{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6EAOJO5KX57JMFUMH3PQLA3ZLI","short_pith_number":"pith:6EAOJO5K","schema_version":"1.0","canonical_sha256":"f100e4bbaabf7e96168c3edf0583795a1bd95f1bbea284a29d54ba0703d7a59d","source":{"kind":"arxiv","id":"2510.27258","version":3},"attestation_state":"computed","paper":{"title":"Higher-order Linear Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Higher-order Linear Attention captures second-order interactions in linear time with a constant-size state.","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Quanquan Gu, Yifan Zhang, Zhen Qin","submitted_at":"2025-10-31T07:54:37Z","abstract_excerpt":"The quadratic cost of scaled dot-product attention is a central obstacle to scaling autoregressive language models to long contexts. Linear-time attention and State Space Models (SSMs) provide scalable alternatives but are typically restricted to first-order or kernel-based approximations, which can limit expressivity. We introduce Higher-order Linear Attention (HLA), a causal, streaming mechanism that realizes higher interactions via compact prefix sufficient statistics. In the second-order case, HLA maintains a constant-size state and computes per-token outputs in linear time without materia"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2510.27258","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-31T07:54:37Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f0bfc303a838b5982ad5d513662834d6f5995deadb1e423399ed1b9128751e38","abstract_canon_sha256":"6621ca0d78c7a98bc0d561bec1b1e67ec62dc6611e6cad8853988c691a0c70cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:33.710135Z","signature_b64":"I7rkLQf9RF1Msg2sifU4jOjYlqys7XqZVoysYJujprS8OKNp8yqkjkIid8IdBzCHWpI7D2Q4xhayMS1a+58kCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f100e4bbaabf7e96168c3edf0583795a1bd95f1bbea284a29d54ba0703d7a59d","last_reissued_at":"2026-05-18T03:09:33.709679Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:33.709679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Higher-order Linear Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Higher-order Linear Attention captures second-order interactions in linear time with a constant-size state.","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Quanquan Gu, Yifan Zhang, Zhen Qin","submitted_at":"2025-10-31T07:54:37Z","abstract_excerpt":"The quadratic cost of scaled dot-product attention is a central obstacle to scaling autoregressive language models to long contexts. Linear-time attention and State Space Models (SSMs) provide scalable alternatives but are typically restricted to first-order or kernel-based approximations, which can limit expressivity. We introduce Higher-order Linear Attention (HLA), a causal, streaming mechanism that realizes higher interactions via compact prefix sufficient statistics. In the second-order case, HLA maintains a constant-size state and computes per-token outputs in linear time without materia"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"In the second-order case, HLA maintains a constant-size state and computes per-token outputs in linear time without materializing any n × n matrices.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That compact prefix sufficient statistics exist and suffice to realize the desired higher-order interactions while preserving the causal streaming property and exact equivalence to the serial recurrence.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Higher-order Linear Attention realizes second-order and higher interactions in linear-time causal attention via constant-size state and associative scans.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Higher-order Linear Attention captures second-order interactions in linear time with a constant-size state.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b13b8529c27f9929f91f1b543ae1d504bee2857e21d372f730569860e4c16b4d"},"source":{"id":"2510.27258","kind":"arxiv","version":3},"verdict":{"id":"0d980761-c643-48e4-83af-7b4b47fcaebc","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T03:03:06.024190Z","strongest_claim":"In the second-order case, HLA maintains a constant-size state and computes per-token outputs in linear time without materializing any n × n matrices.","one_line_summary":"Higher-order Linear Attention realizes second-order and higher interactions in linear-time causal attention via constant-size state and associative scans.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That compact prefix sufficient statistics exist and suffice to realize the desired higher-order interactions while preserving the causal streaming property and exact equivalence to the serial recurrence.","pith_extraction_headline":"Higher-order Linear Attention captures second-order interactions in linear time with a constant-size state."},"references":{"count":18,"sample":[{"doi":"","year":null,"title":"Titans: Learning to Memorize at Test Time","work_id":"fb2b7625-b733-43cb-af52-00b0a31a8d7f","ref_index":1,"cited_arxiv_id":"2501.00663","is_internal_anchor":true},{"doi":"","year":null,"title":"Atlas: Learning to optimally memorize the context at test time","work_id":"88ad83a5-1a41-49a6-a975-2d9374634987","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2009,"title":"Rethinking Attention with Performers","work_id":"4c26d308-8b72-4a98-8e73-950617a75f50","ref_index":3,"cited_arxiv_id":"2009.14794","is_internal_anchor":true},{"doi":"","year":null,"title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","work_id":"d8eba076-0449-4f6a-aae1-5a7260677f0f","ref_index":4,"cited_arxiv_id":"2405.21060","is_internal_anchor":true},{"doi":"","year":null,"title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","work_id":"4ee75248-1199-492c-a52f-6661e0f4adff","ref_index":5,"cited_arxiv_id":"2312.00752","is_internal_anchor":true}],"resolved_work":18,"snapshot_sha256":"aa8e2f50389f1003f8e05673391b7eabf3afaa849c25e915a2c32bab6e3caa49","internal_anchors":12},"formal_canon":{"evidence_count":2,"snapshot_sha256":"e460d43a0a4ab87bf36a224d74c352b5064764644a4d0f0254bdd95e8dad4fd5"},"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":"2510.27258","created_at":"2026-05-18T03:09:33.709759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.27258v3","created_at":"2026-05-18T03:09:33.709759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.27258","created_at":"2026-05-18T03:09:33.709759+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EAOJO5KX57J","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EAOJO5KX57JMFUM","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EAOJO5K","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6EAOJO5KX57JMFUMH3PQLA3ZLI","json":"https://pith.science/pith/6EAOJO5KX57JMFUMH3PQLA3ZLI.json","graph_json":"https://pith.science/api/pith-number/6EAOJO5KX57JMFUMH3PQLA3ZLI/graph.json","events_json":"https://pith.science/api/pith-number/6EAOJO5KX57JMFUMH3PQLA3ZLI/events.json","paper":"https://pith.science/paper/6EAOJO5K"},"agent_actions":{"view_html":"https://pith.science/pith/6EAOJO5KX57JMFUMH3PQLA3ZLI","download_json":"https://pith.science/pith/6EAOJO5KX57JMFUMH3PQLA3ZLI.json","view_paper":"https://pith.science/paper/6EAOJO5K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.27258&json=true","fetch_graph":"https://pith.science/api/pith-number/6EAOJO5KX57JMFUMH3PQLA3ZLI/graph.json","fetch_events":"https://pith.science/api/pith-number/6EAOJO5KX57JMFUMH3PQLA3ZLI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EAOJO5KX57JMFUMH3PQLA3ZLI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EAOJO5KX57JMFUMH3PQLA3ZLI/action/storage_attestation","attest_author":"https://pith.science/pith/6EAOJO5KX57JMFUMH3PQLA3ZLI/action/author_attestation","sign_citation":"https://pith.science/pith/6EAOJO5KX57JMFUMH3PQLA3ZLI/action/citation_signature","submit_replication":"https://pith.science/pith/6EAOJO5KX57JMFUMH3PQLA3ZLI/action/replication_record"}},"created_at":"2026-05-18T03:09:33.709759+00:00","updated_at":"2026-05-18T03:09:33.709759+00:00"}