{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UFT3YNF6SC6WIJRJTCCZFKKZVV","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":"e0b768a00f79df6bbffd2e86706b4bb3c1b2650ca28809e847b9bcc6014be62b","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-28T12:19:47Z","title_canon_sha256":"61cb1f626c5db7b67e2f1e2bca9ef068a7aebb32592bcb75b1808c33dfcd86aa"},"schema_version":"1.0","source":{"id":"2304.14802","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14802","created_at":"2026-07-05T06:05:21Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14802v1","created_at":"2026-07-05T06:05:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14802","created_at":"2026-07-05T06:05:21Z"},{"alias_kind":"pith_short_12","alias_value":"UFT3YNF6SC6W","created_at":"2026-07-05T06:05:21Z"},{"alias_kind":"pith_short_16","alias_value":"UFT3YNF6SC6WIJRJ","created_at":"2026-07-05T06:05:21Z"},{"alias_kind":"pith_short_8","alias_value":"UFT3YNF6","created_at":"2026-07-05T06:05:21Z"}],"graph_snapshots":[{"event_id":"sha256:19d7af585d75753f22bf0abff2792874d4efad1743b26f322a981e23c32c7e60","target":"graph","created_at":"2026-07-05T06:05:21Z","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/2304.14802/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer networks have become the preferred architecture for many tasks due to their state-of-the-art performance. However, the optimal way to implement residual connections in Transformer, which are essential for effective training, is still debated. Two widely used variants are the Post-Layer-Normalization (Post-LN) and Pre-Layer-Normalization (Pre-LN) Transformers, which apply layer normalization after each residual block's output or before each residual block's input, respectively. While both variants enjoy their advantages, they also suffer from severe limitations: Post-LN causes gradi","authors_text":"Arul Menezes, Hany Hassan Awadalla, Huishuai Zhang, Jiang Bian, Junliang Guo, Rui Yan, Shufang Xie, Tao Qin, Xu Tan","cross_cats":["cs.AI","cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-28T12:19:47Z","title":"ResiDual: Transformer with Dual Residual Connections"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14802","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":"sha256:5c4716a8050657798d931cbae6f404043a263f79378f68347daadabe5be5bf8e","target":"record","created_at":"2026-07-05T06:05:21Z","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":"e0b768a00f79df6bbffd2e86706b4bb3c1b2650ca28809e847b9bcc6014be62b","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-28T12:19:47Z","title_canon_sha256":"61cb1f626c5db7b67e2f1e2bca9ef068a7aebb32592bcb75b1808c33dfcd86aa"},"schema_version":"1.0","source":{"id":"2304.14802","kind":"arxiv","version":1}},"canonical_sha256":"a167bc34be90bd642629988592a959ad5caf29f745288d7b465b6401800bb217","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a167bc34be90bd642629988592a959ad5caf29f745288d7b465b6401800bb217","first_computed_at":"2026-07-05T06:05:21.182225Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:05:21.182225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SxUNE3Yx09w4o4IQSM4F6NynA/xFBbUg+kHtEiF78mLNcxLeHwbzw8AklFAymdMVcPas9XOgORBVHoYwISsdBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:05:21.182651Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.14802","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c4716a8050657798d931cbae6f404043a263f79378f68347daadabe5be5bf8e","sha256:19d7af585d75753f22bf0abff2792874d4efad1743b26f322a981e23c32c7e60"],"state_sha256":"d4ba5393b2698d1ec1cfbad9d09e3d48a202cebd42fc3a84d5e8b02675e54c66"}