{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IILT5BTCZUFFLWP6HEANZQGCFX","short_pith_number":"pith:IILT5BTC","canonical_record":{"source":{"id":"2410.13618","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T14:51:17Z","cross_cats_sorted":[],"title_canon_sha256":"a317a0ae6ffb6d7062bc072e466ac3776731dbb06a195daaa331309c0041b93a","abstract_canon_sha256":"99a92284f130510b2729599e028a6d1921ef149f8ad178cc40d7b0a078b5f8ec"},"schema_version":"1.0"},"canonical_sha256":"42173e8662cd0a55d9fe3900dcc0c22dc71916a7a5a077e5501544499afa0219","source":{"kind":"arxiv","id":"2410.13618","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13618","created_at":"2026-07-05T09:22:03Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13618v1","created_at":"2026-07-05T09:22:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13618","created_at":"2026-07-05T09:22:03Z"},{"alias_kind":"pith_short_12","alias_value":"IILT5BTCZUFF","created_at":"2026-07-05T09:22:03Z"},{"alias_kind":"pith_short_16","alias_value":"IILT5BTCZUFFLWP6","created_at":"2026-07-05T09:22:03Z"},{"alias_kind":"pith_short_8","alias_value":"IILT5BTC","created_at":"2026-07-05T09:22:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IILT5BTCZUFFLWP6HEANZQGCFX","target":"record","payload":{"canonical_record":{"source":{"id":"2410.13618","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T14:51:17Z","cross_cats_sorted":[],"title_canon_sha256":"a317a0ae6ffb6d7062bc072e466ac3776731dbb06a195daaa331309c0041b93a","abstract_canon_sha256":"99a92284f130510b2729599e028a6d1921ef149f8ad178cc40d7b0a078b5f8ec"},"schema_version":"1.0"},"canonical_sha256":"42173e8662cd0a55d9fe3900dcc0c22dc71916a7a5a077e5501544499afa0219","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:03.725860Z","signature_b64":"Zkv7ZlnCJXyRphOmVFbTVXXKQ1rBG6DWBr2Adrd/Csm+6ll5+Rib5O4Pnruo0TEgkxAQRJJleLwOD3onYNg5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42173e8662cd0a55d9fe3900dcc0c22dc71916a7a5a077e5501544499afa0219","last_reissued_at":"2026-07-05T09:22:03.725463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:03.725463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.13618","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":"2026-07-05T09:22:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Xupl6g6L4i/VaCu1qx/EByXEi4RUUOEB8YY0rE9IcEbMYx2TrkW7g4Y7ovI99eYhVWc1BgtKQC7hFa12HZBDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T06:45:24.504368Z"},"content_sha256":"aec76e204b2cb455b6fd85a5d00a51e0acf43e2df7da39ace9fac41357bd9ed6","schema_version":"1.0","event_id":"sha256:aec76e204b2cb455b6fd85a5d00a51e0acf43e2df7da39ace9fac41357bd9ed6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IILT5BTCZUFFLWP6HEANZQGCFX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengwei Sun, Jiwei Wei, Ran Ran, Shiyuan He, Yang Yang, Yiming Shi, Yujia Wu","submitted_at":"2024-10-17T14:51:17Z","abstract_excerpt":"The rapid growth of model scale has necessitated substantial computational resources for fine-tuning. Existing approach such as Low-Rank Adaptation (LoRA) has sought to address the problem of handling the large updated parameters in full fine-tuning. However, LoRA utilize random initialization and optimization of low-rank matrices to approximate updated weights, which can result in suboptimal convergence and an accuracy gap compared to full fine-tuning. To address these issues, we propose LoLDU, a Parameter-Efficient Fine-Tuning (PEFT) approach that significantly reduces trainable parameters b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13618","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/2410.13618/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":"2026-07-05T09:22:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XuYomecSDRaMMSkWmmmTWs7XmSq8IRjAG3vYB0pHO1rDrql+eeoCyJSnldpSK+SkCt0wTY8Yh3Vf8yJH0Gb2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T06:45:24.505263Z"},"content_sha256":"9d5f38ef1f638ad5626caa5a39a6dea07cf1b23da6f174205da9d1252f352509","schema_version":"1.0","event_id":"sha256:9d5f38ef1f638ad5626caa5a39a6dea07cf1b23da6f174205da9d1252f352509"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IILT5BTCZUFFLWP6HEANZQGCFX/bundle.json","state_url":"https://pith.science/pith/