{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TRLOC43EYUDM7MKEFERJAG3JNO","short_pith_number":"pith:TRLOC43E","schema_version":"1.0","canonical_sha256":"9c56e17364c506cfb1442922901b696bbea27d978b149a58d25e6abbd423928b","source":{"kind":"arxiv","id":"2403.17919","version":4},"attestation_state":"computed","paper":{"title":"LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","math.OC"],"primary_cat":"cs.LG","authors_text":"Chi Han, Jipeng Zhang, Renjie Pi, Rui Pan, Shizhe Diao, Tong Zhang, Xiang Liu","submitted_at":"2024-03-26T17:55:02Z","abstract_excerpt":"The machine learning community has witnessed impressive advancements since large language models (LLMs) first appeared. Yet, their massive memory consumption has become a significant roadblock to large-scale training. For instance, a 7B model typically requires at least 60 GB of GPU memory with full parameter training, which presents challenges for researchers without access to high-resource environments. Parameter Efficient Fine-Tuning techniques such as Low-Rank Adaptation (LoRA) have been proposed to alleviate this problem. However, in most large-scale fine-tuning settings, their performanc"},"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":"2403.17919","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-26T17:55:02Z","cross_cats_sorted":["cs.AI","cs.CL","math.OC"],"title_canon_sha256":"4022abfc377f7fa11e0aeb80f69ab964f8a0bbd419895f501a31ce001ee91122","abstract_canon_sha256":"6c00e97647e57fb852266968c5a6918f43bc0ba6a7b154559ba77a4cebca368e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:01.419691Z","signature_b64":"S0DedBSniLO+E47nWP6hnSFudKMmrXdKM/ZN2OQBsPyTNQ4c3AqFXsMv9Lbldvw1xDNFDsLBmPzMyrpvsPRFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c56e17364c506cfb1442922901b696bbea27d978b149a58d25e6abbd423928b","last_reissued_at":"2026-07-05T09:54:01.419202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:01.419202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","math.OC"],"primary_cat":"cs.LG","authors_text":"Chi Han, Jipeng Zhang, Renjie Pi, Rui Pan, Shizhe Diao, Tong Zhang, Xiang Liu","submitted_at":"2024-03-26T17:55:02Z","abstract_excerpt":"The machine learning community has witnessed impressive advancements since large language models (LLMs) first appeared. Yet, their massive memory consumption has become a significant roadblock to large-scale training. For instance, a 7B model typically requires at least 60 GB of GPU memory with full parameter training, which presents challenges for researchers without access to high-resource environments. Parameter Efficient Fine-Tuning techniques such as Low-Rank Adaptation (LoRA) have been proposed to alleviate this problem. However, in most large-scale fine-tuning settings, their performanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17919","kind":"arxiv","version":4},"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/2403.17919/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":"2403.17919","created_at":"2026-07-05T09:54:01.419267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.17919v4","created_at":"2026-07-05T09:54:01.419267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17919","created_at":"2026-07-05T09:54:01.419267+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRLOC43EYUDM","created_at":"2026-07-05T09:54:01.419267+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRLOC43EYUDM7MKE","created_at":"2026-07-05T09:54:01.419267+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRLOC43E","created_at":"2026-07-05T09:54:01.419267+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08783","citing_title":"OptMuon: Closed-Loop Orthogonalized Momentum Methods for Stochastic Optimization with Zero-Noise Optimality","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08783","citing_title":"OptMuon: Closed-Loop Orthogonalized Momentum Methods for Stochastic Optimization with Zero-Noise Optimality","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12207","citing_title":"Not How Many, But Which: Parameter Placement in Low-Rank Adaptation","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27487","citing_title":"Low Rank Adaptation for Adversarial Perturbation","ref_index":86,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TRLOC43EYUDM7MKEFERJAG3JNO","json":"https://pith.science/pith/TRLOC43EYUDM7MKEFERJAG3JNO.json","graph_json":"https://pith.science/api/pith-number/TRLOC43EYUDM7MKEFERJAG3JNO/graph.json","events_json":"https://pith.science/api/pith-number/TRLOC43EYUDM7MKEFERJAG3JNO/events.json","paper":"https://pith.science/paper/TRLOC43E"},"agent_actions":{"view_html":"https://pith.science/pith/TRLOC43EYUDM7MKEFERJAG3JNO","download_json":"https://pith.science/pith/TRLOC43EYUDM7MKEFERJAG3JNO.json","view_paper":"https://pith.science/paper/TRLOC43E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.17919&json=true","fetch_graph":"https://pith.science/api/pith-number/TRLOC43EYUDM7MKEFERJAG3JNO/graph.json","fetch_events":"https://pith.science/api/pith-number/TRLOC43EYUDM7MKEFERJAG3JNO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRLOC43EYUDM7MKEFERJAG3JNO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRLOC43EYUDM7MKEFERJAG3JNO/action/storage_attestation","attest_author":"https://pith.science/pith/TRLOC43EYUDM7MKEFERJAG3JNO/action/author_attestation","sign_citation":"https://pith.science/pith/TRLOC43EYUDM7MKEFERJAG3JNO/action/citation_signature","submit_replication":"https://pith.science/pith/TRLOC43EYUDM7MKEFERJAG3JNO/action/replication_record"}},"created_at":"2026-07-05T09:54:01.419267+00:00","updated_at":"2026-07-05T09:54:01.419267+00:00"}