{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GRZ5JYULPWH4B3KS62IGFNGE57","short_pith_number":"pith:GRZ5JYUL","schema_version":"1.0","canonical_sha256":"3473d4e28b7d8fc0ed52f69062b4c4efef76e3032e80ec527bccf2436adf8b7c","source":{"kind":"arxiv","id":"2501.15255","version":1},"attestation_state":"computed","paper":{"title":"Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hongli Xu, Yang Xu, Yunming Liao, Zhiwei Yao, Zihuai Xu, Zuan Xie","submitted_at":"2025-01-25T16:03:58Z","abstract_excerpt":"Considering the hardware-friendly characteristics and broad applicability, structured pruning has emerged as an efficient solution to reduce the resource demands of large language models (LLMs) on resource-constrained devices. Traditional structured pruning methods often need fine-tuning to recover performance loss, which incurs high memory overhead and substantial data requirements, rendering them unsuitable for on-device applications. Additionally, post-training structured pruning techniques typically necessitate specific activation functions or architectural modifications, thereby limiting "},"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":"2501.15255","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-25T16:03:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"db4f657831c60218bc0d4e887bda8ce68bbdf8286cfdb33b9b723d01f0c314db","abstract_canon_sha256":"b03efd1905896707d98669f3fa6a667ed9d1bc4fc34b4273afe0d17c30887636"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:26.406092Z","signature_b64":"hDdG+k2bjhqFWpT5IohZJW82tCToiruhNwmxV7D1EVeLmKyxuBtSoSGiJxAyIklJSmPKG+EF4XXVvRlRciKhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3473d4e28b7d8fc0ed52f69062b4c4efef76e3032e80ec527bccf2436adf8b7c","last_reissued_at":"2026-07-05T10:05:26.405590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:26.405590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hongli Xu, Yang Xu, Yunming Liao, Zhiwei Yao, Zihuai Xu, Zuan Xie","submitted_at":"2025-01-25T16:03:58Z","abstract_excerpt":"Considering the hardware-friendly characteristics and broad applicability, structured pruning has emerged as an efficient solution to reduce the resource demands of large language models (LLMs) on resource-constrained devices. Traditional structured pruning methods often need fine-tuning to recover performance loss, which incurs high memory overhead and substantial data requirements, rendering them unsuitable for on-device applications. Additionally, post-training structured pruning techniques typically necessitate specific activation functions or architectural modifications, thereby limiting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15255","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/2501.15255/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":"2501.15255","created_at":"2026-07-05T10:05:26.405655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15255v1","created_at":"2026-07-05T10:05:26.405655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15255","created_at":"2026-07-05T10:05:26.405655+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRZ5JYULPWH4","created_at":"2026-07-05T10:05:26.405655+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRZ5JYULPWH4B3KS","created_at":"2026-07-05T10:05:26.405655+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRZ5JYUL","created_at":"2026-07-05T10:05:26.405655+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/GRZ5JYULPWH4B3KS62IGFNGE57","json":"https://pith.science/pith/GRZ5JYULPWH4B3KS62IGFNGE57.json","graph_json":"https://pith.science/api/pith-number/GRZ5JYULPWH4B3KS62IGFNGE57/graph.json","events_json":"https://pith.science/api/pith-number/GRZ5JYULPWH4B3KS62IGFNGE57/events.json","paper":"https://pith.science/paper/GRZ5JYUL"},"agent_actions":{"view_html":"https://pith.science/pith/GRZ5JYULPWH4B3KS62IGFNGE57","download_json":"https://pith.science/pith/GRZ5JYULPWH4B3KS62IGFNGE57.json","view_paper":"https://pith.science/paper/GRZ5JYUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15255&json=true","fetch_graph":"https://pith.science/api/pith-number/GRZ5JYULPWH4B3KS62IGFNGE57/graph.json","fetch_events":"https://pith.science/api/pith-number/GRZ5JYULPWH4B3KS62IGFNGE57/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRZ5JYULPWH4B3KS62IGFNGE57/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRZ5JYULPWH4B3KS62IGFNGE57/action/storage_attestation","attest_author":"https://pith.science/pith/GRZ5JYULPWH4B3KS62IGFNGE57/action/author_attestation","sign_citation":"https://pith.science/pith/GRZ5JYULPWH4B3KS62IGFNGE57/action/citation_signature","submit_replication":"https://pith.science/pith/GRZ5JYULPWH4B3KS62IGFNGE57/action/replication_record"}},"created_at":"2026-07-05T10:05:26.405655+00:00","updated_at":"2026-07-05T10:05:26.405655+00:00"}