{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7SV6WX6SVRPXAHNVWAZQ6DJCY5","short_pith_number":"pith:7SV6WX6S","schema_version":"1.0","canonical_sha256":"fcabeb5fd2ac5f701db5b0330f0d22c7620d4a64ec8daeebe67d24b5a016a375","source":{"kind":"arxiv","id":"2606.30562","version":1},"attestation_state":"computed","paper":{"title":"Morphing into Hybrid Attention Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Disen Lan, Jianbin Zheng, Xin Xia, Xipeng Qiu, Xuanda Wang, Xuefeng Xiao, Yu Cheng, Yuxi Ren","submitted_at":"2026-06-29T17:02:34Z","abstract_excerpt":"Hybrid attention models improve long-context efficiency by retaining only a subset of full-attention layers and replacing the remaining layers with linear attention. However, the effectiveness of Transformer-to-hybrid conversion critically depends on which layers preserve full attention. Existing hybrid layer selection methods typically rely on heuristic strategies such as fixed placement patterns or layerwise scoring, implicitly treating layer importance as isolated and overlooking the interdependent layer effect under a global hybrid configuration. In this work, we formulate hybrid layer sel"},"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":"2606.30562","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T17:02:34Z","cross_cats_sorted":[],"title_canon_sha256":"796157b1df394c33522d2339be352affc9c2a660e26160baff7392660432f4d0","abstract_canon_sha256":"219e92509e071e7dabb363f48cfedb19372bc1367092213b7d7c2e2b76a8b038"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:20.668220Z","signature_b64":"Z9N6dvrjygUKm5drs4/cRSZ88W/6O8nTulf33nfBr+0vxfbkFsDI8lmzZN4lLha3xZl/PZrsk70cIH5yL79gDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcabeb5fd2ac5f701db5b0330f0d22c7620d4a64ec8daeebe67d24b5a016a375","last_reissued_at":"2026-06-30T02:18:20.667520Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:20.667520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Morphing into Hybrid Attention Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Disen Lan, Jianbin Zheng, Xin Xia, Xipeng Qiu, Xuanda Wang, Xuefeng Xiao, Yu Cheng, Yuxi Ren","submitted_at":"2026-06-29T17:02:34Z","abstract_excerpt":"Hybrid attention models improve long-context efficiency by retaining only a subset of full-attention layers and replacing the remaining layers with linear attention. However, the effectiveness of Transformer-to-hybrid conversion critically depends on which layers preserve full attention. Existing hybrid layer selection methods typically rely on heuristic strategies such as fixed placement patterns or layerwise scoring, implicitly treating layer importance as isolated and overlooking the interdependent layer effect under a global hybrid configuration. In this work, we formulate hybrid layer sel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30562","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/2606.30562/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":"2606.30562","created_at":"2026-06-30T02:18:20.667626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30562v1","created_at":"2026-06-30T02:18:20.667626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30562","created_at":"2026-06-30T02:18:20.667626+00:00"},{"alias_kind":"pith_short_12","alias_value":"7SV6WX6SVRPX","created_at":"2026-06-30T02:18:20.667626+00:00"},{"alias_kind":"pith_short_16","alias_value":"7SV6WX6SVRPXAHNV","created_at":"2026-06-30T02:18:20.667626+00:00"},{"alias_kind":"pith_short_8","alias_value":"7SV6WX6S","created_at":"2026-06-30T02:18:20.667626+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/7SV6WX6SVRPXAHNVWAZQ6DJCY5","json":"https://pith.science/pith/7SV6WX6SVRPXAHNVWAZQ6DJCY5.json","graph_json":"https://pith.science/api/pith-number/7SV6WX6SVRPXAHNVWAZQ6DJCY5/graph.json","events_json":"https://pith.science/api/pith-number/7SV6WX6SVRPXAHNVWAZQ6DJCY5/events.json","paper":"https://pith.science/paper/7SV6WX6S"},"agent_actions":{"view_html":"https://pith.science/pith/7SV6WX6SVRPXAHNVWAZQ6DJCY5","download_json":"https://pith.science/pith/7SV6WX6SVRPXAHNVWAZQ6DJCY5.json","view_paper":"https://pith.science/paper/7SV6WX6S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30562&json=true","fetch_graph":"https://pith.science/api/pith-number/7SV6WX6SVRPXAHNVWAZQ6DJCY5/graph.json","fetch_events":"https://pith.science/api/pith-number/7SV6WX6SVRPXAHNVWAZQ6DJCY5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7SV6WX6SVRPXAHNVWAZQ6DJCY5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7SV6WX6SVRPXAHNVWAZQ6DJCY5/action/storage_attestation","attest_author":"https://pith.science/pith/7SV6WX6SVRPXAHNVWAZQ6DJCY5/action/author_attestation","sign_citation":"https://pith.science/pith/7SV6WX6SVRPXAHNVWAZQ6DJCY5/action/citation_signature","submit_replication":"https://pith.science/pith/7SV6WX6SVRPXAHNVWAZQ6DJCY5/action/replication_record"}},"created_at":"2026-06-30T02:18:20.667626+00:00","updated_at":"2026-06-30T02:18:20.667626+00:00"}