{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XARKISWTWL77GOF3REB7SEHZXM","short_pith_number":"pith:XARKISWT","schema_version":"1.0","canonical_sha256":"b822a44ad3b2fff338bb8903f910f9bb14f361a79e1e056d6778f43b63fabd8f","source":{"kind":"arxiv","id":"2605.16839","version":1},"attestation_state":"computed","paper":{"title":"CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Block-union KV selection builds minimal tables so chunked prefill attention runs up to 2.72 times faster while staying close to dense accuracy.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Beomseok Kang, Dongwon Jo, Jae-Joon Kim, Jiwon Song","submitted_at":"2026-05-16T06:47:41Z","abstract_excerpt":"Chunked prefill has become a widely adopted serving strategy for long-context large language models, but efficient attention computation in this regime remains challenging. Existing sparse attention methods are primarily designed for one-shot prefill and do not translate efficiently to chunked prefill: block-sparse kernels lose efficiency when the query length is limited by the chunk size, while fine-grained pattern search becomes costly when repeated over the accumulated KV cache at every chunk. QUOKA, a recent method that directly targets chunked prefill, avoids sparse-kernel overhead but re"},"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":"2605.16839","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-16T06:47:41Z","cross_cats_sorted":[],"title_canon_sha256":"737bfbe36fe943f6268813677dd619f9410ed42f63c6c0a7ea40ef1f71ee028d","abstract_canon_sha256":"7ae9a3ee0b125d2213d63e83abef7aacf5a01522096f9c596bd9658a473937a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:25.503597Z","signature_b64":"AXKepVN9FRh32ycW0CskLdVtQWa8BoG7OKVUUOM79G2lixRA760v4f34rKPQQFhwyt/fw9sCXQOqAr4JjGeiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b822a44ad3b2fff338bb8903f910f9bb14f361a79e1e056d6778f43b63fabd8f","last_reissued_at":"2026-05-20T00:03:25.502780Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:25.502780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Block-union KV selection builds minimal tables so chunked prefill attention runs up to 2.72 times faster while staying close to dense accuracy.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Beomseok Kang, Dongwon Jo, Jae-Joon Kim, Jiwon Song","submitted_at":"2026-05-16T06:47:41Z","abstract_excerpt":"Chunked prefill has become a widely adopted serving strategy for long-context large language models, but efficient attention computation in this regime remains challenging. Existing sparse attention methods are primarily designed for one-shot prefill and do not translate efficiently to chunked prefill: block-sparse kernels lose efficiency when the query length is limited by the chunk size, while fine-grained pattern search becomes costly when repeated over the accumulated KV cache at every chunk. QUOKA, a recent method that directly targets chunked prefill, avoids sparse-kernel overhead but re"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On LLaMA-3.1-8B-Instruct, CompactAttention maintains accuracy close to dense attention on the RULER benchmark while delivering up to 2.72× attention speedup at 128K context length under chunked prefill.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The construction of GQA-aware per-group KV block tables via Q-block union and intra-group union produces the minimal tables that preserve all KV blocks selected by the input masks under paged execution constraints without missing query-specific entries.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CompactAttention accelerates chunked-prefill attention via Block-Union KV Selection, delivering up to 2.72x speedup at 128K context on LLaMA-3.1-8B while matching dense accuracy on RULER.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Block-union KV selection builds minimal tables so chunked prefill attention runs up to 2.72 times faster while staying close to dense accuracy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2076819c7affe5a6e61cdc4bfb3bb202c05ee3a9d9a7879c895920213ea15900"},"source":{"id":"2605.16839","kind":"arxiv","version":1},"verdict":{"id":"52526f39-cdc7-4f46-b6e5-98baadde51ba","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T21:15:41.130579Z","strongest_claim":"On LLaMA-3.1-8B-Instruct, CompactAttention maintains accuracy close to dense attention on the RULER benchmark while delivering up to 2.72× attention speedup at 128K context length under chunked prefill.","one_line_summary":"CompactAttention accelerates chunked-prefill attention via Block-Union KV Selection, delivering up to 2.72x speedup at 128K context on LLaMA-3.1-8B while matching dense accuracy on RULER.