{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:R2G6RHI5OTYJ773SPRPR4VYAEK","short_pith_number":"pith:R2G6RHI5","schema_version":"1.0","canonical_sha256":"8e8de89d1d74f09fff727c5f1e570022bb383c6157d8ddf4bce7b961ed90013d","source":{"kind":"arxiv","id":"2510.02361","version":2},"attestation_state":"computed","paper":{"title":"ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Wei, Fangxiang Feng, Haojie Ouyang, Jianwei Lv, Lei Ren, Xiaojie Wang","submitted_at":"2025-09-28T11:04:00Z","abstract_excerpt":"Transformer-based large models excel in natural language processing and computer vision, but face severe computational inefficiencies due to the self-attention's quadratic complexity with input tokens. Recently, researchers have proposed a series of methods based on block selection and compression to alleviate this problem, but they either have issues with semantic incompleteness or poor training-inference efficiency. To comprehensively address these challenges, we propose ChunkLLM, a lightweight and pluggable training framework. Specifically, we introduce two components: QK Adapter (Q-Adapter"},"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":"2510.02361","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-28T11:04:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0ea44986a246960d41508d0d889d4950062bc96b000710d541b5654cc1d01e0b","abstract_canon_sha256":"d5e2c297b4a8793f947aca6af934276d39640dec9925d5cf61fc11d1ee7b62e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:03:56.775417Z","signature_b64":"yFon4lzwN0avA4KzhEQtCBZ8O+f9ls3XX42KLUzDQYsGHDIuVvXuPicFi0VhNxQULGiJaYVU/g/nAQadS4r6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e8de89d1d74f09fff727c5f1e570022bb383c6157d8ddf4bce7b961ed90013d","last_reissued_at":"2026-05-26T02:03:56.774545Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:03:56.774545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Wei, Fangxiang Feng, Haojie Ouyang, Jianwei Lv, Lei Ren, Xiaojie Wang","submitted_at":"2025-09-28T11:04:00Z","abstract_excerpt":"Transformer-based large models excel in natural language processing and computer vision, but face severe computational inefficiencies due to the self-attention's quadratic complexity with input tokens. Recently, researchers have proposed a series of methods based on block selection and compression to alleviate this problem, but they either have issues with semantic incompleteness or poor training-inference efficiency. To comprehensively address these challenges, we propose ChunkLLM, a lightweight and pluggable training framework. Specifically, we introduce two components: QK Adapter (Q-Adapter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.02361","kind":"arxiv","version":2},"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/2510.02361/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":"2510.02361","created_at":"2026-05-26T02:03:56.774681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.02361v2","created_at":"2026-05-26T02:03:56.774681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.02361","created_at":"2026-05-26T02:03:56.774681+00:00"},{"alias_kind":"pith_short_12","alias_value":"R2G6RHI5OTYJ","created_at":"2026-05-26T02:03:56.774681+00:00"},{"alias_kind":"pith_short_16","alias_value":"R2G6RHI5OTYJ773S","created_at":"2026-05-26T02:03:56.774681+00:00"},{"alias_kind":"pith_short_8","alias_value":"R2G6RHI5","created_at":"2026-05-26T02:03:56.774681+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/R2G6RHI5OTYJ773SPRPR4VYAEK","json":"https://pith.science/pith/R2G6RHI5OTYJ773SPRPR4VYAEK.json","graph_json":"https://pith.science/api/pith-number/R2G6RHI5OTYJ773SPRPR4VYAEK/graph.json","events_json":"https://pith.science/api/pith-number/R2G6RHI5OTYJ773SPRPR4VYAEK/events.json","paper":"https://pith.science/paper/R2G6RHI5"},"agent_actions":{"view_html":"https://pith.science/pith/R2G6RHI5OTYJ773SPRPR4VYAEK","download_json":"https://pith.science/pith/R2G6RHI5OTYJ773SPRPR4VYAEK.json","view_paper":"https://pith.science/paper/R2G6RHI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.02361&json=true","fetch_graph":"https://pith.science/api/pith-number/R2G6RHI5OTYJ773SPRPR4VYAEK/graph.json","fetch_events":"https://pith.science/api/pith-number/R2G6RHI5OTYJ773SPRPR4VYAEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R2G6RHI5OTYJ773SPRPR4VYAEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R2G6RHI5OTYJ773SPRPR4VYAEK/action/storage_attestation","attest_author":"https://pith.science/pith/R2G6RHI5OTYJ773SPRPR4VYAEK/action/author_attestation","sign_citation":"https://pith.science/pith/R2G6RHI5OTYJ773SPRPR4VYAEK/action/citation_signature","submit_replication":"https://pith.science/pith/R2G6RHI5OTYJ773SPRPR4VYAEK/action/replication_record"}},"created_at":"2026-05-26T02:03:56.774681+00:00","updated_at":"2026-05-26T02:03:56.774681+00:00"}