{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NP2MUTJYVUNNWO2ER3OHMJ7U7W","short_pith_number":"pith:NP2MUTJY","schema_version":"1.0","canonical_sha256":"6bf4ca4d38ad1adb3b448edc7627f4fdb9ee7f25c21c6ff457e6e94acf1d9813","source":{"kind":"arxiv","id":"2511.02043","version":4},"attestation_state":"computed","paper":{"title":"Flashlight: PyTorch Compiler Extensions to Accelerate Attention Variants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.LG","authors_text":"Abhinav Jangda, Ang\\'elica Moreira, Bozhi You, Divya Mahajan, Irene Wang, Keshav Pingali, Roshan Dathathri, Zelal Su Mustafaoglu","submitted_at":"2025-11-03T20:25:19Z","abstract_excerpt":"Attention is a fundamental building block of large language models (LLMs), so there have been many efforts to implement it efficiently. For example, FlashAttention leverages tiling and kernel fusion to optimize attention. Recently, a number of variants of attention have been introduced to enhance model quality or efficiency. Supporting them efficiently remains difficult since they usually require specialized kernels or hand-tuned implementations. FlexAttention recently addressed part of this gap by using static programming templates to support FlashAttention-like kernels for a subset of 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":"2511.02043","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-03T20:25:19Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"0d6b3edf3307870668f7e4f471c7b2500634c1ec80d2f826dd5e7eb4072ad340","abstract_canon_sha256":"b7ab18297b586b6ae27c50df89e1af2744503a0b83278e531719a2e835ed0897"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:16.050565Z","signature_b64":"WGMs1iGT0riiyKkktfZ3x9QCH2uNTpMgMzlV6UcbaEnI0rcVg9+ZGysSNDHIjO0sh3jw1OR+REV6zJM44Yi0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bf4ca4d38ad1adb3b448edc7627f4fdb9ee7f25c21c6ff457e6e94acf1d9813","last_reissued_at":"2026-05-22T01:03:16.049836Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:16.049836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flashlight: PyTorch Compiler Extensions to Accelerate Attention Variants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.LG","authors_text":"Abhinav Jangda, Ang\\'elica Moreira, Bozhi You, Divya Mahajan, Irene Wang, Keshav Pingali, Roshan Dathathri, Zelal Su Mustafaoglu","submitted_at":"2025-11-03T20:25:19Z","abstract_excerpt":"Attention is a fundamental building block of large language models (LLMs), so there have been many efforts to implement it efficiently. For example, FlashAttention leverages tiling and kernel fusion to optimize attention. Recently, a number of variants of attention have been introduced to enhance model quality or efficiency. Supporting them efficiently remains difficult since they usually require specialized kernels or hand-tuned implementations. FlexAttention recently addressed part of this gap by using static programming templates to support FlashAttention-like kernels for a subset of attent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.02043","kind":"arxiv","version":4},"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/2511.02043/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":"2511.02043","created_at":"2026-05-22T01:03:16.049942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.02043v4","created_at":"2026-05-22T01:03:16.049942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.02043","created_at":"2026-05-22T01:03:16.049942+00:00"},{"alias_kind":"pith_short_12","alias_value":"NP2MUTJYVUNN","created_at":"2026-05-22T01:03:16.049942+00:00"},{"alias_kind":"pith_short_16","alias_value":"NP2MUTJYVUNNWO2E","created_at":"2026-05-22T01:03:16.049942+00:00"},{"alias_kind":"pith_short_8","alias_value":"NP2MUTJY","created_at":"2026-05-22T01:03:16.049942+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/NP2MUTJYVUNNWO2ER3OHMJ7U7W","json":"https://pith.science/pith/NP2MUTJYVUNNWO2ER3OHMJ7U7W.json","graph_json":"https://pith.science/api/pith-number/NP2MUTJYVUNNWO2ER3OHMJ7U7W/graph.json","events_json":"https://pith.science/api/pith-number/NP2MUTJYVUNNWO2ER3OHMJ7U7W/events.json","paper":"https://pith.science/paper/NP2MUTJY"},"agent_actions":{"view_html":"https://pith.science/pith/NP2MUTJYVUNNWO2ER3OHMJ7U7W","download_json":"https://pith.science/pith/NP2MUTJYVUNNWO2ER3OHMJ7U7W.json","view_paper":"https://pith.science/paper/NP2MUTJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.02043&json=true","fetch_graph":"https://pith.science/api/pith-number/NP2MUTJYVUNNWO2ER3OHMJ7U7W/graph.json","fetch_events":"https://pith.science/api/pith-number/NP2MUTJYVUNNWO2ER3OHMJ7U7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NP2MUTJYVUNNWO2ER3OHMJ7U7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NP2MUTJYVUNNWO2ER3OHMJ7U7W/action/storage_attestation","attest_author":"https://pith.science/pith/NP2MUTJYVUNNWO2ER3OHMJ7U7W/action/author_attestation","sign_citation":"https://pith.science/pith/NP2MUTJYVUNNWO2ER3OHMJ7U7W/action/citation_signature","submit_replication":"https://pith.science/pith/NP2MUTJYVUNNWO2ER3OHMJ7U7W/action/replication_record"}},"created_at":"2026-05-22T01:03:16.049942+00:00","updated_at":"2026-05-22T01:03:16.049942+00:00"}