{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GGPSIDEL3LHVQSTFNUCESAVOWU","short_pith_number":"pith:GGPSIDEL","canonical_record":{"source":{"id":"2309.02411","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-05T17:40:34Z","cross_cats_sorted":[],"title_canon_sha256":"ad9b597275ad9761fcc629fdc0ce83fca21a1516f9d2c2d72ec8df14587d81f0","abstract_canon_sha256":"a55f911b9b1b87caccb863f27009d7a580849a534f7bd263ddcfc17c21c1383f"},"schema_version":"1.0"},"canonical_sha256":"319f240c8bdacf584a656d044902aeb5328edeb987bb92bd3fad643eedd1ca11","source":{"kind":"arxiv","id":"2309.02411","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.02411","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"arxiv_version","alias_value":"2309.02411v1","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02411","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"pith_short_12","alias_value":"GGPSIDEL3LHV","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"pith_short_16","alias_value":"GGPSIDEL3LHVQSTF","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"pith_short_8","alias_value":"GGPSIDEL","created_at":"2026-07-05T06:47:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GGPSIDEL3LHVQSTFNUCESAVOWU","target":"record","payload":{"canonical_record":{"source":{"id":"2309.02411","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-05T17:40:34Z","cross_cats_sorted":[],"title_canon_sha256":"ad9b597275ad9761fcc629fdc0ce83fca21a1516f9d2c2d72ec8df14587d81f0","abstract_canon_sha256":"a55f911b9b1b87caccb863f27009d7a580849a534f7bd263ddcfc17c21c1383f"},"schema_version":"1.0"},"canonical_sha256":"319f240c8bdacf584a656d044902aeb5328edeb987bb92bd3fad643eedd1ca11","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:59.884410Z","signature_b64":"4K902+8dLvjb2j2fJpf66dSrvK1wxQ033CSJHGk78+vnBZp7l/d1VBz9ZP7eXfu4bsgq1XOzZ7bFCzLJAjdDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"319f240c8bdacf584a656d044902aeb5328edeb987bb92bd3fad643eedd1ca11","last_reissued_at":"2026-07-05T06:47:59.883996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:59.883996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.02411","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:47:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OVOvsrDQr2SdfvpXFNHj3T9rx2zI/rUaWQ0jVzDtWugJUsq1CGektnpi+EFuZINctf78eskT0jkWPAVLZXStBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:20:12.461925Z"},"content_sha256":"4ee842c14b56666ba76592e007bbd58987342b59bae744b9291fbaa61fedac63","schema_version":"1.0","event_id":"sha256:4ee842c14b56666ba76592e007bbd58987342b59bae744b9291fbaa61fedac63"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GGPSIDEL3LHVQSTFNUCESAVOWU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Delta-LoRA: Fine-Tuning High-Rank Parameters with the Delta of Low-Rank Matrices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bojia Zi, Jianan Wang, Kam-Fai Wong, Lei Zhang, Lingzhi Wang, Xianbiao Qi","submitted_at":"2023-09-05T17:40:34Z","abstract_excerpt":"In this paper, we present Delta-LoRA, which is a novel parameter-efficient approach to fine-tune large language models (LLMs). In contrast to LoRA and other low-rank adaptation methods such as AdaLoRA, Delta-LoRA not only updates the low-rank matrices $\\bA$ and $\\bB$, but also propagate the learning to the pre-trained weights $\\bW$ via updates utilizing the delta of the product of two low-rank matrices ($\\bA^{(t+1)}\\bB^{(t+1)} - \\bA^{(t)}\\bB^{(t)}$). Such a strategy effectively addresses the limitation that the incremental update of low-rank matrices is inadequate for learning representations "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02411","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/2309.02411/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":"2026-07-05T06:47:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3582MnbyPWDhK+p/nASShhtbcs5+5kaezDlMgmJwJYpFzc2pnXekrWRuaPkJJPULRq2PPj9r+vwgvOgfkXsUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:20:12.462455Z"},"content_sha256":"a42e738b5229ab81d5b339368335ea33f03d645dbad82e33d498a121d899e25b","schema_version":"1.0","event_id":"sha256:a42e738b5229ab81d5b339368335ea33f03d645dbad82e33d498a121d899e25b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GGPSIDEL3LHVQSTFNUCESAVOWU/bundle.json","state_url":"https://pith.science/pith/GGPSIDEL3LHVQSTFNUCESAVOWU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GGPSIDEL3LHVQSTFNUCESAVOWU/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":"2026-08-04T12:20:12Z","links":{"resolver":"https://pith.science/pith/GGPSIDEL3LHVQSTFNUCESAVOWU","bundle":"https://pith.science/pith/GGPSIDEL3LHVQSTFNUCESAVOWU/bundle.json","state":"https://pith.science/pith/GGPSIDEL3LHVQSTFNUCESAVOWU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GGPSIDEL3LHVQSTFNUCESAVOWU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GGPSIDEL3LHVQSTFNUCESAVOWU","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":"a55f911b9b1b87caccb863f27009d7a580849a534f7bd263ddcfc17c21c1383f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-05T17:40:34Z","title_canon_sha256":"ad9b597275ad9761fcc629fdc0ce83fca21a1516f9d2c2d72ec8df14587d81f0"},"schema_version":"1.0","source":{"id":"2309.02411","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.02411","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"arxiv_version","alias_value":"2309.02411v1","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02411","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"pith_short_12","alias_value":"GGPSIDEL3LHV","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"pith_short_16","alias_value":"GGPSIDEL3LHVQSTF","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"pith_short_8","alias_value":"GGPSIDEL","created_at":"2026-07-05T06:47:59Z"}],"graph_snapshots":[{"event_id":"sha256:a42e738b5229ab81d5b339368335ea33f03d645dbad82e33d498a121d899e25b","target":"graph","created_at":"2026-07-05T06:47:59Z","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/2309.02411/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present Delta-LoRA, which is a novel parameter-efficient approach to fine-tune large language models (LLMs). In contrast to LoRA and other low-rank adaptation methods such as AdaLoRA, Delta-LoRA not only updates the low-rank matrices $\\bA$ and $\\bB$, but also propagate the learning to the pre-trained weights $\\bW$ via updates utilizing the delta of the product of two low-rank matrices ($\\bA^{(t+1)}\\bB^{(t+1)} - \\bA^{(t)}\\bB^{(t)}$). Such a strategy effectively addresses the limitation that the incremental update of low-rank matrices is inadequate for learning representations ","authors_text":"Bojia Zi, Jianan Wang, Kam-Fai Wong, Lei Zhang, Lingzhi Wang, Xianbiao Qi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-05T17:40:34Z","title":"Delta-LoRA: Fine-Tuning High-Rank Parameters with the Delta of Low-Rank Matrices"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02411","kind":"arxiv","version":1},"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":"sha256:4ee842c14b56666ba76592e007bbd58987342b59bae744b9291fbaa61fedac63","target":"record","created_at":"2026-07-05T06:47:59Z","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":"a55f911b9b1b87caccb863f27009d7a580849a534f7bd263ddcfc17c21c1383f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-05T17:40:34Z","title_canon_sha256":"ad9b597275ad9761fcc629fdc0ce83fca21a1516f9d2c2d72ec8df14587d81f0"},"schema_version":"1.0","source":{"id":"2309.02411","kind":"arxiv","version":1}},"canonical_sha256":"319f240c8bdacf584a656d044902aeb5328edeb987bb92bd3fad643eedd1ca11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"319f240c8bdacf584a656d044902aeb5328edeb987bb92bd3fad643eedd1ca11","first_computed_at":"2026-07-05T06:47:59.883996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:47:59.883996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4K902+8dLvjb2j2fJpf66dSrvK1wxQ033CSJHGk78+vnBZp7l/d1VBz9ZP7eXfu4bsgq1XOzZ7bFCzLJAjdDAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:47:59.884410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.02411","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ee842c14b56666ba76592e007bbd58987342b59bae744b9291fbaa61fedac63","sha256:a42e738b5229ab81d5b339368335ea33f03d645dbad82e33d498a121d899e25b"],"state_sha256":"24cdcf703d9014ce7d773d02553a845fdf692aae8d98d27883ebff7175e52d44"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Utym83HvDDp4haMMEA1b/85FiG0rEITQRyQQ5xlUoQboquNfQyTlZbsFyC16S5xIRxpxz2uSnweRezBlYXMwCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:20:12.466562Z","bundle_sha256":"985bedb8ce7f1e200df20e84bba4811474462aa45dde78cdbfe18822011ae6ad"}}