{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QC4F64PYMFMFO7QHVT5ISXMBTI","short_pith_number":"pith:QC4F64PY","canonical_record":{"source":{"id":"2305.06648","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-05-11T08:29:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"48249d58d2cf9c7272ac526b0866b151cdb1fac5a0f73c5697e4852220fad2e5","abstract_canon_sha256":"3e35fe18b9a37a8107997d1ca7492fd3c6670c58fb59104a3888c6724370c987"},"schema_version":"1.0"},"canonical_sha256":"80b85f71f86158577e07acfa895d819a0d52e69940538c5ecee2de85addb3a3c","source":{"kind":"arxiv","id":"2305.06648","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.06648","created_at":"2026-07-05T06:59:52Z"},{"alias_kind":"arxiv_version","alias_value":"2305.06648v2","created_at":"2026-07-05T06:59:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06648","created_at":"2026-07-05T06:59:52Z"},{"alias_kind":"pith_short_12","alias_value":"QC4F64PYMFMF","created_at":"2026-07-05T06:59:52Z"},{"alias_kind":"pith_short_16","alias_value":"QC4F64PYMFMFO7QH","created_at":"2026-07-05T06:59:52Z"},{"alias_kind":"pith_short_8","alias_value":"QC4F64PY","created_at":"2026-07-05T06:59:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QC4F64PYMFMFO7QHVT5ISXMBTI","target":"record","payload":{"canonical_record":{"source":{"id":"2305.06648","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-05-11T08:29:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"48249d58d2cf9c7272ac526b0866b151cdb1fac5a0f73c5697e4852220fad2e5","abstract_canon_sha256":"3e35fe18b9a37a8107997d1ca7492fd3c6670c58fb59104a3888c6724370c987"},"schema_version":"1.0"},"canonical_sha256":"80b85f71f86158577e07acfa895d819a0d52e69940538c5ecee2de85addb3a3c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:52.186689Z","signature_b64":"rNNClZx1ZZWi4F1TkJWUKqtkHXhh3Gzsj6QtOk5TWPC+4adIJWjVoYJ4pNGqp6kwk6572VLF6QXk7S4GR1pZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80b85f71f86158577e07acfa895d819a0d52e69940538c5ecee2de85addb3a3c","last_reissued_at":"2026-07-05T06:59:52.186347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:52.186347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.06648","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":"2026-07-05T06:59:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wt5dobIzuMcEgjwaGjrX+N5FItSxJor+UWrq9tE/Tg7o2q5j99K6SjBBRct9WJxf9AhfbxJTt5ymvVAQTgmtCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T05:01:20.295785Z"},"content_sha256":"73987e5a3fa06c26611d5793b961857dddc551941d32ab461390196c01689425","schema_version":"1.0","event_id":"sha256:73987e5a3fa06c26611d5793b961857dddc551941d32ab461390196c01689425"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QC4F64PYMFMFO7QHVT5ISXMBTI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalization bounds for neural ordinary differential equations and deep residual networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Pierre Marion","submitted_at":"2023-05-11T08:29:34Z","abstract_excerpt":"Neural ordinary differential equations (neural ODEs) are a popular family of continuous-depth deep learning models. In this work, we consider a large family of parameterized ODEs with continuous-in-time parameters, which include time-dependent neural ODEs. We derive a generalization bound for this class by a Lipschitz-based argument. By leveraging the analogy between neural ODEs and deep residual networks, our approach yields in particular a generalization bound for a class of deep residual networks. The bound involves the magnitude of the difference between successive weight matrices. We illu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06648","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/2305.06648/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":"2026-07-05T06:59:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9oCJt31Sx3/MZ6ej4FonQfRcrk9D6TWRv0/outn8s0Za3b357jjFybwS9MCcln83B4JHk7qoDBDqc7cxKWn3CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T05:01:20.296188Z"},"content_sha256":"432ccbd843b2a14f9ce15bfa99d51b69bd9c686f6d86fb631a354e1e61e8123a","schema_version":"1.0","event_id":"sha256:432ccbd843b2a14f9ce15bfa99d51b69bd9c686f6d86fb631a354e1e61e8123a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QC4F64PYMFMFO7QHVT5ISXMBTI/bundle.json","state_url":"https://pith.science