{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JJEO6DL3PSTVSA5R3NNX6HHBRW","short_pith_number":"pith:JJEO6DL3","schema_version":"1.0","canonical_sha256":"4a48ef0d7b7ca75903b1db5b7f1ce18d9a3a52f07bc138ea0c539244d56feeff","source":{"kind":"arxiv","id":"2605.17887","version":1},"attestation_state":"computed","paper":{"title":"Attention Sinks and Outliers in Attention Residuals","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Binghui Wang, Chenghao Qiu, Chenwei Xu, Eric Hanchen Jiang, Haoran Dai, Haotian Zhang, Haozheng Luo, Jingyuan Huang, Shaoyang Zhang, Xi Chen, Yan Chen, Yijiang Li, Zhenyu Pan","submitted_at":"2026-05-18T05:53:09Z","abstract_excerpt":"We propose OASIS, an outlier- and sink-aware technique built on inter-layer null signaling. As AttnResidual architectures introduce an additional depth-wise normalization channel, they improve inter-layer routing flexibility but also exacerbate attention sinks, activation outliers, and the resulting degradation in inference stability and quantization robustness. OASIS addresses this issue by introducing a Softmax1-based null space and coupling token-level null evidence to depth routing through an inter-layer null signal, thereby reducing sink-dominated routing and improving structural robustne"},"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":"2605.17887","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T05:53:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1ae67c549eced96bc455e0ef42d3f22831638bcda2de68fd53eee13eb3bcff7f","abstract_canon_sha256":"3ccd38cfa83954805a05226a8402d70730257506ef17f25616bbb609f145eb8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:03.844576Z","signature_b64":"Dle44cXk97j5TkwUV6id/wovh5yhVFp9JToSAWoy15z9eeq5/GUiB25G3fd/C2pIRkIfYvC4F44FmJ5TVqj3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a48ef0d7b7ca75903b1db5b7f1ce18d9a3a52f07bc138ea0c539244d56feeff","last_reissued_at":"2026-05-20T00:05:03.843541Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:03.843541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention Sinks and Outliers in Attention Residuals","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Binghui Wang, Chenghao Qiu, Chenwei Xu, Eric Hanchen Jiang, Haoran Dai, Haotian Zhang, Haozheng Luo, Jingyuan Huang, Shaoyang Zhang, Xi Chen, Yan Chen, Yijiang Li, Zhenyu Pan","submitted_at":"2026-05-18T05:53:09Z","abstract_excerpt":"We propose OASIS, an outlier- and sink-aware technique built on inter-layer null signaling. As AttnResidual architectures introduce an additional depth-wise normalization channel, they improve inter-layer routing flexibility but also exacerbate attention sinks, activation outliers, and the resulting degradation in inference stability and quantization robustness. OASIS addresses this issue by introducing a Softmax1-based null space and coupling token-level null evidence to depth routing through an inter-layer null signal, thereby reducing sink-dominated routing and improving structural robustne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17887","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/2605.17887/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":"2605.17887","created_at":"2026-05-20T00:05:03.843731+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17887v1","created_at":"2026-05-20T00:05:03.843731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17887","created_at":"2026-05-20T00:05:03.843731+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJEO6DL3PSTV","created_at":"2026-05-20T00:05:03.843731+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJEO6DL3PSTVSA5R","created_at":"2026-05-20T00:05:03.843731+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJEO6DL3","created_at":"2026-05-20T00:05:03.843731+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/JJEO6DL3PSTVSA5R3NNX6HHBRW","json":"https://pith.science/pith/JJEO6DL3PSTVSA5R3NNX6HHBRW.json","graph_json":"https://pith.science/api/pith-number/JJEO6DL3PSTVSA5R3NNX6HHBRW/graph.json","events_json":"https://pith.science/api/pith-number/JJEO6DL3PSTVSA5R3NNX6HHBRW/events.json","paper":"https://pith.science/paper/JJEO6DL3"},"agent_actions":{"view_html":"https://pith.science/pith/JJEO6DL3PSTVSA5R3NNX6HHBRW","download_json":"https://pith.science/pith/JJEO6DL3PSTVSA5R3NNX6HHBRW.json","view_paper":"https://pith.science/paper/JJEO6DL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17887&json=true","fetch_graph":"https://pith.science/api/pith-number/JJEO6DL3PSTVSA5R3NNX6HHBRW/graph.json","fetch_events":"https://pith.science/api/pith-number/JJEO6DL3PSTVSA5R3NNX6HHBRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJEO6DL3PSTVSA5R3NNX6HHBRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJEO6DL3PSTVSA5R3NNX6HHBRW/action/storage_attestation","attest_author":"https://pith.science/pith/JJEO6DL3PSTVSA5R3NNX6HHBRW/action/author_attestation","sign_citation":"https://pith.science/pith/JJEO6DL3PSTVSA5R3NNX6HHBRW/action/citation_signature","submit_replication":"https://pith.science/pith/JJEO6DL3PSTVSA5R3NNX6HHBRW/action/replication_record"}},"created_at":"2026-05-20T00:05:03.843731+00:00","updated_at":"2026-05-20T00:05:03.843731+00:00"}