{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MFOVBOXE5VYS4HKXSS4I43XYEI","short_pith_number":"pith:MFOVBOXE","schema_version":"1.0","canonical_sha256":"615d50bae4ed712e1d5794b88e6ef82205096dfda5bbd48aefe760b3421cb3b3","source":{"kind":"arxiv","id":"2409.17372","version":2},"attestation_state":"computed","paper":{"title":"Search for Efficient Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Wu, Ming Lin, Pu Zhao, Xuan Shen, Xue Lin, Yanzhi Wang, Yifan Gong, Yushu Wu, Zhenglun Kong, Zheng Zhan","submitted_at":"2024-09-25T21:32:12Z","abstract_excerpt":"Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Numerous efficient techniques, including weight pruning, quantization, and distillation, have been embraced to compress LLMs, targeting memory reduction and inference acceleration, which underscore the redundancy in LLMs. However, most model compression techniques concentrate on weight optimization, overlooking the exploration of optimal architectures. Besides, traditional architecture search methods, limited by the elevated complexity with extensive parameters, struggle to demonstrate their eff"},"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":"2409.17372","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-25T21:32:12Z","cross_cats_sorted":[],"title_canon_sha256":"3ceda56b3e28fe8e80212d22f3ca71eb71c55351db9622afc102cad74c0e986b","abstract_canon_sha256":"6e6f2cef5f1e7c490db94d830d296d444e251dc597b4ea78eead5243b91efce7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:55.171052Z","signature_b64":"PBh9Ie4vOa5BEJ4W8sMVIvzpeG7tKiEbnpOjC6bWd38EfeCEA6GLCBPXgo7nVK75lZZgC6e2+ueolmisUhy8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"615d50bae4ed712e1d5794b88e6ef82205096dfda5bbd48aefe760b3421cb3b3","last_reissued_at":"2026-07-05T09:28:55.170569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:55.170569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Search for Efficient Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Wu, Ming Lin, Pu Zhao, Xuan Shen, Xue Lin, Yanzhi Wang, Yifan Gong, Yushu Wu, Zhenglun Kong, Zheng Zhan","submitted_at":"2024-09-25T21:32:12Z","abstract_excerpt":"Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Numerous efficient techniques, including weight pruning, quantization, and distillation, have been embraced to compress LLMs, targeting memory reduction and inference acceleration, which underscore the redundancy in LLMs. However, most model compression techniques concentrate on weight optimization, overlooking the exploration of optimal architectures. Besides, traditional architecture search methods, limited by the elevated complexity with extensive parameters, struggle to demonstrate their eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17372","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/2409.17372/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":"2409.17372","created_at":"2026-07-05T09:28:55.170621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.17372v2","created_at":"2026-07-05T09:28:55.170621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17372","created_at":"2026-07-05T09:28:55.170621+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFOVBOXE5VYS","created_at":"2026-07-05T09:28:55.170621+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFOVBOXE5VYS4HKX","created_at":"2026-07-05T09:28:55.170621+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFOVBOXE","created_at":"2026-07-05T09:28:55.170621+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09412","citing_title":"FASP: Fast and Accurate Structured Pruning of Large Language Models","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MFOVBOXE5VYS4HKXSS4I43XYEI","json":"https://pith.science/pith/MFOVBOXE5VYS4HKXSS4I43XYEI.json","graph_json":"https://pith.science/api/pith-number/MFOVBOXE5VYS4HKXSS4I43XYEI/graph.json","events_json":"https://pith.science/api/pith-number/MFOVBOXE5VYS4HKXSS4I43XYEI/events.json","paper":"https://pith.science/paper/MFOVBOXE"},"agent_actions":{"view_html":"https://pith.science/pith/MFOVBOXE5VYS4HKXSS4I43XYEI","download_json":"https://pith.science/pith/MFOVBOXE5VYS4HKXSS4I43XYEI.json","view_paper":"https://pith.science/paper/MFOVBOXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.17372&json=true","fetch_graph":"https://pith.science/api/pith-number/MFOVBOXE5VYS4HKXSS4I43XYEI/graph.json","fetch_events":"https://pith.science/api/pith-number/MFOVBOXE5VYS4HKXSS4I43XYEI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFOVBOXE5VYS4HKXSS4I43XYEI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFOVBOXE5VYS4HKXSS4I43XYEI/action/storage_attestation","attest_author":"https://pith.science/pith/MFOVBOXE5VYS4HKXSS4I43XYEI/action/author_attestation","sign_citation":"https://pith.science/pith/MFOVBOXE5VYS4HKXSS4I43XYEI/action/citation_signature","submit_replication":"https://pith.science/pith/MFOVBOXE5VYS4HKXSS4I43XYEI/action/replication_record"}},"created_at":"2026-07-05T09:28:55.170621+00:00","updated_at":"2026-07-05T09:28:55.170621+00:00"}