/pith/QC4F64PYMFMFO7QHVT5ISXMBTI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QC4F64PYMFMFO7QHVT5ISXMBTI/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":"2026-07-27T05:01:20Z","links":{"resolver":"https://pith.science/pith/QC4F64PYMFMFO7QHVT5ISXMBTI","bundle":"https://pith.science/pith/QC4F64PYMFMFO7QHVT5ISXMBTI/bundle.json","state":"https://pith.science/pith/QC4F64PYMFMFO7QHVT5ISXMBTI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QC4F64PYMFMFO7QHVT5ISXMBTI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QC4F64PYMFMFO7QHVT5ISXMBTI","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":"3e35fe18b9a37a8107997d1ca7492fd3c6670c58fb59104a3888c6724370c987","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-05-11T08:29:34Z","title_canon_sha256":"48249d58d2cf9c7272ac526b0866b151cdb1fac5a0f73c5697e4852220fad2e5"},"schema_version":"1.0","source":{"id":"2305.06648","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.06648","created_at":"2026-07-05T06:59:52Z"},{"alias_kind":"arxiv_version","alias_value":"2305.06648v2","created_at":"2026-07-05T06:59:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06648","created_at":"2026-07-05T06:59:52Z"},{"alias_kind":"pith_short_12","alias_value":"QC4F64PYMFMF","created_at":"2026-07-05T06:59:52Z"},{"alias_kind":"pith_short_16","alias_value":"QC4F64PYMFMFO7QH","created_at":"2026-07-05T06:59:52Z"},{"alias_kind":"pith_short_8","alias_value":"QC4F64PY","created_at":"2026-07-05T06:59:52Z"}],"graph_snapshots":[{"event_id":"sha256:432ccbd843b2a14f9ce15bfa99d51b69bd9c686f6d86fb631a354e1e61e8123a","target":"graph","created_at":"2026-07-05T06:59:52Z","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/2305.06648/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural ordinary differential equations (neural ODEs) are a popular family of continuous-depth deep learning models. In this work, we consider a large family of parameterized ODEs with continuous-in-time parameters, which include time-dependent neural ODEs. We derive a generalization bound for this class by a Lipschitz-based argument. By leveraging the analogy between neural ODEs and deep residual networks, our approach yields in particular a generalization bound for a class of deep residual networks. The bound involves the magnitude of the difference between successive weight matrices. We illu","authors_text":"Pierre Marion","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-05-11T08:29:34Z","title":"Generalization bounds for neural ordinary differential equations and deep residual networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06648","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":"sha256:73987e5a3fa06c26611d5793b961857dddc551941d32ab461390196c01689425","target":"record","created_at":"2026-07-05T06:59:52Z","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":"3e35fe18b9a37a8107997d1ca7492fd3c6670c58fb59104a3888c6724370c987","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-05-11T08:29:34Z","title_canon_sha256":"48249d58d2cf9c7272ac526b0866b151cdb1fac5a0f73c5697e4852220fad2e5"},"schema_version":"1.0","source":{"id":"2305.06648","kind":"arxiv","version":2}},"canonical_sha256":"80b85f71f86158577e07acfa895d819a0d52e69940538c5ecee2de85addb3a3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80b85f71f86158577e07acfa895d819a0d52e69940538c5ecee2de85addb3a3c","first_computed_at":"2026-07-05T06:59:52.186347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:52.186347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rNNClZx1ZZWi4F1TkJWUKqtkHXhh3Gzsj6QtOk5TWPC+4adIJWjVoYJ4pNGqp6kwk6572VLF6QXk7S4GR1pZCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:52.186689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.06648","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73987e5a3fa06c26611d5793b961857dddc551941d32ab461390196c01689425","sha256:432ccbd843b2a14f9ce15bfa99d51b69bd9c686f6d86fb631a354e1e61e8123a"],"state_sha256":"9d3bd1367466aa317e7bda13f9809551832ad98d6d9db68be6c3091effb21c31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AHKQKfalBkIWBXfoFe7JVl5Fa2HUI8xp4ZvHjEum+1esDyJFona+qOmcK2Ss1WWt6THX/UeRsSwCb3LtutEUCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T05:01:20.298649Z","bundle_sha256":"c5208363d7fe81ca47d599bbc63ca2868901472fb3084b6d470589444f43d54c"}}