{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7NJBZ7TEIQYGTAE6JANE6EMEKV","short_pith_number":"pith:7NJBZ7TE","canonical_record":{"source":{"id":"2410.09758","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T07:28:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"82ef0c829cd4e1f02000ab639337e248ccc563001c643f32f745ea1a67cdd71e","abstract_canon_sha256":"9977a64001db852b85db5c7d8fb81e3dd75cb378778f5536eb6850013e514253"},"schema_version":"1.0"},"canonical_sha256":"fb521cfe64443069809e481a4f1184555e13540436858035bf5c7dade4618f3b","source":{"kind":"arxiv","id":"2410.09758","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09758","created_at":"2026-07-05T11:47:14Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09758v2","created_at":"2026-07-05T11:47:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09758","created_at":"2026-07-05T11:47:14Z"},{"alias_kind":"pith_short_12","alias_value":"7NJBZ7TEIQYG","created_at":"2026-07-05T11:47:14Z"},{"alias_kind":"pith_short_16","alias_value":"7NJBZ7TEIQYGTAE6","created_at":"2026-07-05T11:47:14Z"},{"alias_kind":"pith_short_8","alias_value":"7NJBZ7TE","created_at":"2026-07-05T11:47:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7NJBZ7TEIQYGTAE6JANE6EMEKV","target":"record","payload":{"canonical_record":{"source":{"id":"2410.09758","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T07:28:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"82ef0c829cd4e1f02000ab639337e248ccc563001c643f32f745ea1a67cdd71e","abstract_canon_sha256":"9977a64001db852b85db5c7d8fb81e3dd75cb378778f5536eb6850013e514253"},"schema_version":"1.0"},"canonical_sha256":"fb521cfe64443069809e481a4f1184555e13540436858035bf5c7dade4618f3b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:14.783982Z","signature_b64":"N4qJp+V1khpt4XqNxxIySRZ1jp8pHkOqhKYwIC8PnfObbpYsbYQK7TSvSsFOtT3exm6FJX4kn6uq1O7+xIxpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb521cfe64443069809e481a4f1184555e13540436858035bf5c7dade4618f3b","last_reissued_at":"2026-07-05T11:47:14.783329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:14.783329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.09758","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:47:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aOnzSOtwsLrUVL86upeyV8QZwq/mEQp5yr7Q/kUQwd75ZoZXB+Eb8Ds0QogTWuCFlUtUAKjbYKZd1KHvrDmABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T20:59:52.063118Z"},"content_sha256":"1a1238a9b46bb65e037f739436250b527a2332c58f1b03b200a6a70df0d10b93","schema_version":"1.0","event_id":"sha256:1a1238a9b46bb65e037f739436250b527a2332c58f1b03b200a6a70df0d10b93"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7NJBZ7TEIQYGTAE6JANE6EMEKV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BiDoRA: Bi-level Optimization-Based Weight-Decomposed Low-Rank Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Peijia Qin, Pengtao Xie, Ruiyi Zhang","submitted_at":"2024-10-13T07:28:26Z","abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) is a flexible and efficient method for adapting large language models (LLMs) to downstream tasks. Among these methods, weight-decomposed low-rank adaptation (DoRA) is a promising approach that decomposes weight matrices into magnitude and direction components to mimic full fine-tuning (FT) better. However, DoRA's simultaneous optimization of these components makes it over-expressive, increases the risk of overfitting, and creates a coupled updating pattern that limits its learning capacity. To address these issues, we propose Bi-level Optimization-Based W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09758","kind":"arxiv","version":2},"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/2410.09758/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":"2026-07-05T11:47:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hXt5v5hQ0PUWC48rZarLV3+LwESSgCkkiq4NYXWA9+fQiXRIp1khYCjpwY+HwLDqEdgkN08+PdkFyjmIIJPQAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T20:59:52.063666Z"},"content_sha256":"05b8bb564c529ae086e1391c2cc6552e45524b9661725945d5cdd34f7eadeb81","schema_version":"1.0","event_id":"sha256:05b8bb564c529ae086e1391c2cc6552e45524b9661725945d5cdd34f7eadeb81"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7NJBZ7TEIQYGTAE6JANE6EMEKV/bundle.json","state_