IILT5BTCZUFFLWP6HEANZQGCFX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IILT5BTCZUFFLWP6HEANZQGCFX/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":"2026-08-01T06:45:24Z","links":{"resolver":"https://pith.science/pith/IILT5BTCZUFFLWP6HEANZQGCFX","bundle":"https://pith.science/pith/IILT5BTCZUFFLWP6HEANZQGCFX/bundle.json","state":"https://pith.science/pith/IILT5BTCZUFFLWP6HEANZQGCFX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IILT5BTCZUFFLWP6HEANZQGCFX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IILT5BTCZUFFLWP6HEANZQGCFX","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":"99a92284f130510b2729599e028a6d1921ef149f8ad178cc40d7b0a078b5f8ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T14:51:17Z","title_canon_sha256":"a317a0ae6ffb6d7062bc072e466ac3776731dbb06a195daaa331309c0041b93a"},"schema_version":"1.0","source":{"id":"2410.13618","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13618","created_at":"2026-07-05T09:22:03Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13618v1","created_at":"2026-07-05T09:22:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13618","created_at":"2026-07-05T09:22:03Z"},{"alias_kind":"pith_short_12","alias_value":"IILT5BTCZUFF","created_at":"2026-07-05T09:22:03Z"},{"alias_kind":"pith_short_16","alias_value":"IILT5BTCZUFFLWP6","created_at":"2026-07-05T09:22:03Z"},{"alias_kind":"pith_short_8","alias_value":"IILT5BTC","created_at":"2026-07-05T09:22:03Z"}],"graph_snapshots":[{"event_id":"sha256:9d5f38ef1f638ad5626caa5a39a6dea07cf1b23da6f174205da9d1252f352509","target":"graph","created_at":"2026-07-05T09:22:03Z","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/2410.13618/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid growth of model scale has necessitated substantial computational resources for fine-tuning. Existing approach such as Low-Rank Adaptation (LoRA) has sought to address the problem of handling the large updated parameters in full fine-tuning. However, LoRA utilize random initialization and optimization of low-rank matrices to approximate updated weights, which can result in suboptimal convergence and an accuracy gap compared to full fine-tuning. To address these issues, we propose LoLDU, a Parameter-Efficient Fine-Tuning (PEFT) approach that significantly reduces trainable parameters b","authors_text":"Chengwei Sun, Jiwei Wei, Ran Ran, Shiyuan He, Yang Yang, Yiming Shi, Yujia Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T14:51:17Z","title":"LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13618","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:aec76e204b2cb455b6fd85a5d00a51e0acf43e2df7da39ace9fac41357bd9ed6","target":"record","created_at":"2026-07-05T09:22:03Z","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":"99a92284f130510b2729599e028a6d1921ef149f8ad178cc40d7b0a078b5f8ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T14:51:17Z","title_canon_sha256":"a317a0ae6ffb6d7062bc072e466ac3776731dbb06a195daaa331309c0041b93a"},"schema_version":"1.0","source":{"id":"2410.13618","kind":"arxiv","version":1}},"canonical_sha256":"42173e8662cd0a55d9fe3900dcc0c22dc71916a7a5a077e5501544499afa0219","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42173e8662cd0a55d9fe3900dcc0c22dc71916a7a5a077e5501544499afa0219","first_computed_at":"2026-07-05T09:22:03.725463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:03.725463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zkv7ZlnCJXyRphOmVFbTVXXKQ1rBG6DWBr2Adrd/Csm+6ll5+Rib5O4Pnruo0TEgkxAQRJJleLwOD3onYNg5DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:03.725860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13618","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aec76e204b2cb455b6fd85a5d00a51e0acf43e2df7da39ace9fac41357bd9ed6","sha256:9d5f38ef1f638ad5626caa5a39a6dea07cf1b23da6f174205da9d1252f352509"],"state_sha256":"a57c2c62c48f798db9f128853e4f172dadf56e1d56cb1eb901e0698da89db3ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PXcHQSCgB+RzBr9d7ENBBJxySgx5PqPkfEOjZLX+OBgZLMxZjVg/60BwUzNJaH0asT7HB2M42RQAPqugl+cGAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T06:45:24.512106Z","bundle_sha256":"6268cc8331a7a50d103d8941f8740c1671fcb877a27a34fbb1d03d987b6c581d"}}