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The construction of GQA-aware per-group KV block tables via Q-block union and intra-group union produces the minimal tables that preserve all KV blocks selected by the input masks under paged execution constraints without missing query-specific entries.","pith_extraction_headline":"Block-union KV selection builds minimal tables so chunked prefill attention runs up to 2.72 times faster while staying close to dense accuracy."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16839/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.236773Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T21:20:56.776000Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.323268Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.395742Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"c456aa911eb1598e933d3ef7f12087df499110ce49fe6daf90c19f3d98342b88"},"references":{"count":28,"sample":[{"doi":"","year":2025,"title":"OpenAI GPT-5 System Card","work_id":"ca87689a-0d29-4476-b504-b65dbbb08af4","ref_index":1,"cited_arxiv_id":"2601.03267","is_internal_anchor":true},{"doi":"","year":2026,"title":"System card: Claude Opus 4.6","work_id":"d72a2098-05b3-4aae-ad94-f93a8fc5576d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Gemini 3 Pro model card","work_id":"267390f5-3359-44fc-855f-79a2c06c7d30","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Kimi K2.5: Visual Agentic Intelligence","work_id":"d690be8f-5d53-49b0-b1e7-79668eb8fcdb","ref_index":4,"cited_arxiv_id":"2602.02276","is_internal_anchor":true},{"doi":"","year":2026,"title":"Deepseek-v4: Towards highly efficient million-token context intelligence","work_id":"b5a5843d-47c0-432e-88d5-c9eaac555a7f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":28,"snapshot_sha256":"1e70316cabd47fd7bd15ab7a67cabec1e4f42f290186508b9ff28f8cd85a2a26","internal_anchors":9},"formal_canon":{"evidence_count":1,"snapshot_sha256":"13fb3fec9d7324a45aef6c07420d0047a3ef2724a78ed97d2733c55fc98a9517"},"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":"2605.16839","created_at":"2026-05-20T00:03:25.502901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16839v1","created_at":"2026-05-20T00:03:25.502901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16839","created_at":"2026-05-20T00:03:25.502901+00:00"},{"alias_kind":"pith_short_12","alias_value":"XARKISWTWL77","created_at":"2026-05-20T00:03:25.502901+00:00"},{"alias_kind":"pith_short_16","alias_value":"XARKISWTWL77GOF3","created_at":"2026-05-20T00:03:25.502901+00:00"},{"alias_kind":"pith_short_8","alias_value":"XARKISWT","created_at":"2026-05-20T00:03:25.502901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XARKISWTWL77GOF3REB7SEHZXM","json":"https://pith.science/pith/XARKISWTWL77GOF3REB7SEHZXM.json","graph_json":"https://pith.science/api/pith-number/XARKISWTWL77GOF3REB7SEHZXM/graph.json","events_json":"https://pith.science/api/pith-number/XARKISWTWL77GOF3REB7SEHZXM/events.json","paper":"https://pith.science/paper/XARKISWT"},"agent_actions":{"view_html":"https://pith.science/pith/XARKISWTWL77GOF3REB7SEHZXM","download_json":"https://pith.science/pith/XARKISWTWL77GOF3REB7SEHZXM.json","view_paper":"https://pith.science/paper/XARKISWT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16839&json=true","fetch_graph":"https://pith.science/api/pith-number/XARKISWTWL77GOF3REB7SEHZXM/graph.json","fetch_events":"https://pith.science/api/pith-number/XARKISWTWL77GOF3REB7SEHZXM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XARKISWTWL77GOF3REB7SEHZXM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XARKISWTWL77GOF3REB7SEHZXM/action/storage_attestation","attest_author":"https://pith.science/pith/XARKISWTWL77GOF3REB7SEHZXM/action/author_attestation","sign_citation":"https://pith.science/pith/XARKISWTWL77GOF3REB7SEHZXM/action/citation_signature","submit_replication":"https://pith.science/pith/XARKISWTWL77GOF3REB7SEHZXM/action/replication_record"}},"created_at":"2026-05-20T00:03:25.502901+00:00","updated_at":"2026-05-20T00:03:25.502901+00:00"}