{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2QSZFGMVMBRIOV2SJ5TLK75E37","short_pith_number":"pith:2QSZFGMV","schema_version":"1.0","canonical_sha256":"d42592999560628757524f66b57fa4dfcd57409cb0fab28666395da388343dcf","source":{"kind":"arxiv","id":"2405.18377","version":1},"attestation_state":"computed","paper":{"title":"LLaMA-NAS: Efficient Neural Architecture Search for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anthony Sarah, Maciej Szankin, Sairam Sundaresan, Sharath Nittur Sridhar","submitted_at":"2024-05-28T17:20:44Z","abstract_excerpt":"The abilities of modern large language models (LLMs) in solving natural language processing, complex reasoning, sentiment analysis and other tasks have been extraordinary which has prompted their extensive adoption. Unfortunately, these abilities come with very high memory and computational costs which precludes the use of LLMs on most hardware platforms. To mitigate this, we propose an effective method of finding Pareto-optimal network architectures based on LLaMA2-7B using one-shot NAS. In particular, we fine-tune LLaMA2-7B only once and then apply genetic algorithm-based search to find smal"},"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":"2405.18377","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-28T17:20:44Z","cross_cats_sorted":[],"title_canon_sha256":"8d49bc577b0be67a3f57bd808e2a208f5a9d647a5122e37265f01e01ab92b920","abstract_canon_sha256":"58d07bdfb3d1cdd8caaabc006b60639b263277dac696c7e1fb57a1c7fd9c3876"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:19.508222Z","signature_b64":"y4iz2Q6kUHQFh1Qmdi3k3vKwnc8dnWVC1MBKPQ+IzFUlm9Dy9SqBFMuu6jajl3FCNuMj1z3QjVoqWmY0+RNvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d42592999560628757524f66b57fa4dfcd57409cb0fab28666395da388343dcf","last_reissued_at":"2026-07-05T08:24:19.507801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:19.507801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLaMA-NAS: Efficient Neural Architecture Search for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anthony Sarah, Maciej Szankin, Sairam Sundaresan, Sharath Nittur Sridhar","submitted_at":"2024-05-28T17:20:44Z","abstract_excerpt":"The abilities of modern large language models (LLMs) in solving natural language processing, complex reasoning, sentiment analysis and other tasks have been extraordinary which has prompted their extensive adoption. Unfortunately, these abilities come with very high memory and computational costs which precludes the use of LLMs on most hardware platforms. To mitigate this, we propose an effective method of finding Pareto-optimal network architectures based on LLaMA2-7B using one-shot NAS. In particular, we fine-tune LLaMA2-7B only once and then apply genetic algorithm-based search to find smal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18377","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/2405.18377/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":"2405.18377","created_at":"2026-07-05T08:24:19.507864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18377v1","created_at":"2026-07-05T08:24:19.507864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18377","created_at":"2026-07-05T08:24:19.507864+00:00"},{"alias_kind":"pith_short_12","alias_value":"2QSZFGMVMBRI","created_at":"2026-07-05T08:24:19.507864+00:00"},{"alias_kind":"pith_short_16","alias_value":"2QSZFGMVMBRIOV2S","created_at":"2026-07-05T08:24:19.507864+00:00"},{"alias_kind":"pith_short_8","alias_value":"2QSZFGMV","created_at":"2026-07-05T08:24:19.507864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29582","citing_title":"Bilevel Optimization for Neural Architecture Search","ref_index":105,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2QSZFGMVMBRIOV2SJ5TLK75E37","json":"https://pith.science/pith/2QSZFGMVMBRIOV2SJ5TLK75E37.json","graph_json":"https://pith.science/api/pith-number/2QSZFGMVMBRIOV2SJ5TLK75E37/graph.json","events_json":"https://pith.science/api/pith-number/2QSZFGMVMBRIOV2SJ5TLK75E37/events.json","paper":"https://pith.science/paper/2QSZFGMV"},"agent_actions":{"view_html":"https://pith.science/pith/2QSZFGMVMBRIOV2SJ5TLK75E37","download_json":"https://pith.science/pith/2QSZFGMVMBRIOV2SJ5TLK75E37.json","view_paper":"https://pith.science/paper/2QSZFGMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18377&json=true","fetch_graph":"https://pith.science/api/pith-number/2QSZFGMVMBRIOV2SJ5TLK75E37/graph.json","fetch_events":"https://pith.science/api/pith-number/2QSZFGMVMBRIOV2SJ5TLK75E37/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2QSZFGMVMBRIOV2SJ5TLK75E37/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2QSZFGMVMBRIOV2SJ5TLK75E37/action/storage_attestation","attest_author":"https://pith.science/pith/2QSZFGMVMBRIOV2SJ5TLK75E37/action/author_attestation","sign_citation":"https://pith.science/pith/2QSZFGMVMBRIOV2SJ5TLK75E37/action/citation_signature","submit_replication":"https://pith.science/pith/2QSZFGMVMBRIOV2SJ5TLK75E37/action/replication_record"}},"created_at":"2026-07-05T08:24:19.507864+00:00","updated_at":"2026-07-05T08:24:19.507864+00:00"}