{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:62OOEDM2HDEFD3XTG7D6H4LCV5","short_pith_number":"pith:62OOEDM2","canonical_record":{"source":{"id":"2505.03552","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T14:04:46Z","cross_cats_sorted":["math.DS","math.OC"],"title_canon_sha256":"8e1ede93b35cb3e943d7506a1354ce7eb96993fd37b676c973978cc05ad6e396","abstract_canon_sha256":"8260005cf9672b8b397adc991a9e5817449c7f6fc7ab86db6f33fb4df837d111"},"schema_version":"1.0"},"canonical_sha256":"f69ce20d9a38c851eef337c7e3f162af5f512f7b55c6164e857cdfb9ba0da9a2","source":{"kind":"arxiv","id":"2505.03552","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03552","created_at":"2026-07-05T11:49:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03552v2","created_at":"2026-07-05T11:49:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03552","created_at":"2026-07-05T11:49:09Z"},{"alias_kind":"pith_short_12","alias_value":"62OOEDM2HDEF","created_at":"2026-07-05T11:49:09Z"},{"alias_kind":"pith_short_16","alias_value":"62OOEDM2HDEFD3XT","created_at":"2026-07-05T11:49:09Z"},{"alias_kind":"pith_short_8","alias_value":"62OOEDM2","created_at":"2026-07-05T11:49:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:62OOEDM2HDEFD3XTG7D6H4LCV5","target":"record","payload":{"canonical_record":{"source":{"id":"2505.03552","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T14:04:46Z","cross_cats_sorted":["math.DS","math.OC"],"title_canon_sha256":"8e1ede93b35cb3e943d7506a1354ce7eb96993fd37b676c973978cc05ad6e396","abstract_canon_sha256":"8260005cf9672b8b397adc991a9e5817449c7f6fc7ab86db6f33fb4df837d111"},"schema_version":"1.0"},"canonical_sha256":"f69ce20d9a38c851eef337c7e3f162af5f512f7b55c6164e857cdfb9ba0da9a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:09.826124Z","signature_b64":"ooHI+RBl/l4bt7lJgYtbkGBJZj53ozmRA0aNoxTn4ByYXrkoOOPvxlFMBXfjEoRIAPi0HfZ20vBBVAaFaRTrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f69ce20d9a38c851eef337c7e3f162af5f512f7b55c6164e857cdfb9ba0da9a2","last_reissued_at":"2026-07-05T11:49:09.825701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:09.825701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.03552","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":"2026-07-05T11:49:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8K382xrfgIiDLdvpoPksP+xUAah2f4xV6VTog0nM4IFehk0pib+zR1MqyuACLTp+OrbxRPh+FhYb1aPFQxrVAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:14:54.880941Z"},"content_sha256":"6dd79da441adc0494c7bc7d56b196ef1da12ef7acf360c753e783cd58e61f236","schema_version":"1.0","event_id":"sha256:6dd79da441adc0494c7bc7d56b196ef1da12ef7acf360c753e783cd58e61f236"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:62OOEDM2HDEFD3XTG7D6H4LCV5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Training of Physics-enhanced Neural ODEs via Direct Collocation and Nonlinear Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.DS","math.OC"],"primary_cat":"cs.LG","authors_text":"Bernhard Bachmann, Linus Langenkamp, Philip Hannebohm","submitted_at":"2025-05-06T14:04:46Z","abstract_excerpt":"We propose a novel approach for training Physics-enhanced Neural ODEs (PeN-ODEs) by expressing the training process as a dynamic optimization problem. The full model, including neural components, is discretized using a high-order implicit Runge-Kutta method with flipped Legendre-Gauss-Radau points, resulting in a large-scale nonlinear program (NLP) efficiently solved by state-of-the-art NLP solvers such as Ipopt. This formulation enables simultaneous optimization of network parameters and state trajectories, addressing key limitations of ODE solver-based training in terms of stability, runtime"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03552","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/2505.03552/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":"2026-07-05T11:49:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"15KuUacN4mDVdc7Jzpr9SWrMrKGSsuISycZWi/kUrE8hGz5O996Tdix2o54iz1SDBWbIOM47hPwFeXW9Q54gBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:14:54.881507Z"},"content_sha256":"58266187e7d931dcee4ecb871626494ad4968709191ae9da9a6ec654d580cbde","schema_version":"1.0","event_id":"sha256:58266187e7d931dcee4ecb871626494ad4968709191ae9da9a6ec654d580cbde"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/62OOEDM2HDEFD3XTG7D6H4LCV5/bundle.json","state_url":"https://pith.science