{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YBDWLXJZTGAFHH2RAXENSIIU3N","short_pith_number":"pith:YBDWLXJZ","schema_version":"1.0","canonical_sha256":"c04765dd399980539f5105c8d92114db53b2e2fd37c5484e19b1076a541b46d0","source":{"kind":"arxiv","id":"2606.11052","version":1},"attestation_state":"computed","paper":{"title":"Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boyu Zhu, Huiming Wang, Xinyu Zhou, Yingfa Chen, Yi Xu, Zhijiang Guo, Zhiwei Li","submitted_at":"2026-06-09T16:17:19Z","abstract_excerpt":"Chain-of-thought (CoT) supervised fine-tuning (SFT) is widely adopted to improve reasoning ability, yet we find that it systematically degrades long-context recall in hybrid linear-attention models. Across architectures including HypeNet and Jet-Nemotron, retrieval performance on Needle-In-A-Haystack (NIAH) deteriorates substantially after CoT-SFT, and the degradation becomes more severe under harder retrieval settings and longer context windows. For example, HypeNet-9B on NIAH-S2@256K decreases from $67.2\\%$ to $9.4\\%$. We attribute this to CoT-SFT biasing attention gradients toward short-ran"},"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":"2606.11052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T16:17:19Z","cross_cats_sorted":[],"title_canon_sha256":"9139e28386020b1b25038f0f2b07380edb9207b4e43af1e87167587cfdc72efb","abstract_canon_sha256":"223ade04307dac051437c8edfe5139f29c748bb7a302bf2ae60f847a0153d7b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:11:07.105103Z","signature_b64":"s0OtHnH2Fii6SHZMhOFtCmCXVfbrfShqhh7XZZO2mpyhlKEppk6MeCSeCFNZEPgyfh5HD5vYsgKmR3w6JpKzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c04765dd399980539f5105c8d92114db53b2e2fd37c5484e19b1076a541b46d0","last_reissued_at":"2026-06-10T01:11:07.104160Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:11:07.104160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boyu Zhu, Huiming Wang, Xinyu Zhou, Yingfa Chen, Yi Xu, Zhijiang Guo, Zhiwei Li","submitted_at":"2026-06-09T16:17:19Z","abstract_excerpt":"Chain-of-thought (CoT) supervised fine-tuning (SFT) is widely adopted to improve reasoning ability, yet we find that it systematically degrades long-context recall in hybrid linear-attention models. Across architectures including HypeNet and Jet-Nemotron, retrieval performance on Needle-In-A-Haystack (NIAH) deteriorates substantially after CoT-SFT, and the degradation becomes more severe under harder retrieval settings and longer context windows. For example, HypeNet-9B on NIAH-S2@256K decreases from $67.2\\%$ to $9.4\\%$. We attribute this to CoT-SFT biasing attention gradients toward short-ran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11052","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/2606.11052/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":"2606.11052","created_at":"2026-06-10T01:11:07.104331+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11052v1","created_at":"2026-06-10T01:11:07.104331+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11052","created_at":"2026-06-10T01:11:07.104331+00:00"},{"alias_kind":"pith_short_12","alias_value":"YBDWLXJZTGAF","created_at":"2026-06-10T01:11:07.104331+00:00"},{"alias_kind":"pith_short_16","alias_value":"YBDWLXJZTGAFHH2R","created_at":"2026-06-10T01:11:07.104331+00:00"},{"alias_kind":"pith_short_8","alias_value":"YBDWLXJZ","created_at":"2026-06-10T01:11:07.104331+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/YBDWLXJZTGAFHH2RAXENSIIU3N","json":"https://pith.science/pith/YBDWLXJZTGAFHH2RAXENSIIU3N.json","graph_json":"https://pith.science/api/pith-number/YBDWLXJZTGAFHH2RAXENSIIU3N/graph.json","events_json":"https://pith.science/api/pith-number/YBDWLXJZTGAFHH2RAXENSIIU3N/events.json","paper":"https://pith.science/paper/YBDWLXJZ"},"agent_actions":{"view_html":"https://pith.science/pith/YBDWLXJZTGAFHH2RAXENSIIU3N","download_json":"https://pith.science/pith/YBDWLXJZTGAFHH2RAXENSIIU3N.json","view_paper":"https://pith.science/paper/YBDWLXJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11052&json=true","fetch_graph":"https://pith.science/api/pith-number/YBDWLXJZTGAFHH2RAXENSIIU3N/graph.json","fetch_events":"https://pith.science/api/pith-number/YBDWLXJZTGAFHH2RAXENSIIU3N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YBDWLXJZTGAFHH2RAXENSIIU3N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YBDWLXJZTGAFHH2RAXENSIIU3N/action/storage_attestation","attest_author":"https://pith.science/pith/YBDWLXJZTGAFHH2RAXENSIIU3N/action/author_attestation","sign_citation":"https://pith.science/pith/YBDWLXJZTGAFHH2RAXENSIIU3N/action/citation_signature","submit_replication":"https://pith.science/pith/YBDWLXJZTGAFHH2RAXENSIIU3N/action/replication_record"}},"created_at":"2026-06-10T01:11:07.104331+00:00","updated_at":"2026-06-10T01:11:07.104331+00:00"}