{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5TMGYSGQU7GVMKHTO2PFMLFQ43","short_pith_number":"pith:5TMGYSGQ","canonical_record":{"source":{"id":"2606.09762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T17:24:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1b61e43aab77b72aa4a49cb68216f17789df62483d194e9811a376c4f9eabe43","abstract_canon_sha256":"71bce03075ebae2f58a3d72090509e0820fc6e354144dff5a5becacf6d59bb48"},"schema_version":"1.0"},"canonical_sha256":"ecd86c48d0a7cd5628f3769e562cb0e6eeb93c5c653565865b49a9a612ebc451","source":{"kind":"arxiv","id":"2606.09762","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09762","created_at":"2026-06-09T02:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09762v1","created_at":"2026-06-09T02:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09762","created_at":"2026-06-09T02:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"5TMGYSGQU7GV","created_at":"2026-06-09T02:09:08Z"},{"alias_kind":"pith_short_16","alias_value":"5TMGYSGQU7GVMKHT","created_at":"2026-06-09T02:09:08Z"},{"alias_kind":"pith_short_8","alias_value":"5TMGYSGQ","created_at":"2026-06-09T02:09:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5TMGYSGQU7GVMKHTO2PFMLFQ43","target":"record","payload":{"canonical_record":{"source":{"id":"2606.09762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T17:24:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1b61e43aab77b72aa4a49cb68216f17789df62483d194e9811a376c4f9eabe43","abstract_canon_sha256":"71bce03075ebae2f58a3d72090509e0820fc6e354144dff5a5becacf6d59bb48"},"schema_version":"1.0"},"canonical_sha256":"ecd86c48d0a7cd5628f3769e562cb0e6eeb93c5c653565865b49a9a612ebc451","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:09:08.277397Z","signature_b64":"HB0qFIgKAyPh3hsrKCHp9vfP3F4hJas3AfVYUbDnzV9X3/ExOcBiLaNV+O4iJmZ98cPZJhb+dh66iOk02H4/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecd86c48d0a7cd5628f3769e562cb0e6eeb93c5c653565865b49a9a612ebc451","last_reissued_at":"2026-06-09T02:09:08.276514Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:09:08.276514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.09762","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":"2026-06-09T02:09:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vonp6hspdGg9gZhmlEPhfgTUlHC0xtQ3kPTB/Iq9qVw7PzRnzIxLl3OZZKT5PP2O/rg1tyMTdMyihLvupgPzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T09:28:33.415828Z"},"content_sha256":"1c8f059878ecf8900ee681d8dc98cd473e818e1a12eb6957a7275e5c91f6df2f","schema_version":"1.0","event_id":"sha256:1c8f059878ecf8900ee681d8dc98cd473e818e1a12eb6957a7275e5c91f6df2f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5TMGYSGQU7GVMKHTO2PFMLFQ43","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Preserving Plasticity in Continual Learning via Dynamical Isometry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andries Rosseau, Ann Now\\'e, Robert M\\\"uller","submitted_at":"2026-06-08T17:24:15Z","abstract_excerpt":"Continual training of deep neural networks under non-stationarity often leads to a progressive loss of plasticity, eventually limiting further learning. We relate plasticity to the empirical Neural Tangent Kernel, and identify dynamical isometry (the condition that layer-wise Jacobian singular values remain close to one) as a key mechanism for preserving plasticity in continual learning. We revisit a class of networks that are almost-everywhere isometric while remaining universal Lipschitz function approximators, demonstrating that near-dynamical isometry is compatible with expressive nonlinea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09762","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/2606.09762/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":"2026-06-09T02:09:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2OR7ZbNLxbkgxc6gW80ILMuy9ck1YdNcTmC2q6FsdLBe0PFATRG6w5u1jfaN2aT1h3nHvdBLQLw/DjjNXqT1BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T09:28:33.416223Z"},"content_sha256":"645c46be85faa33e83066a4ef0e80eb06b1025344f2cc6746f2a7925b34692a1","schema_version":"1.0","event_id":"sha256:645c46be85faa33e83066a4ef0e80eb06b1025344f2cc6746f2a7925b34692a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5TMGYSGQU7GVMKHTO2PFMLFQ43/bundle.json","state_url":"https://pith.science