{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HTDI2FY7TGIY4JUVGQOBQPCSCP","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":"0166ef561633e6c530ab93cf86303531d193319f8f5d530af5fc8eccf394609a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-30T05:21:57Z","title_canon_sha256":"bb1cb96f374fafa4d11f48d916fac452a7f2bfd25ae4ebcb1a2722dd1055e08b"},"schema_version":"1.0","source":{"id":"2601.22580","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.22580","created_at":"2026-06-05T01:15:19Z"},{"alias_kind":"arxiv_version","alias_value":"2601.22580v2","created_at":"2026-06-05T01:15:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22580","created_at":"2026-06-05T01:15:19Z"},{"alias_kind":"pith_short_12","alias_value":"HTDI2FY7TGIY","created_at":"2026-06-05T01:15:19Z"},{"alias_kind":"pith_short_16","alias_value":"HTDI2FY7TGIY4JUV","created_at":"2026-06-05T01:15:19Z"},{"alias_kind":"pith_short_8","alias_value":"HTDI2FY7","created_at":"2026-06-05T01:15:19Z"}],"graph_snapshots":[{"event_id":"sha256:2fedb167a10beff21065041c13a088f0f46a407b8dc8505b73fce681f5f9124a","target":"graph","created_at":"2026-06-05T01:15:19Z","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/2601.22580/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of Large Language Models (LLMs) hinges on the stable training of deep Transformer architectures. A critical design choice is the placement of normalization layers, leading to a fundamental trade-off: the ``PreNorm'' architecture ensures training stability at the cost of potential performance degradation in deep models, while the ``PostNorm'' architecture offers strong performance but suffers from severe training instability. In this work, we propose SpanNorm, a novel technique designed to resolve this dilemma by integrating the strengths of both paradigms. Structurally, SpanNorm es","authors_text":"Bei Li, Chao Wang, Jiaqi Zhang, Jingang Wang, Linkun Lyu, Peng Pei, Tong Xiao, Xin Chen, Xinyu Liu, Xunliang Cai, Yuchun Fan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-30T05:21:57Z","title":"SpanNorm: Reconciling Training Stability and Performance in Deep Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.22580","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":"sha256:4fd874c024462e9aace74da9b8f38caf0145bbd011942261fee7369ad73b240f","target":"record","created_at":"2026-06-05T01:15:19Z","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":"0166ef561633e6c530ab93cf86303531d193319f8f5d530af5fc8eccf394609a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-30T05:21:57Z","title_canon_sha256":"bb1cb96f374fafa4d11f48d916fac452a7f2bfd25ae4ebcb1a2722dd1055e08b"},"schema_version":"1.0","source":{"id":"2601.22580","kind":"arxiv","version":2}},"canonical_sha256":"3cc68d171f99918e2695341c183c5213d50f9aeb7244fbc0a865f971fad7dd10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cc68d171f99918e2695341c183c5213d50f9aeb7244fbc0a865f971fad7dd10","first_computed_at":"2026-06-05T01:15:19.555586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:19.555586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"11zMnb/DWwgCOcVcd5qxVUuD24VkFhr1MgBEA8sHtAcUHMsfpbiU7swtMiOsmmVBNvXLts6wDlo0EyOMlGpNCA==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:19.556084Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.22580","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fd874c024462e9aace74da9b8f38caf0145bbd011942261fee7369ad73b240f","sha256:2fedb167a10beff21065041c13a088f0f46a407b8dc8505b73fce681f5f9124a"],"state_sha256":"def0edf4ec5f3a485b8f39c401819bd4fa9777646ead3d76596f1e256a1fb7bc"}