{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZEJFOUIOJCIOCH7L4VOVVOIC46","short_pith_number":"pith:ZEJFOUIO","canonical_record":{"source":{"id":"2606.02078","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T11:07:35Z","cross_cats_sorted":[],"title_canon_sha256":"9161779578cf503de5c610a0c2b4cdf083b735e5bb9f2e2c7993a03f6c93b708","abstract_canon_sha256":"4394651da76a10b68ff619e9245633e78ec82f4b0cd8ec93d70cb29641146cb0"},"schema_version":"1.0"},"canonical_sha256":"c91257510e4890e11febe55d5ab902e7a384a456a923e7e6996848cf2ecf33f7","source":{"kind":"arxiv","id":"2606.02078","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02078","created_at":"2026-06-02T02:05:05Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02078v1","created_at":"2026-06-02T02:05:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02078","created_at":"2026-06-02T02:05:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZEJFOUIOJCIO","created_at":"2026-06-02T02:05:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZEJFOUIOJCIOCH7L","created_at":"2026-06-02T02:05:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZEJFOUIO","created_at":"2026-06-02T02:05:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZEJFOUIOJCIOCH7L4VOVVOIC46","target":"record","payload":{"canonical_record":{"source":{"id":"2606.02078","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T11:07:35Z","cross_cats_sorted":[],"title_canon_sha256":"9161779578cf503de5c610a0c2b4cdf083b735e5bb9f2e2c7993a03f6c93b708","abstract_canon_sha256":"4394651da76a10b68ff619e9245633e78ec82f4b0cd8ec93d70cb29641146cb0"},"schema_version":"1.0"},"canonical_sha256":"c91257510e4890e11febe55d5ab902e7a384a456a923e7e6996848cf2ecf33f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:05:05.349228Z","signature_b64":"8G3ALIud3N2q6Y6iiLNhzFsQWxd8Vl2R3gI2lfJ7GkQcZkvi1H3korxSFGgSACegW+W3i3LAN/uPN/5o/wYmDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c91257510e4890e11febe55d5ab902e7a384a456a923e7e6996848cf2ecf33f7","last_reissued_at":"2026-06-02T02:05:05.348860Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:05:05.348860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.02078","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":"2026-06-02T02:05:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NUK05+P/CMJRSu5997HwlLpVkXqs0Q1JoZsF51U99DruF0IWRfbrLSvvTxIvK9Wg5Q7lyzfFf/XljGT9QCT+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:43:27.420637Z"},"content_sha256":"dd6c938bdaf28aeb9c61388b87b0db122e498c3ddf60231b0116e78efbdbc6a7","schema_version":"1.0","event_id":"sha256:dd6c938bdaf28aeb9c61388b87b0db122e498c3ddf60231b0116e78efbdbc6a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZEJFOUIOJCIOCH7L4VOVVOIC46","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond $\\ell_2$-norm and $\\ell_\\infty$-norm: A Curvature-Inspired $\\ell_p$-Norm Scheme for Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jianhao Xu, Zhuang Yang","submitted_at":"2026-06-01T11:07:35Z","abstract_excerpt":"The existing optimizers for deep neural networks (DNNs) typically rely on either the $\\ell_2$ norm or the $\\ell_\\infty$ norm, resulting in optimizers that do not adapt well to substantial changes in curvature across parameter dimensions. Generally, the training process of DNNs often exhibits strong curvature anisotropy in the early period, whereas in the later period, the training process of DNNs tends to move toward flatter regions with weaker anisotropy. Particularly, optimizers based on the \\(\\ell_2\\)-norm are usually dominated by high-curvature directions, restricting updates of optimizers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02078","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/2606.02078/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":"2026-06-02T02:05:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZeVlrWCJCxOpkPo/SwQC6XAoO35T+QrNcFSEWk3xhA1vVguXGY5z/+yOp55FrBfkW5QzseoRjY23ZZxTokQgBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:43:27.421518Z"},"content_sha256":"a2df6e6a886a0ccdd9c6f5ccb3285890bb540f13137934e1eec7ccdc99b3b8f3","schema_version":"1.0","event_id":"sha256:a2df6e6a886a0ccdd9c6f5ccb3285890bb540f13137934e1eec7ccdc99b3b8f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZEJFOUIOJCIOCH7L4VOVVOIC46/bundle.json","state_url":"https://