{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QRLTVU7ZECX2BYOEXONX7YELH6","short_pith_number":"pith:QRLTVU7Z","canonical_record":{"source":{"id":"2310.17513","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T16:08:33Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"0175515db0d4d0d31659bd23b17150ecc7f159b5995747b2cabddf8ad1174566","abstract_canon_sha256":"0badba7f391c4f445896617adbe3cfaa6d58887ed263b009b8da48f73f111150"},"schema_version":"1.0"},"canonical_sha256":"84573ad3f920afa0e1c4bb9b7fe08b3f963b620ecd06af949686ee452f438c72","source":{"kind":"arxiv","id":"2310.17513","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17513","created_at":"2026-07-05T07:56:55Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17513v3","created_at":"2026-07-05T07:56:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17513","created_at":"2026-07-05T07:56:55Z"},{"alias_kind":"pith_short_12","alias_value":"QRLTVU7ZECX2","created_at":"2026-07-05T07:56:55Z"},{"alias_kind":"pith_short_16","alias_value":"QRLTVU7ZECX2BYOE","created_at":"2026-07-05T07:56:55Z"},{"alias_kind":"pith_short_8","alias_value":"QRLTVU7Z","created_at":"2026-07-05T07:56:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QRLTVU7ZECX2BYOEXONX7YELH6","target":"record","payload":{"canonical_record":{"source":{"id":"2310.17513","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T16:08:33Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"0175515db0d4d0d31659bd23b17150ecc7f159b5995747b2cabddf8ad1174566","abstract_canon_sha256":"0badba7f391c4f445896617adbe3cfaa6d58887ed263b009b8da48f73f111150"},"schema_version":"1.0"},"canonical_sha256":"84573ad3f920afa0e1c4bb9b7fe08b3f963b620ecd06af949686ee452f438c72","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:55.592738Z","signature_b64":"dOWxa7ZQE2blZQgt6UKijqbkLCiEACZdNJO/5PyN49Nl3Vjnj8O84Ar3HzksAeI1EeejbjsAQsy12m+d2eN1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84573ad3f920afa0e1c4bb9b7fe08b3f963b620ecd06af949686ee452f438c72","last_reissued_at":"2026-07-05T07:56:55.592266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:55.592266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.17513","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:56:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PrLrBhVjy+qVIXBVCPdkrG91zRH+X6VaZifLT819mxDvL61b/WtWoA2IbGcVJvhNlUiisOPkSadVb/KBtY4dAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:38:04.693811Z"},"content_sha256":"378dd45c66b4a87de563443904898521cff7b6bfb1214ff54daccccc466a3bc3","schema_version":"1.0","event_id":"sha256:378dd45c66b4a87de563443904898521cff7b6bfb1214ff54daccccc466a3bc3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QRLTVU7ZECX2BYOEXONX7YELH6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Expressive Power of Low-Rank Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kangwook Lee, Yuchen Zeng","submitted_at":"2023-10-26T16:08:33Z","abstract_excerpt":"Low-Rank Adaptation (LoRA), a parameter-efficient fine-tuning method that leverages low-rank adaptation of weight matrices, has emerged as a prevalent technique for fine-tuning pre-trained models such as large language models and diffusion models. Despite its huge success in practice, the theoretical underpinnings of LoRA have largely remained unexplored. This paper takes the first step to bridge this gap by theoretically analyzing the expressive power of LoRA. We prove that, for fully connected neural networks, LoRA can adapt any model $f$ to accurately represent any smaller target model $\\ov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17513","kind":"arxiv","version":3},"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/2310.17513/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:56:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PC+4OdL0+z+o/vErew7mYdpR+O8CgnZl0JNFyK1Ly/3sZKHBAcJ7opad+q80Bm2KF5JgLq3LMgNdEkRZdLBSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:38:04.694747Z"},"content_sha256":"1c00834e01bfec89999bfbeed1d06eb793cb1ac282787f9c6080de091604a80a","schema_version":"1.0","event_id":"sha256:1c00834e01bfec89999bfbeed1d06eb793cb1ac282787f9c6080de091604a80a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QRLTVU7ZECX2BYOEXONX7YELH6/bundle.json","state