{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VZBV5DNCKJQV4ZSQCFGULSUP23","short_pith_number":"pith:VZBV5DNC","canonical_record":{"source":{"id":"2405.17357","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T17:02:27Z","cross_cats_sorted":[],"title_canon_sha256":"cf8cb46cc2a420b0c1244f79679a5e097a36fe2a12fcc04457256dca702a8070","abstract_canon_sha256":"df9de06eebae9d0d1f022ccfa61f227674e6be72dc66f3725bb44ba113b32e98"},"schema_version":"1.0"},"canonical_sha256":"ae435e8da252615e6650114d45ca8fd6e92a710749faf83b523355f6b74be5e8","source":{"kind":"arxiv","id":"2405.17357","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17357","created_at":"2026-07-05T08:37:07Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17357v3","created_at":"2026-07-05T08:37:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17357","created_at":"2026-07-05T08:37:07Z"},{"alias_kind":"pith_short_12","alias_value":"VZBV5DNCKJQV","created_at":"2026-07-05T08:37:07Z"},{"alias_kind":"pith_short_16","alias_value":"VZBV5DNCKJQV4ZSQ","created_at":"2026-07-05T08:37:07Z"},{"alias_kind":"pith_short_8","alias_value":"VZBV5DNC","created_at":"2026-07-05T08:37:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VZBV5DNCKJQV4ZSQCFGULSUP23","target":"record","payload":{"canonical_record":{"source":{"id":"2405.17357","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T17:02:27Z","cross_cats_sorted":[],"title_canon_sha256":"cf8cb46cc2a420b0c1244f79679a5e097a36fe2a12fcc04457256dca702a8070","abstract_canon_sha256":"df9de06eebae9d0d1f022ccfa61f227674e6be72dc66f3725bb44ba113b32e98"},"schema_version":"1.0"},"canonical_sha256":"ae435e8da252615e6650114d45ca8fd6e92a710749faf83b523355f6b74be5e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:07.006553Z","signature_b64":"CZJ9Q1I9cFx7QR/P3e1gRcAsolvXdh8sIJqgeCPSJxc1uesAAPh79J/QHyY1vjtpvZX0AVugmu5+P0cJ4UcPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae435e8da252615e6650114d45ca8fd6e92a710749faf83b523355f6b74be5e8","last_reissued_at":"2026-07-05T08:37:07.005767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:07.005767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.17357","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":"2026-07-05T08:37:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P2OikYb91ryleH3GaCbfPOuF/dmxu7B7rIOCB3A2IRJsYp0YWEhbcXxMfKo6TWC4G3WWT1/OumjfAxyj0J/SDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:30:54.359985Z"},"content_sha256":"bd1c9b27eb04f6d3c22dae4d1af57d2e17b43423bd0e28db2fe213ecd866499f","schema_version":"1.0","event_id":"sha256:bd1c9b27eb04f6d3c22dae4d1af57d2e17b43423bd0e28db2fe213ecd866499f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VZBV5DNCKJQV4ZSQCFGULSUP23","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DoRA: Enhancing Parameter-Efficient Fine-Tuning with Dynamic Rank Distribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changhao Guan, Fengran Mo, Ganglin Bao, Jinan Xu, Kaiyu Huang, Yulong Mao","submitted_at":"2024-05-27T17:02:27Z","abstract_excerpt":"Fine-tuning large-scale pre-trained models is inherently a resource-intensive task. While it can enhance the capabilities of the model, it also incurs substantial computational costs, posing challenges to the practical application of downstream tasks. Existing parameter-efficient fine-tuning (PEFT) methods such as Low-Rank Adaptation (LoRA) rely on a bypass framework that ignores the differential parameter budget requirements across weight matrices, which may lead to suboptimal fine-tuning outcomes. To address this issue, we introduce the Dynamic Low-Rank Adaptation (DoRA) method. DoRA decompo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17357","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/2405.17357/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":"2026-07-05T08:37:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gqI8Dtf3BR0GOhEzmDtYd6V7X73qnC2ekBD/IqHf4PagaXkum3BpSg7B34VY4Oy9HMsj8LNbDiEt0xpmHDt+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:30:54.360603Z"},"content_sha256":"10b1fa125d3cf098386716e1915972e85f6bfd17fcfbc7473a4a74a76d859256","schema_version":"1.0","event_id":"sha256:10b1fa125d3cf098386716e1915972e85f6bfd17fcfbc7473a4a74a76d859256"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VZBV5DNCKJQV4ZSQCFGULSUP23/bundle.json","state_url":"https://pith