{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:25432O6XVOFBGNWJNCGN4X5GVT","short_pith_number":"pith:25432O6X","canonical_record":{"source":{"id":"2408.03290","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-06T16:39:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"3ae9f99467846c913f2f80bebbc9812aea8a5097b98cbd5fcc70ea99b93ef4ce","abstract_canon_sha256":"083014ceef77c488aed675663f7e73a666b0a1ef6c5b2ed1ccdb5e4ebee10d5d"},"schema_version":"1.0"},"canonical_sha256":"d779bd3bd7ab8a1336c9688cde5fa6acecee271749b2192db1b7295a20c9f6dd","source":{"kind":"arxiv","id":"2408.03290","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.03290","created_at":"2026-07-05T08:52:48Z"},{"alias_kind":"arxiv_version","alias_value":"2408.03290v1","created_at":"2026-07-05T08:52:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03290","created_at":"2026-07-05T08:52:48Z"},{"alias_kind":"pith_short_12","alias_value":"25432O6XVOFB","created_at":"2026-07-05T08:52:48Z"},{"alias_kind":"pith_short_16","alias_value":"25432O6XVOFBGNWJ","created_at":"2026-07-05T08:52:48Z"},{"alias_kind":"pith_short_8","alias_value":"25432O6X","created_at":"2026-07-05T08:52:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:25432O6XVOFBGNWJNCGN4X5GVT","target":"record","payload":{"canonical_record":{"source":{"id":"2408.03290","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-06T16:39:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"3ae9f99467846c913f2f80bebbc9812aea8a5097b98cbd5fcc70ea99b93ef4ce","abstract_canon_sha256":"083014ceef77c488aed675663f7e73a666b0a1ef6c5b2ed1ccdb5e4ebee10d5d"},"schema_version":"1.0"},"canonical_sha256":"d779bd3bd7ab8a1336c9688cde5fa6acecee271749b2192db1b7295a20c9f6dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:48.555926Z","signature_b64":"xuaJ+ZabyBB/HeDdGDf6NjU+LpWx86dyAqVirXo6VOjrumq4pB8OjimfJ9MA5ASMuhXBycQnhQy9e7PbYykVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d779bd3bd7ab8a1336c9688cde5fa6acecee271749b2192db1b7295a20c9f6dd","last_reissued_at":"2026-07-05T08:52:48.555543Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:48.555543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.03290","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":"2026-07-05T08:52:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ru4Rzx/YksOufGirxulO1soGkzPHi4VA2vOIAw5dCUoFTXGRSU80tFWoIr+cgQ/5aOzo6TkCBGKE3q7Nza/QBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:10:27.646400Z"},"content_sha256":"03ef79f337b666f220ba3572f4d265ecd973a88b1b9691b441fddcdc07a8aa52","schema_version":"1.0","event_id":"sha256:03ef79f337b666f220ba3572f4d265ecd973a88b1b9691b441fddcdc07a8aa52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:25432O6XVOFBGNWJNCGN4X5GVT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SARA: Singular-Value Based Adaptive Low-Rank Adaption","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Jihao Gu, Ping Gong, Shuai Chen, Yibo Zhang, Zelin Wang","submitted_at":"2024-08-06T16:39:42Z","abstract_excerpt":"With the increasing number of parameters in large pre-trained models, LoRA as a parameter-efficient fine-tuning(PEFT) method is widely used for not adding inference overhead. The LoRA method assumes that weight changes during fine-tuning can be approximated by low-rank matrices. However, the rank values need to be manually verified to match different downstream tasks, and they cannot accommodate the varying importance of different layers in the model. In this work, we first analyze the relationship between the performance of different layers and their ranks using SVD. Based on this, we design "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03290","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/2408.03290/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":"2026-07-05T08:52:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0R56r8gdXejqdb+lsdTsmc0aCHeh4LghtZKmP7RhgH8SpvurDUTQMrXac8oyG7ezIZf9vdc/tJCR8B+vxFfvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:10:27.646978Z"},"content_sha256":"b5d918510b2dcbbd330aa9d6b5ce6fd2846b1ac00ec830aa6837a332b6923373","schema_version":"1.0","event_id":"sha256:b5d918510b2dcbbd330aa9d6b5ce6fd2846b1ac00ec830aa6837a332b6923373"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/25432O6XVOFBGNWJNCGN4X5GVT/bundle.json","state_url":"https://pith