{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XIATMQIQYNXRZ7GYGFRZM6OPSI","short_pith_number":"pith:XIATMQIQ","schema_version":"1.0","canonical_sha256":"ba01364110c36f1cfcd831639679cf9212ffd3fddfe5ec538843f0440d275b1b","source":{"kind":"arxiv","id":"2306.01160","version":1},"attestation_state":"computed","paper":{"title":"Faster Causal Attention Over Large Sequences Through Sparse Flash Attention","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Daniele Paliotta, Fran\\c{c}ois Fleuret, Martin Jaggi, Matteo Pagliardini","submitted_at":"2023-06-01T21:33:59Z","abstract_excerpt":"Transformer-based language models have found many diverse applications requiring them to process sequences of increasing length. For these applications, the causal self-attention -- which is the only component scaling quadratically w.r.t. the sequence length -- becomes a central concern. While many works have proposed schemes to sparsify the attention patterns and reduce the computational overhead of self-attention, those are often limited by implementations concerns and end up imposing a simple and static structure over the attention matrix. Conversely, implementing more dynamic sparse attent"},"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":"2306.01160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T21:33:59Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"15a934385069a712dab74eb532ededf8423b0b1a37e0b692c3e567c82250a6fd","abstract_canon_sha256":"194ca8aa4b8dccd1fce36082902c880ff92147eeda3eb03f6854bccf62819dcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:38.838612Z","signature_b64":"sAAGiQnszU2Sm4tO3wMAaQeU7L5fQvhCrmuaSqXgkFTJnuWBuz0NDdxP1t6Mz1wpbjsTSiTeE7xYXGMGaBYjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba01364110c36f1cfcd831639679cf9212ffd3fddfe5ec538843f0440d275b1b","last_reissued_at":"2026-07-05T06:16:38.838205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:38.838205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Faster Causal Attention Over Large Sequences Through Sparse Flash Attention","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Daniele Paliotta, Fran\\c{c}ois Fleuret, Martin Jaggi, Matteo Pagliardini","submitted_at":"2023-06-01T21:33:59Z","abstract_excerpt":"Transformer-based language models have found many diverse applications requiring them to process sequences of increasing length. For these applications, the causal self-attention -- which is the only component scaling quadratically w.r.t. the sequence length -- becomes a central concern. While many works have proposed schemes to sparsify the attention patterns and reduce the computational overhead of self-attention, those are often limited by implementations concerns and end up imposing a simple and static structure over the attention matrix. Conversely, implementing more dynamic sparse attent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01160","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/2306.01160/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":"2306.01160","created_at":"2026-07-05T06:16:38.838260+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01160v1","created_at":"2026-07-05T06:16:38.838260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01160","created_at":"2026-07-05T06:16:38.838260+00:00"},{"alias_kind":"pith_short_12","alias_value":"XIATMQIQYNXR","created_at":"2026-07-05T06:16:38.838260+00:00"},{"alias_kind":"pith_short_16","alias_value":"XIATMQIQYNXRZ7GY","created_at":"2026-07-05T06:16:38.838260+00:00"},{"alias_kind":"pith_short_8","alias_value":"XIATMQIQ","created_at":"2026-07-05T06:16:38.838260+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.14294","citing_title":"A Survey on Efficient Inference for Large Language Models","ref_index":160,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XIATMQIQYNXRZ7GYGFRZM6OPSI","json":"https://pith.science/pith/XIATMQIQYNXRZ7GYGFRZM6OPSI.json","graph_json":"https://pith.science/api/pith-number/XIATMQIQYNXRZ7GYGFRZM6OPSI/graph.json","events_json":"https://pith.science/api/pith-number/XIATMQIQYNXRZ7GYGFRZM6OPSI/events.json","paper":"https://pith.science/paper/XIATMQIQ"},"agent_actions":{"view_html":"https://pith.science/pith/XIATMQIQYNXRZ7GYGFRZM6OPSI","download_json":"https://pith.science/pith/XIATMQIQYNXRZ7GYGFRZM6OPSI.json","view_paper":"https://pith.science/paper/XIATMQIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01160&json=true","fetch_graph":"https://pith.science/api/pith-number/XIATMQIQYNXRZ7GYGFRZM6OPSI/graph.json","fetch_events":"https://pith.science/api/pith-number/XIATMQIQYNXRZ7GYGFRZM6OPSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XIATMQIQYNXRZ7GYGFRZM6OPSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XIATMQIQYNXRZ7GYGFRZM6OPSI/action/storage_attestation","attest_author":"https://pith.science/pith/XIATMQIQYNXRZ7GYGFRZM6OPSI/action/author_attestation","sign_citation":"https://pith.science/pith/XIATMQIQYNXRZ7GYGFRZM6OPSI/action/citation_signature","submit_replication":"https://pith.science/pith/XIATMQIQYNXRZ7GYGFRZM6OPSI/action/replication_record"}},"created_at":"2026-07-05T06:16:38.838260+00:00","updated_at":"2026-07-05T06:16:38.838260+00:00"}