_url":"https://pith.science/pith/QRLTVU7ZECX2BYOEXONX7YELH6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QRLTVU7ZECX2BYOEXONX7YELH6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T02:38:04Z","links":{"resolver":"https://pith.science/pith/QRLTVU7ZECX2BYOEXONX7YELH6","bundle":"https://pith.science/pith/QRLTVU7ZECX2BYOEXONX7YELH6/bundle.json","state":"https://pith.science/pith/QRLTVU7ZECX2BYOEXONX7YELH6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QRLTVU7ZECX2BYOEXONX7YELH6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QRLTVU7ZECX2BYOEXONX7YELH6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0badba7f391c4f445896617adbe3cfaa6d58887ed263b009b8da48f73f111150","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T16:08:33Z","title_canon_sha256":"0175515db0d4d0d31659bd23b17150ecc7f159b5995747b2cabddf8ad1174566"},"schema_version":"1.0","source":{"id":"2310.17513","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17513","created_at":"2026-07-05T07:56:55Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17513v3","created_at":"2026-07-05T07:56:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17513","created_at":"2026-07-05T07:56:55Z"},{"alias_kind":"pith_short_12","alias_value":"QRLTVU7ZECX2","created_at":"2026-07-05T07:56:55Z"},{"alias_kind":"pith_short_16","alias_value":"QRLTVU7ZECX2BYOE","created_at":"2026-07-05T07:56:55Z"},{"alias_kind":"pith_short_8","alias_value":"QRLTVU7Z","created_at":"2026-07-05T07:56:55Z"}],"graph_snapshots":[{"event_id":"sha256:1c00834e01bfec89999bfbeed1d06eb793cb1ac282787f9c6080de091604a80a","target":"graph","created_at":"2026-07-05T07:56:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.17513/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Low-Rank Adaptation (LoRA), a parameter-efficient fine-tuning method that leverages low-rank adaptation of weight matrices, has emerged as a prevalent technique for fine-tuning pre-trained models such as large language models and diffusion models. Despite its huge success in practice, the theoretical underpinnings of LoRA have largely remained unexplored. This paper takes the first step to bridge this gap by theoretically analyzing the expressive power of LoRA. We prove that, for fully connected neural networks, LoRA can adapt any model $f$ to accurately represent any smaller target model $\\ov","authors_text":"Kangwook Lee, Yuchen Zeng","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T16:08:33Z","title":"The Expressive Power of Low-Rank Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17513","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:378dd45c66b4a87de563443904898521cff7b6bfb1214ff54daccccc466a3bc3","target":"record","created_at":"2026-07-05T07:56:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0badba7f391c4f445896617adbe3cfaa6d58887ed263b009b8da48f73f111150","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T16:08:33Z","title_canon_sha256":"0175515db0d4d0d31659bd23b17150ecc7f159b5995747b2cabddf8ad1174566"},"schema_version":"1.0","source":{"id":"2310.17513","kind":"arxiv","version":3}},"canonical_sha256":"84573ad3f920afa0e1c4bb9b7fe08b3f963b620ecd06af949686ee452f438c72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84573ad3f920afa0e1c4bb9b7fe08b3f963b620ecd06af949686ee452f438c72","first_computed_at":"2026-07-05T07:56:55.592266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:55.592266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dOWxa7ZQE2blZQgt6UKijqbkLCiEACZdNJO/5PyN49Nl3Vjnj8O84Ar3HzksAeI1EeejbjsAQsy12m+d2eN1Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:55.592738Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.17513","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:378dd45c66b4a87de563443904898521cff7b6bfb1214ff54daccccc466a3bc3","sha256:1c00834e01bfec89999bfbeed1d06eb793cb1ac282787f9c6080de091604a80a"],"state_sha256":"0511c3be5e8dcedf104b37ac1b8b0d74023afbd8c32aaa9dae56b19937169e80"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bH9u+TE5jcT/hetamKi1+grN88tvclwQChifbXt4dewE6wJkIAZi8U4OTcwWXW+oJQKoAYELU+5NJwT0ubgFBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:38:04.703889Z","bundle_sha256":"e548391e66dc1d004790c34b6d92ff538ccc8669e149d8ac141af7d7893110de"}}