.science/pith/25432O6XVOFBGNWJNCGN4X5GVT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/25432O6XVOFBGNWJNCGN4X5GVT/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":"2026-08-07T01:10:27Z","links":{"resolver":"https://pith.science/pith/25432O6XVOFBGNWJNCGN4X5GVT","bundle":"https://pith.science/pith/25432O6XVOFBGNWJNCGN4X5GVT/bundle.json","state":"https://pith.science/pith/25432O6XVOFBGNWJNCGN4X5GVT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/25432O6XVOFBGNWJNCGN4X5GVT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:25432O6XVOFBGNWJNCGN4X5GVT","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":"083014ceef77c488aed675663f7e73a666b0a1ef6c5b2ed1ccdb5e4ebee10d5d","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-06T16:39:42Z","title_canon_sha256":"3ae9f99467846c913f2f80bebbc9812aea8a5097b98cbd5fcc70ea99b93ef4ce"},"schema_version":"1.0","source":{"id":"2408.03290","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.03290","created_at":"2026-07-05T08:52:48Z"},{"alias_kind":"arxiv_version","alias_value":"2408.03290v1","created_at":"2026-07-05T08:52:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03290","created_at":"2026-07-05T08:52:48Z"},{"alias_kind":"pith_short_12","alias_value":"25432O6XVOFB","created_at":"2026-07-05T08:52:48Z"},{"alias_kind":"pith_short_16","alias_value":"25432O6XVOFBGNWJ","created_at":"2026-07-05T08:52:48Z"},{"alias_kind":"pith_short_8","alias_value":"25432O6X","created_at":"2026-07-05T08:52:48Z"}],"graph_snapshots":[{"event_id":"sha256:b5d918510b2dcbbd330aa9d6b5ce6fd2846b1ac00ec830aa6837a332b6923373","target":"graph","created_at":"2026-07-05T08:52:48Z","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/2408.03290/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the increasing number of parameters in large pre-trained models, LoRA as a parameter-efficient fine-tuning(PEFT) method is widely used for not adding inference overhead. The LoRA method assumes that weight changes during fine-tuning can be approximated by low-rank matrices. However, the rank values need to be manually verified to match different downstream tasks, and they cannot accommodate the varying importance of different layers in the model. In this work, we first analyze the relationship between the performance of different layers and their ranks using SVD. Based on this, we design ","authors_text":"Jihao Gu, Ping Gong, Shuai Chen, Yibo Zhang, Zelin Wang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-06T16:39:42Z","title":"SARA: Singular-Value Based Adaptive Low-Rank Adaption"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03290","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":"sha256:03ef79f337b666f220ba3572f4d265ecd973a88b1b9691b441fddcdc07a8aa52","target":"record","created_at":"2026-07-05T08:52:48Z","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":"083014ceef77c488aed675663f7e73a666b0a1ef6c5b2ed1ccdb5e4ebee10d5d","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-06T16:39:42Z","title_canon_sha256":"3ae9f99467846c913f2f80bebbc9812aea8a5097b98cbd5fcc70ea99b93ef4ce"},"schema_version":"1.0","source":{"id":"2408.03290","kind":"arxiv","version":1}},"canonical_sha256":"d779bd3bd7ab8a1336c9688cde5fa6acecee271749b2192db1b7295a20c9f6dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d779bd3bd7ab8a1336c9688cde5fa6acecee271749b2192db1b7295a20c9f6dd","first_computed_at":"2026-07-05T08:52:48.555543Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:52:48.555543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xuaJ+ZabyBB/HeDdGDf6NjU+LpWx86dyAqVirXo6VOjrumq4pB8OjimfJ9MA5ASMuhXBycQnhQy9e7PbYykVDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:52:48.555926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.03290","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03ef79f337b666f220ba3572f4d265ecd973a88b1b9691b441fddcdc07a8aa52","sha256:b5d918510b2dcbbd330aa9d6b5ce6fd2846b1ac00ec830aa6837a332b6923373"],"state_sha256":"8cd8761ab3e3df0cd812253fb15a31d04ba7f8fba5dfef05cdfc83a597e61bbc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XjirBKnpgoKhFj3LssW/d2CVSTdqeGS2xmS0UCdAS1vtb5HB2h8jbO2L8Z9cE8c74/S1Dfb1p2XsU2QZdhoLCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:10:27.652540Z","bundle_sha256":"c78a228c821368ef15544fd6e558cafc69732ae5a5c7b3c9717a605bed71a19a"}}