{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:S7R2NBBCKPWPM4N5UDDHCHFRB4","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":"1bcf5ffa50a9de4ed1dbf36ad1273ace773654eca9ef89e3d6d455c417d426fe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-13T09:19:34Z","title_canon_sha256":"ec979ac4b67ad28160d0c05f7ed0ab0f329a71068f7dc5747623641ff58409c0"},"schema_version":"1.0","source":{"id":"2007.06257","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.06257","created_at":"2026-07-05T08:04:09Z"},{"alias_kind":"arxiv_version","alias_value":"2007.06257v2","created_at":"2026-07-05T08:04:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.06257","created_at":"2026-07-05T08:04:09Z"},{"alias_kind":"pith_short_12","alias_value":"S7R2NBBCKPWP","created_at":"2026-07-05T08:04:09Z"},{"alias_kind":"pith_short_16","alias_value":"S7R2NBBCKPWPM4N5","created_at":"2026-07-05T08:04:09Z"},{"alias_kind":"pith_short_8","alias_value":"S7R2NBBC","created_at":"2026-07-05T08:04:09Z"}],"graph_snapshots":[{"event_id":"sha256:2a9991dc7440828b71db72623085215ff10161c10eabdc77c4b87e6c3043ba86","target":"graph","created_at":"2026-07-05T08:04:09Z","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/2007.06257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stacking non-linear layers allows deep neural networks to model complicated functions, and including residual connections in Transformer layers is beneficial for convergence and performance. However, residual connections may make the model \"forget\" distant layers and fail to fuse information from previous layers effectively. Selectively managing the representation aggregation of Transformer layers may lead to better performance. In this paper, we present a Transformer with depth-wise LSTMs connecting cascading Transformer layers and sub-layers. We show that layer normalization and feed-forward","authors_text":"Deyi Xiong, Hongfei Xu, Josef van Genabith, Qiuhui Liu, Yang Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-13T09:19:34Z","title":"Rewiring the Transformer with Depth-Wise LSTMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.06257","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":"sha256:4543a79f07cc3015ba779a348c34c0b045af96c97549351c8899d6943cad1937","target":"record","created_at":"2026-07-05T08:04:09Z","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":"1bcf5ffa50a9de4ed1dbf36ad1273ace773654eca9ef89e3d6d455c417d426fe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-13T09:19:34Z","title_canon_sha256":"ec979ac4b67ad28160d0c05f7ed0ab0f329a71068f7dc5747623641ff58409c0"},"schema_version":"1.0","source":{"id":"2007.06257","kind":"arxiv","version":2}},"canonical_sha256":"97e3a6842253ecf671bda0c6711cb10f0cb3a9e851f1f2ea595ec16a8c7a5d06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97e3a6842253ecf671bda0c6711cb10f0cb3a9e851f1f2ea595ec16a8c7a5d06","first_computed_at":"2026-07-05T08:04:09.847357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:09.847357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GsGJbgAIfZ5qXIPhZ+nVmU7TwcKZYYa/IhLyNbQDXQjKGGhXFQtUCfU8/Y8SUi15wZTqbGbGe+9/8LfQ3lXYBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:09.847848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.06257","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4543a79f07cc3015ba779a348c34c0b045af96c97549351c8899d6943cad1937","sha256:2a9991dc7440828b71db72623085215ff10161c10eabdc77c4b87e6c3043ba86"],"state_sha256":"652922a3e1d648a09e2e0f46ab02487a73398cd81677cc80c71537f37749a90a"}