pith.science/pith/ZEJFOUIOJCIOCH7L4VOVVOIC46/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZEJFOUIOJCIOCH7L4VOVVOIC46/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":"2026-08-04T06:43:27Z","links":{"resolver":"https://pith.science/pith/ZEJFOUIOJCIOCH7L4VOVVOIC46","bundle":"https://pith.science/pith/ZEJFOUIOJCIOCH7L4VOVVOIC46/bundle.json","state":"https://pith.science/pith/ZEJFOUIOJCIOCH7L4VOVVOIC46/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZEJFOUIOJCIOCH7L4VOVVOIC46/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZEJFOUIOJCIOCH7L4VOVVOIC46","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":"4394651da76a10b68ff619e9245633e78ec82f4b0cd8ec93d70cb29641146cb0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T11:07:35Z","title_canon_sha256":"9161779578cf503de5c610a0c2b4cdf083b735e5bb9f2e2c7993a03f6c93b708"},"schema_version":"1.0","source":{"id":"2606.02078","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02078","created_at":"2026-06-02T02:05:05Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02078v1","created_at":"2026-06-02T02:05:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02078","created_at":"2026-06-02T02:05:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZEJFOUIOJCIO","created_at":"2026-06-02T02:05:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZEJFOUIOJCIOCH7L","created_at":"2026-06-02T02:05:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZEJFOUIO","created_at":"2026-06-02T02:05:05Z"}],"graph_snapshots":[{"event_id":"sha256:a2df6e6a886a0ccdd9c6f5ccb3285890bb540f13137934e1eec7ccdc99b3b8f3","target":"graph","created_at":"2026-06-02T02:05:05Z","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/2606.02078/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The existing optimizers for deep neural networks (DNNs) typically rely on either the $\\ell_2$ norm or the $\\ell_\\infty$ norm, resulting in optimizers that do not adapt well to substantial changes in curvature across parameter dimensions. Generally, the training process of DNNs often exhibits strong curvature anisotropy in the early period, whereas in the later period, the training process of DNNs tends to move toward flatter regions with weaker anisotropy. Particularly, optimizers based on the \\(\\ell_2\\)-norm are usually dominated by high-curvature directions, restricting updates of optimizers","authors_text":"Jianhao Xu, Zhuang Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T11:07:35Z","title":"Beyond $\\ell_2$-norm and $\\ell_\\infty$-norm: A Curvature-Inspired $\\ell_p$-Norm Scheme for Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02078","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:dd6c938bdaf28aeb9c61388b87b0db122e498c3ddf60231b0116e78efbdbc6a7","target":"record","created_at":"2026-06-02T02:05:05Z","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":"4394651da76a10b68ff619e9245633e78ec82f4b0cd8ec93d70cb29641146cb0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T11:07:35Z","title_canon_sha256":"9161779578cf503de5c610a0c2b4cdf083b735e5bb9f2e2c7993a03f6c93b708"},"schema_version":"1.0","source":{"id":"2606.02078","kind":"arxiv","version":1}},"canonical_sha256":"c91257510e4890e11febe55d5ab902e7a384a456a923e7e6996848cf2ecf33f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c91257510e4890e11febe55d5ab902e7a384a456a923e7e6996848cf2ecf33f7","first_computed_at":"2026-06-02T02:05:05.348860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:05:05.348860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8G3ALIud3N2q6Y6iiLNhzFsQWxd8Vl2R3gI2lfJ7GkQcZkvi1H3korxSFGgSACegW+W3i3LAN/uPN/5o/wYmDA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:05:05.349228Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02078","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd6c938bdaf28aeb9c61388b87b0db122e498c3ddf60231b0116e78efbdbc6a7","sha256:a2df6e6a886a0ccdd9c6f5ccb3285890bb540f13137934e1eec7ccdc99b3b8f3"],"state_sha256":"0e7cee84224809c65280004f3e90261804e75cc9f28c68dd4c4cb44e4daa506b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Kw2II/kd2+iSNbGGzZxR1gupN661HppvqyIrv5CFOTo5/ILTecWlNVTrtSMD2qpX85A0giCWbPkyWuJ47+qAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:43:27.428769Z","bundle_sha256":"3cd7c6278189e4b2ec199915b254f94bd143c38a32b21e80fe291ab6fcaa6e95"}}