.science/pith/VZBV5DNCKJQV4ZSQCFGULSUP23/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VZBV5DNCKJQV4ZSQCFGULSUP23/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":"2026-08-04T14:30:54Z","links":{"resolver":"https://pith.science/pith/VZBV5DNCKJQV4ZSQCFGULSUP23","bundle":"https://pith.science/pith/VZBV5DNCKJQV4ZSQCFGULSUP23/bundle.json","state":"https://pith.science/pith/VZBV5DNCKJQV4ZSQCFGULSUP23/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VZBV5DNCKJQV4ZSQCFGULSUP23/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VZBV5DNCKJQV4ZSQCFGULSUP23","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":"df9de06eebae9d0d1f022ccfa61f227674e6be72dc66f3725bb44ba113b32e98","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T17:02:27Z","title_canon_sha256":"cf8cb46cc2a420b0c1244f79679a5e097a36fe2a12fcc04457256dca702a8070"},"schema_version":"1.0","source":{"id":"2405.17357","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17357","created_at":"2026-07-05T08:37:07Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17357v3","created_at":"2026-07-05T08:37:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17357","created_at":"2026-07-05T08:37:07Z"},{"alias_kind":"pith_short_12","alias_value":"VZBV5DNCKJQV","created_at":"2026-07-05T08:37:07Z"},{"alias_kind":"pith_short_16","alias_value":"VZBV5DNCKJQV4ZSQ","created_at":"2026-07-05T08:37:07Z"},{"alias_kind":"pith_short_8","alias_value":"VZBV5DNC","created_at":"2026-07-05T08:37:07Z"}],"graph_snapshots":[{"event_id":"sha256:10b1fa125d3cf098386716e1915972e85f6bfd17fcfbc7473a4a74a76d859256","target":"graph","created_at":"2026-07-05T08:37:07Z","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/2405.17357/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning large-scale pre-trained models is inherently a resource-intensive task. While it can enhance the capabilities of the model, it also incurs substantial computational costs, posing challenges to the practical application of downstream tasks. Existing parameter-efficient fine-tuning (PEFT) methods such as Low-Rank Adaptation (LoRA) rely on a bypass framework that ignores the differential parameter budget requirements across weight matrices, which may lead to suboptimal fine-tuning outcomes. To address this issue, we introduce the Dynamic Low-Rank Adaptation (DoRA) method. DoRA decompo","authors_text":"Changhao Guan, Fengran Mo, Ganglin Bao, Jinan Xu, Kaiyu Huang, Yulong Mao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T17:02:27Z","title":"DoRA: Enhancing Parameter-Efficient Fine-Tuning with Dynamic Rank Distribution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17357","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:bd1c9b27eb04f6d3c22dae4d1af57d2e17b43423bd0e28db2fe213ecd866499f","target":"record","created_at":"2026-07-05T08:37:07Z","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":"df9de06eebae9d0d1f022ccfa61f227674e6be72dc66f3725bb44ba113b32e98","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T17:02:27Z","title_canon_sha256":"cf8cb46cc2a420b0c1244f79679a5e097a36fe2a12fcc04457256dca702a8070"},"schema_version":"1.0","source":{"id":"2405.17357","kind":"arxiv","version":3}},"canonical_sha256":"ae435e8da252615e6650114d45ca8fd6e92a710749faf83b523355f6b74be5e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae435e8da252615e6650114d45ca8fd6e92a710749faf83b523355f6b74be5e8","first_computed_at":"2026-07-05T08:37:07.005767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:07.005767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CZJ9Q1I9cFx7QR/P3e1gRcAsolvXdh8sIJqgeCPSJxc1uesAAPh79J/QHyY1vjtpvZX0AVugmu5+P0cJ4UcPCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:07.006553Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17357","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd1c9b27eb04f6d3c22dae4d1af57d2e17b43423bd0e28db2fe213ecd866499f","sha256:10b1fa125d3cf098386716e1915972e85f6bfd17fcfbc7473a4a74a76d859256"],"state_sha256":"187a85b9fef5369e9b829f69f96096067ab22ec0e6ec34b1e19170687138a411"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AQrRhyj7mfdNGVznHVv0oSLKLbVpeJvA1UgZXuk6I4RFHDHsfFiRw1Kf+SDfrANT/NX80kednhLuF5gSKf+LAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T14:30:54.365478Z","bundle_sha256":"a004f526abf28db12be18993b4b14b864b8377da03e25e48a57fd9ee829dc0b8"}}