/pith/62OOEDM2HDEFD3XTG7D6H4LCV5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/62OOEDM2HDEFD3XTG7D6H4LCV5/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":"2026-08-22T09:14:54Z","links":{"resolver":"https://pith.science/pith/62OOEDM2HDEFD3XTG7D6H4LCV5","bundle":"https://pith.science/pith/62OOEDM2HDEFD3XTG7D6H4LCV5/bundle.json","state":"https://pith.science/pith/62OOEDM2HDEFD3XTG7D6H4LCV5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/62OOEDM2HDEFD3XTG7D6H4LCV5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:62OOEDM2HDEFD3XTG7D6H4LCV5","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":"8260005cf9672b8b397adc991a9e5817449c7f6fc7ab86db6f33fb4df837d111","cross_cats_sorted":["math.DS","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T14:04:46Z","title_canon_sha256":"8e1ede93b35cb3e943d7506a1354ce7eb96993fd37b676c973978cc05ad6e396"},"schema_version":"1.0","source":{"id":"2505.03552","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03552","created_at":"2026-07-05T11:49:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03552v2","created_at":"2026-07-05T11:49:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03552","created_at":"2026-07-05T11:49:09Z"},{"alias_kind":"pith_short_12","alias_value":"62OOEDM2HDEF","created_at":"2026-07-05T11:49:09Z"},{"alias_kind":"pith_short_16","alias_value":"62OOEDM2HDEFD3XT","created_at":"2026-07-05T11:49:09Z"},{"alias_kind":"pith_short_8","alias_value":"62OOEDM2","created_at":"2026-07-05T11:49:09Z"}],"graph_snapshots":[{"event_id":"sha256:58266187e7d931dcee4ecb871626494ad4968709191ae9da9a6ec654d580cbde","target":"graph","created_at":"2026-07-05T11:49:09Z","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/2505.03552/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel approach for training Physics-enhanced Neural ODEs (PeN-ODEs) by expressing the training process as a dynamic optimization problem. The full model, including neural components, is discretized using a high-order implicit Runge-Kutta method with flipped Legendre-Gauss-Radau points, resulting in a large-scale nonlinear program (NLP) efficiently solved by state-of-the-art NLP solvers such as Ipopt. This formulation enables simultaneous optimization of network parameters and state trajectories, addressing key limitations of ODE solver-based training in terms of stability, runtime","authors_text":"Bernhard Bachmann, Linus Langenkamp, Philip Hannebohm","cross_cats":["math.DS","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T14:04:46Z","title":"Efficient Training of Physics-enhanced Neural ODEs via Direct Collocation and Nonlinear Programming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03552","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":"sha256:6dd79da441adc0494c7bc7d56b196ef1da12ef7acf360c753e783cd58e61f236","target":"record","created_at":"2026-07-05T11:49:09Z","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":"8260005cf9672b8b397adc991a9e5817449c7f6fc7ab86db6f33fb4df837d111","cross_cats_sorted":["math.DS","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T14:04:46Z","title_canon_sha256":"8e1ede93b35cb3e943d7506a1354ce7eb96993fd37b676c973978cc05ad6e396"},"schema_version":"1.0","source":{"id":"2505.03552","kind":"arxiv","version":2}},"canonical_sha256":"f69ce20d9a38c851eef337c7e3f162af5f512f7b55c6164e857cdfb9ba0da9a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f69ce20d9a38c851eef337c7e3f162af5f512f7b55c6164e857cdfb9ba0da9a2","first_computed_at":"2026-07-05T11:49:09.825701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:09.825701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ooHI+RBl/l4bt7lJgYtbkGBJZj53ozmRA0aNoxTn4ByYXrkoOOPvxlFMBXfjEoRIAPi0HfZ20vBBVAaFaRTrBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:09.826124Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03552","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6dd79da441adc0494c7bc7d56b196ef1da12ef7acf360c753e783cd58e61f236","sha256:58266187e7d931dcee4ecb871626494ad4968709191ae9da9a6ec654d580cbde"],"state_sha256":"d21f306389bf967b14773b0c60b70bbd40e94c3a0ac7f587a9081819a1349315"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qh7eleu9viouNOuadAWqNtpScwu6V8NLeWCGrtLfflOf9Qk2lxsLVuwn6kpON45hvqjgW5+B1f1LbySEVukiCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T09:14:54.886158Z","bundle_sha256":"afa00e25478d1540cbdcd803c8f58875d56020098dfd6b36a4712a20a7d8f0a3"}}