/pith/5TMGYSGQU7GVMKHTO2PFMLFQ43/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5TMGYSGQU7GVMKHTO2PFMLFQ43/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":"2026-07-03T09:28:33Z","links":{"resolver":"https://pith.science/pith/5TMGYSGQU7GVMKHTO2PFMLFQ43","bundle":"https://pith.science/pith/5TMGYSGQU7GVMKHTO2PFMLFQ43/bundle.json","state":"https://pith.science/pith/5TMGYSGQU7GVMKHTO2PFMLFQ43/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5TMGYSGQU7GVMKHTO2PFMLFQ43/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5TMGYSGQU7GVMKHTO2PFMLFQ43","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":"71bce03075ebae2f58a3d72090509e0820fc6e354144dff5a5becacf6d59bb48","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T17:24:15Z","title_canon_sha256":"1b61e43aab77b72aa4a49cb68216f17789df62483d194e9811a376c4f9eabe43"},"schema_version":"1.0","source":{"id":"2606.09762","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09762","created_at":"2026-06-09T02:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09762v1","created_at":"2026-06-09T02:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09762","created_at":"2026-06-09T02:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"5TMGYSGQU7GV","created_at":"2026-06-09T02:09:08Z"},{"alias_kind":"pith_short_16","alias_value":"5TMGYSGQU7GVMKHT","created_at":"2026-06-09T02:09:08Z"},{"alias_kind":"pith_short_8","alias_value":"5TMGYSGQ","created_at":"2026-06-09T02:09:08Z"}],"graph_snapshots":[{"event_id":"sha256:645c46be85faa33e83066a4ef0e80eb06b1025344f2cc6746f2a7925b34692a1","target":"graph","created_at":"2026-06-09T02:09:08Z","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/2606.09762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continual training of deep neural networks under non-stationarity often leads to a progressive loss of plasticity, eventually limiting further learning. We relate plasticity to the empirical Neural Tangent Kernel, and identify dynamical isometry (the condition that layer-wise Jacobian singular values remain close to one) as a key mechanism for preserving plasticity in continual learning. We revisit a class of networks that are almost-everywhere isometric while remaining universal Lipschitz function approximators, demonstrating that near-dynamical isometry is compatible with expressive nonlinea","authors_text":"Andries Rosseau, Ann Now\\'e, Robert M\\\"uller","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T17:24:15Z","title":"Preserving Plasticity in Continual Learning via Dynamical Isometry"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09762","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":"sha256:1c8f059878ecf8900ee681d8dc98cd473e818e1a12eb6957a7275e5c91f6df2f","target":"record","created_at":"2026-06-09T02:09:08Z","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":"71bce03075ebae2f58a3d72090509e0820fc6e354144dff5a5becacf6d59bb48","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T17:24:15Z","title_canon_sha256":"1b61e43aab77b72aa4a49cb68216f17789df62483d194e9811a376c4f9eabe43"},"schema_version":"1.0","source":{"id":"2606.09762","kind":"arxiv","version":1}},"canonical_sha256":"ecd86c48d0a7cd5628f3769e562cb0e6eeb93c5c653565865b49a9a612ebc451","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecd86c48d0a7cd5628f3769e562cb0e6eeb93c5c653565865b49a9a612ebc451","first_computed_at":"2026-06-09T02:09:08.276514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:09:08.276514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HB0qFIgKAyPh3hsrKCHp9vfP3F4hJas3AfVYUbDnzV9X3/ExOcBiLaNV+O4iJmZ98cPZJhb+dh66iOk02H4/Dg==","signature_status":"signed_v1","signed_at":"2026-06-09T02:09:08.277397Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09762","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c8f059878ecf8900ee681d8dc98cd473e818e1a12eb6957a7275e5c91f6df2f","sha256:645c46be85faa33e83066a4ef0e80eb06b1025344f2cc6746f2a7925b34692a1"],"state_sha256":"82ceff2c592c0da239502a1181f5246985930762c8801b631f0e2e9f32882a1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JlevpCxuE2zl7bIUaFTsHQz8X8dYuq8478FNdlJC02qIuYIEBuwJnIPg2MlQ40kSMh11+ZsDcIGzR7KWsvDYCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T09:28:33.418192Z","bundle_sha256":"08d13f02dd3f28694be64669d914d8e737f1bc7dc0c36d1539fb60fe61d794be"}}