{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5AVSX54LRM4X7ULLDHBLMHPSWU","short_pith_number":"pith:5AVSX54L","schema_version":"1.0","canonical_sha256":"e82b2bf78b8b397fd16b19c2b61df2b537e39cd430f3207ac64a6d50b54af57e","source":{"kind":"arxiv","id":"2409.13199","version":2},"attestation_state":"computed","paper":{"title":"CFSP: An Efficient Structured Pruning Framework for LLMs with Coarse-to-Fine Activation Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Qin, Dongliang Xu, HuiMing Fan, Jingchang Chen, Liping Shan, Minghua Ma, Ming Liu, Qing Yang, Yuxin Wang, Zekun Wang","submitted_at":"2024-09-20T04:03:27Z","abstract_excerpt":"The colossal parameters and computational overhead of Large Language Models (LLMs) challenge their real-world applications. Network pruning, which targets unstructured or structured sparsity by removing redundant parameters, has recently been explored for LLM acceleration. Existing LLM pruning works focus on unstructured pruning, which typically requires special hardware support for a practical speed-up. In contrast, structured pruning can reduce latency on general devices. However, it remains a challenge to perform structured pruning efficiently and maintain performance, especially at high sp"},"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":"2409.13199","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-20T04:03:27Z","cross_cats_sorted":[],"title_canon_sha256":"036e65714502449b5a735c3e50d289152dde56fa0e38a501d9c8e6327ffab6fd","abstract_canon_sha256":"052ea92bc89815eb96f35e571ece5c67f82916e135d6aca91a8b01382cff5415"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:51.866583Z","signature_b64":"nGKn/zzK1Pdyvp24p4GLzxcYI9FzTD6VhbCsr8qMgpphkvAvaFRbTJjliIl1t0rDBxGkn3djkcFcUFsPjMFCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e82b2bf78b8b397fd16b19c2b61df2b537e39cd430f3207ac64a6d50b54af57e","last_reissued_at":"2026-07-05T09:46:51.866015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:51.866015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CFSP: An Efficient Structured Pruning Framework for LLMs with Coarse-to-Fine Activation Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Qin, Dongliang Xu, HuiMing Fan, Jingchang Chen, Liping Shan, Minghua Ma, Ming Liu, Qing Yang, Yuxin Wang, Zekun Wang","submitted_at":"2024-09-20T04:03:27Z","abstract_excerpt":"The colossal parameters and computational overhead of Large Language Models (LLMs) challenge their real-world applications. Network pruning, which targets unstructured or structured sparsity by removing redundant parameters, has recently been explored for LLM acceleration. Existing LLM pruning works focus on unstructured pruning, which typically requires special hardware support for a practical speed-up. In contrast, structured pruning can reduce latency on general devices. However, it remains a challenge to perform structured pruning efficiently and maintain performance, especially at high sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13199","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/2409.13199/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":"2409.13199","created_at":"2026-07-05T09:46:51.866092+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.13199v2","created_at":"2026-07-05T09:46:51.866092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13199","created_at":"2026-07-05T09:46:51.866092+00:00"},{"alias_kind":"pith_short_12","alias_value":"5AVSX54LRM4X","created_at":"2026-07-05T09:46:51.866092+00:00"},{"alias_kind":"pith_short_16","alias_value":"5AVSX54LRM4X7ULL","created_at":"2026-07-05T09:46:51.866092+00:00"},{"alias_kind":"pith_short_8","alias_value":"5AVSX54L","created_at":"2026-07-05T09:46:51.866092+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/5AVSX54LRM4X7ULLDHBLMHPSWU","json":"https://pith.science/pith/5AVSX54LRM4X7ULLDHBLMHPSWU.json","graph_json":"https://pith.science/api/pith-number/5AVSX54LRM4X7ULLDHBLMHPSWU/graph.json","events_json":"https://pith.science/api/pith-number/5AVSX54LRM4X7ULLDHBLMHPSWU/events.json","paper":"https://pith.science/paper/5AVSX54L"},"agent_actions":{"view_html":"https://pith.science/pith/5AVSX54LRM4X7ULLDHBLMHPSWU","download_json":"https://pith.science/pith/5AVSX54LRM4X7ULLDHBLMHPSWU.json","view_paper":"https://pith.science/paper/5AVSX54L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.13199&json=true","fetch_graph":"https://pith.science/api/pith-number/5AVSX54LRM4X7ULLDHBLMHPSWU/graph.json","fetch_events":"https://pith.science/api/pith-number/5AVSX54LRM4X7ULLDHBLMHPSWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5AVSX54LRM4X7ULLDHBLMHPSWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5AVSX54LRM4X7ULLDHBLMHPSWU/action/storage_attestation","attest_author":"https://pith.science/pith/5AVSX54LRM4X7ULLDHBLMHPSWU/action/author_attestation","sign_citation":"https://pith.science/pith/5AVSX54LRM4X7ULLDHBLMHPSWU/action/citation_signature","submit_replication":"https://pith.science/pith/5AVSX54LRM4X7ULLDHBLMHPSWU/action/replication_record"}},"created_at":"2026-07-05T09:46:51.866092+00:00","updated_at":"2026-07-05T09:46:51.866092+00:00"}