{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:O2QKGYYLBOC65AMZA6IRCHSV7M","short_pith_number":"pith:O2QKGYYL","schema_version":"1.0","canonical_sha256":"76a0a3630b0b85ee81990791111e55fb2ba2211fa03ae9013d5369cdb1873ed2","source":{"kind":"arxiv","id":"2606.31859","version":1},"attestation_state":"computed","paper":{"title":"Review Residuals: Update-Conditioned Residual Gating for Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Kyle Kramer","submitted_at":"2026-06-30T15:53:27Z","abstract_excerpt":"Residual connections add every sublayer's proposed update with a fixed coefficient of one; the network never evaluates whether an update is reliable before committing it. Drawing on the human-factors principle of independent verification, we introduce Review Residuals, which scale each update by a learned, input-dependent gate conditioned on both the current state and the proposed update: h_l = h_{l-1} + r_l * u_l with r_l = sigmoid(W[RMSNorm(h_{l-1}), RMSNorm(u_l)]). Conditioning the gate on the update is the property that distinguishes it from prior gated and scaled residuals. We report two "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.31859","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T15:53:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"dfdfc74f9de5efc2707b4e896312c223df5fdd10c939eb0bdccb6d1171b2f8d2","abstract_canon_sha256":"ab6b0b5ac405ebcea60000eecba28800a718abab7db097dd61c18c8b0a074229"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:17.730510Z","signature_b64":"Kl8X8Xem2S81KP4tR9DhoECrUz6Lb+1hlcsqclUlJEbVedle+NZIU5yVEb6zr2AYC1zgMqqsXwsk8r042RydBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76a0a3630b0b85ee81990791111e55fb2ba2211fa03ae9013d5369cdb1873ed2","last_reissued_at":"2026-07-01T01:18:17.729982Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:17.729982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Review Residuals: Update-Conditioned Residual Gating for Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Kyle Kramer","submitted_at":"2026-06-30T15:53:27Z","abstract_excerpt":"Residual connections add every sublayer's proposed update with a fixed coefficient of one; the network never evaluates whether an update is reliable before committing it. Drawing on the human-factors principle of independent verification, we introduce Review Residuals, which scale each update by a learned, input-dependent gate conditioned on both the current state and the proposed update: h_l = h_{l-1} + r_l * u_l with r_l = sigmoid(W[RMSNorm(h_{l-1}), RMSNorm(u_l)]). Conditioning the gate on the update is the property that distinguishes it from prior gated and scaled residuals. We report two "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31859","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/2606.31859/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.31859","created_at":"2026-07-01T01:18:17.730052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31859v1","created_at":"2026-07-01T01:18:17.730052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31859","created_at":"2026-07-01T01:18:17.730052+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2QKGYYLBOC6","created_at":"2026-07-01T01:18:17.730052+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2QKGYYLBOC65AMZ","created_at":"2026-07-01T01:18:17.730052+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2QKGYYL","created_at":"2026-07-01T01:18:17.730052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O2QKGYYLBOC65AMZA6IRCHSV7M","json":"https://pith.science/pith/O2QKGYYLBOC65AMZA6IRCHSV7M.json","graph_json":"https://pith.science/api/pith-number/O2QKGYYLBOC65AMZA6IRCHSV7M/graph.json","events_json":"https://pith.science/api/pith-number/O2QKGYYLBOC65AMZA6IRCHSV7M/events.json","paper":"https://pith.science/paper/O2QKGYYL"},"agent_actions":{"view_html":"https://pith.science/pith/O2QKGYYLBOC65AMZA6IRCHSV7M","download_json":"https://pith.science/pith/O2QKGYYLBOC65AMZA6IRCHSV7M.json","view_paper":"https://pith.science/paper/O2QKGYYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31859&json=true","fetch_graph":"https://pith.science/api/pith-number/O2QKGYYLBOC65AMZA6IRCHSV7M/graph.json","fetch_events":"https://pith.science/api/pith-number/O2QKGYYLBOC65AMZA6IRCHSV7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2QKGYYLBOC65AMZA6IRCHSV7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2QKGYYLBOC65AMZA6IRCHSV7M/action/storage_attestation","attest_author":"https://pith.science/pith/O2QKGYYLBOC65AMZA6IRCHSV7M/action/author_attestation","sign_citation":"https://pith.science/pith/O2QKGYYLBOC65AMZA6IRCHSV7M/action/citation_signature","submit_replication":"https://pith.science/pith/O2QKGYYLBOC65AMZA6IRCHSV7M/action/replication_record"}},"created_at":"2026-07-01T01:18:17.730052+00:00","updated_at":"2026-07-01T01:18:17.730052+00:00"}