh Medapati","submitted_at":"2025-05-19T17:34:32Z","abstract_excerpt":"Modern deep learning algorithms use variations of gradient descent as their main learning methods. Gradient descent can be understood as the simplest Ordinary Differential Equation (ODE) solver; namely, the Euler method applied to the gradient flow differential equation. Since Euler, many ODE solvers have been devised that follow the gradient flow equation more precisely and more stably. Runge-Kutta (RK) methods provide a family of very powerful explicit and implicit high-order ODE solvers. However, these higher-order solvers have not found wide application in deep learning so far. In this wor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13397","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/2505.13397/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":"2026-07-05T11:05:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nBPXXPor4L7/k/3hL3KME6cwwn2X4IIujPs59IIdlXl13pYPW0yAEylcI30DGe09nb5U8JJXAU+4mec9ZZ7zAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:06:47.565688Z"},"content_sha256":"a00c637b72f138363a0e9713a603a10e146be704f05967d99d06682bc75d975b","schema_version":"1.0","event_id":"sha256:a00c637b72f138363a0e9713a603a10e146be704f05967d99d06682bc75d975b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QD35S7M4XPK67HXE3HXUL4DBZ6/bundle.json","state_url":"https://pith.science/pith/QD35S7M4XPK67HXE3HXUL4DBZ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QD35S7M4XPK67HXE3HXUL4DBZ6/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":"2026-08-18T15:06:47Z","links":{"resolver":"https://pith.science/pith/QD35S7M4XPK67HXE3HXUL4DBZ6","bundle":"https://pith.science/pith/QD35S7M4XPK67HXE3HXUL4DBZ6/bundle.json","state":"https://pith.science/pith/QD35S7M4XPK67HXE3HXUL4DBZ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QD35S7M4XPK67HXE3HXUL4DBZ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QD35S7M4XPK67HXE3HXUL4DBZ6","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":"5b1c9ef9e573ab4403541c78d2e003135e630794cc8bf4056057dc31fe5ca967","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T17:34:32Z","title_canon_sha256":"60b628d91d31f5d7b259f70e5a7472d85b7be38dbfeb497ec5161dbc81a268b9"},"schema_version":"1.0","source":{"id":"2505.13397","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13397","created_at":"2026-07-05T11:05:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13397v1","created_at":"2026-07-05T11:05:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13397","created_at":"2026-07-05T11:05:29Z"},{"alias_kind":"pith_short_12","alias_value":"QD35S7M4XPK6","created_at":"2026-07-05T11:05:29Z"},{"alias_kind":"pith_short_16","alias_value":"QD35S7M4XPK67HXE","created_at":"2026-07-05T11:05:29Z"},{"alias_kind":"pith_short_8","alias_value":"QD35S7M4","created_at":"2026-07-05T11:05:29Z"}],"graph_snapshots":[{"event_id":"sha256:a00c637b72f138363a0e9713a603a10e146be704f05967d99d06682bc75d975b","target":"graph","created_at":"2026-07-05T11:05:29Z","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/2505.13397/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern deep learning algorithms use variations of gradient descent as their main learning methods. Gradient descent can be understood as the simplest Ordinary Differential Equation (ODE) solver; namely, the Euler method applied to the gradient flow differential equation. Since Euler, many ODE solvers have been devised that follow the gradient flow equation more precisely and more stably. Runge-Kutta (RK) methods provide a family of very powerful explicit and implicit high-order ODE solvers. However, these higher-order solvers have not found wide application in deep learning so far. In this wor","authors_text":"Benoit Dherin, Hanna Mazzawi, Javier Gonzalvo, Michael Munn, Michael Wunder, Sourabh Medapati","cross_cats":["cs.NA","math.NA","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T17:34:32Z","title":"Learning by solving differential equations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13397","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:cd4db173caf8103d522a493336ed63547b3bf4c44ae00455007ece97118339e8","target":"record","created_at":"2026-07-05T11:05:29Z","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":"5b1c9ef9e573ab4403541c78d2e003135e630794cc8bf4056057dc31fe5ca967","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T17:34:32Z","title_canon_sha256":"60b628d91d31f5d7b259f70e5a7472d85b7be38dbfeb497ec5161dbc81a268b9"},"schema_version":"1.0","source":{"id":"2505.13397","kind":"arxiv","version":1}},"canonical_sha256":"80f7d97d9cbbd5ef9ee4d9ef45f061cfaf82200cf9df35de2a47ed9ba9c9b31c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80f7d97d9cbbd5ef9ee4d9ef45f061cfaf82200cf9df35de2a47ed9ba9c9b31c","first_computed_at":"2026-07-05T11:05:29.452056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:29.452056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sa5QaK7lHHxIGSJCLIEPGXlu+Nc37tSHLs9cyRhAa6vqKX3M+nJejayD8EIiHv/k3t4Z8+PhBlgSex47EyAmBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:29.452543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13397","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd4db173caf8103d522a493336ed63547b3bf4c44ae00455007ece97118339e8","sha256:a00c637b72f138363a0e9713a603a10e146be704f05967d99d06682bc75d975b"],"state_sha256":"5286cc1e6510f0543775a67680d29deef09a30a46e8e29a94c776024a783bd73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NTA7ZuOlLifpCJwSHDw2lMAOhVmTmrnbwRxIJ+w/VEIsK59BRrk5pd1nkQYPMWPv5GArcExonmpuvyMUZl3KCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T15:06:47.576704Z","bundle_sha256":"220687ae8a79c5a4dcf9a2fc637c2978dc037a67cf152f1c6d9a6d823a73797b"}}