url":"https://pith.science/pith/7NJBZ7TEIQYGTAE6JANE6EMEKV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7NJBZ7TEIQYGTAE6JANE6EMEKV/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":"2026-08-15T20:59:52Z","links":{"resolver":"https://pith.science/pith/7NJBZ7TEIQYGTAE6JANE6EMEKV","bundle":"https://pith.science/pith/7NJBZ7TEIQYGTAE6JANE6EMEKV/bundle.json","state":"https://pith.science/pith/7NJBZ7TEIQYGTAE6JANE6EMEKV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7NJBZ7TEIQYGTAE6JANE6EMEKV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7NJBZ7TEIQYGTAE6JANE6EMEKV","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":"9977a64001db852b85db5c7d8fb81e3dd75cb378778f5536eb6850013e514253","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T07:28:26Z","title_canon_sha256":"82ef0c829cd4e1f02000ab639337e248ccc563001c643f32f745ea1a67cdd71e"},"schema_version":"1.0","source":{"id":"2410.09758","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09758","created_at":"2026-07-05T11:47:14Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09758v2","created_at":"2026-07-05T11:47:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09758","created_at":"2026-07-05T11:47:14Z"},{"alias_kind":"pith_short_12","alias_value":"7NJBZ7TEIQYG","created_at":"2026-07-05T11:47:14Z"},{"alias_kind":"pith_short_16","alias_value":"7NJBZ7TEIQYGTAE6","created_at":"2026-07-05T11:47:14Z"},{"alias_kind":"pith_short_8","alias_value":"7NJBZ7TE","created_at":"2026-07-05T11:47:14Z"}],"graph_snapshots":[{"event_id":"sha256:05b8bb564c529ae086e1391c2cc6552e45524b9661725945d5cdd34f7eadeb81","target":"graph","created_at":"2026-07-05T11:47:14Z","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/2410.09758/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) is a flexible and efficient method for adapting large language models (LLMs) to downstream tasks. Among these methods, weight-decomposed low-rank adaptation (DoRA) is a promising approach that decomposes weight matrices into magnitude and direction components to mimic full fine-tuning (FT) better. However, DoRA's simultaneous optimization of these components makes it over-expressive, increases the risk of overfitting, and creates a coupled updating pattern that limits its learning capacity. To address these issues, we propose Bi-level Optimization-Based W","authors_text":"Peijia Qin, Pengtao Xie, Ruiyi Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T07:28:26Z","title":"BiDoRA: Bi-level Optimization-Based Weight-Decomposed Low-Rank Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09758","kind":"arxiv","version":2},"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":"sha256:1a1238a9b46bb65e037f739436250b527a2332c58f1b03b200a6a70df0d10b93","target":"record","created_at":"2026-07-05T11:47:14Z","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":"9977a64001db852b85db5c7d8fb81e3dd75cb378778f5536eb6850013e514253","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T07:28:26Z","title_canon_sha256":"82ef0c829cd4e1f02000ab639337e248ccc563001c643f32f745ea1a67cdd71e"},"schema_version":"1.0","source":{"id":"2410.09758","kind":"arxiv","version":2}},"canonical_sha256":"fb521cfe64443069809e481a4f1184555e13540436858035bf5c7dade4618f3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb521cfe64443069809e481a4f1184555e13540436858035bf5c7dade4618f3b","first_computed_at":"2026-07-05T11:47:14.783329Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:14.783329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N4qJp+V1khpt4XqNxxIySRZ1jp8pHkOqhKYwIC8PnfObbpYsbYQK7TSvSsFOtT3exm6FJX4kn6uq1O7+xIxpCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:14.783982Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.09758","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a1238a9b46bb65e037f739436250b527a2332c58f1b03b200a6a70df0d10b93","sha256:05b8bb564c529ae086e1391c2cc6552e45524b9661725945d5cdd34f7eadeb81"],"state_sha256":"31e12548f48b462ff198d46bfbdfd1641bbda5940967d45ab2d6c4cf49f95a7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w6HculyR2UDZ+gpGQK9mx/+sT8U0FnQrlCRSAe7N3Gfnvu9Jv+Fn6hMRWKkK+UfCiFoFYBHyjpBq8xd9SOGKAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T20:59:52.068817Z","bundle_sha256":"488d4d3fbaa31688816a955a4e46968f28042bdbe5a3236a6134e8c88af87a4e"}}