{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UMLZJUNIILI6OT5OAZ2BDNBWCB","short_pith_number":"pith:UMLZJUNI","schema_version":"1.0","canonical_sha256":"a31794d1a842d1e74fae067411b43610748a3fba372f57ed784c253ea9085e8a","source":{"kind":"arxiv","id":"2607.19358","version":1},"attestation_state":"computed","paper":{"title":"LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Zeng, Fan Jiang, Linlong Xu, Longyue Wang, Shimin Shan, Weihua Luo, Yu Liu, Yu Zhao, Zekun Zhang","submitted_at":"2026-05-29T03:05:29Z","abstract_excerpt":"Recent advances in long chain-of-thought reasoning models such as DeepSeek-R1 have led to increasingly longer inference context lengths under the test-time scaling paradigm. However, the O(n^2) computational complexity of standard self-attention causes inference costs to grow sharply with long sequences, limiting the deployment of long-CoT reasoning in production settings. To address this, we propose LISA (Linear-Indexed Sparse Attention), a plug-and-play attention replacement module that requires no pretraining from scratch. LISA integrates two lightweight components in parallel within the or"},"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":"2607.19358","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T03:05:29Z","cross_cats_sorted":[],"title_canon_sha256":"b6da7d6fe505a137bc289b655de0f502b6b1072af2e320177555c749a857b528","abstract_canon_sha256":"35628adecb0d4022076353b52dfbac0ec629caa78f97c787e92a1b633cf378fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T00:23:44.670409Z","signature_b64":"2hl3hsgl70c4kqN6W8BZSIy1ii2waE33P6LVZWBFLzuWQS0TJwz57HkVGmWJGakgIrVjGJ5uiVyiusv/2JO8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a31794d1a842d1e74fae067411b43610748a3fba372f57ed784c253ea9085e8a","last_reissued_at":"2026-07-23T00:23:44.669523Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T00:23:44.669523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Zeng, Fan Jiang, Linlong Xu, Longyue Wang, Shimin Shan, Weihua Luo, Yu Liu, Yu Zhao, Zekun Zhang","submitted_at":"2026-05-29T03:05:29Z","abstract_excerpt":"Recent advances in long chain-of-thought reasoning models such as DeepSeek-R1 have led to increasingly longer inference context lengths under the test-time scaling paradigm. However, the O(n^2) computational complexity of standard self-attention causes inference costs to grow sharply with long sequences, limiting the deployment of long-CoT reasoning in production settings. To address this, we propose LISA (Linear-Indexed Sparse Attention), a plug-and-play attention replacement module that requires no pretraining from scratch. LISA integrates two lightweight components in parallel within the or"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19358","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/2607.19358/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":"2607.19358","created_at":"2026-07-23T00:23:44.669956+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.19358v1","created_at":"2026-07-23T00:23:44.669956+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19358","created_at":"2026-07-23T00:23:44.669956+00:00"},{"alias_kind":"pith_short_12","alias_value":"UMLZJUNIILI6","created_at":"2026-07-23T00:23:44.669956+00:00"},{"alias_kind":"pith_short_16","alias_value":"UMLZJUNIILI6OT5O","created_at":"2026-07-23T00:23:44.669956+00:00"},{"alias_kind":"pith_short_8","alias_value":"UMLZJUNI","created_at":"2026-07-23T00:23:44.669956+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/UMLZJUNIILI6OT5OAZ2BDNBWCB","json":"https://pith.science/pith/UMLZJUNIILI6OT5OAZ2BDNBWCB.json","graph_json":"https://pith.science/api/pith-number/UMLZJUNIILI6OT5OAZ2BDNBWCB/graph.json","events_json":"https://pith.science/api/pith-number/UMLZJUNIILI6OT5OAZ2BDNBWCB/events.json","paper":"https://pith.science/paper/UMLZJUNI"},"agent_actions":{"view_html":"https://pith.science/pith/UMLZJUNIILI6OT5OAZ2BDNBWCB","download_json":"https://pith.science/pith/UMLZJUNIILI6OT5OAZ2BDNBWCB.json","view_paper":"https://pith.science/paper/UMLZJUNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.19358&json=true","fetch_graph":"https://pith.science/api/pith-number/UMLZJUNIILI6OT5OAZ2BDNBWCB/graph.json","fetch_events":"https://pith.science/api/pith-number/UMLZJUNIILI6OT5OAZ2BDNBWCB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UMLZJUNIILI6OT5OAZ2BDNBWCB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UMLZJUNIILI6OT5OAZ2BDNBWCB/action/storage_attestation","attest_author":"https://pith.science/pith/UMLZJUNIILI6OT5OAZ2BDNBWCB/action/author_attestation","sign_citation":"https://pith.science/pith/UMLZJUNIILI6OT5OAZ2BDNBWCB/action/citation_signature","submit_replication":"https://pith.science/pith/UMLZJUNIILI6OT5OAZ2BDNBWCB/action/replication_record"}},"created_at":"2026-07-23T00:23:44.669956+00:00","updated_at":"2026-07-23T00:23:44.669956+00:00"}