{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LZHXRTPQFTEKHUIODTK6ZU33WA","short_pith_number":"pith:LZHXRTPQ","canonical_record":{"source":{"id":"2409.14396","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-22T11:24:10Z","cross_cats_sorted":[],"title_canon_sha256":"3a7400e818fd31700a745d29f2dcb4930a1b87133e7e0875e7eb0f8c5410914b","abstract_canon_sha256":"7616a205e5d11f23f597b195636fded87f384d9dc183a99bcaabc264bc4181d7"},"schema_version":"1.0"},"canonical_sha256":"5e4f78cdf02cc8a3d10e1cd5ecd37bb00bfe53521c2cc588f1807082228cfa1b","source":{"kind":"arxiv","id":"2409.14396","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14396","created_at":"2026-07-05T11:09:00Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14396v2","created_at":"2026-07-05T11:09:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14396","created_at":"2026-07-05T11:09:00Z"},{"alias_kind":"pith_short_12","alias_value":"LZHXRTPQFTEK","created_at":"2026-07-05T11:09:00Z"},{"alias_kind":"pith_short_16","alias_value":"LZHXRTPQFTEKHUIO","created_at":"2026-07-05T11:09:00Z"},{"alias_kind":"pith_short_8","alias_value":"LZHXRTPQ","created_at":"2026-07-05T11:09:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LZHXRTPQFTEKHUIODTK6ZU33WA","target":"record","payload":{"canonical_record":{"source":{"id":"2409.14396","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-22T11:24:10Z","cross_cats_sorted":[],"title_canon_sha256":"3a7400e818fd31700a745d29f2dcb4930a1b87133e7e0875e7eb0f8c5410914b","abstract_canon_sha256":"7616a205e5d11f23f597b195636fded87f384d9dc183a99bcaabc264bc4181d7"},"schema_version":"1.0"},"canonical_sha256":"5e4f78cdf02cc8a3d10e1cd5ecd37bb00bfe53521c2cc588f1807082228cfa1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:00.569754Z","signature_b64":"oRG5I9ai0TuAjtVbkUrYEbBlgQFiG0BvOQ4ZpJ7jnOnzJZ79T/SBCMHvj/PJUB57C5/OP4IXJlblx0SDlGUdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e4f78cdf02cc8a3d10e1cd5ecd37bb00bfe53521c2cc588f1807082228cfa1b","last_reissued_at":"2026-07-05T11:09:00.569312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:00.569312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.14396","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":"2026-07-05T11:09:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KCGp9EQDyqVeAjoiuSUehsw7XdpklBWMGuiF9mueR9y34lfbh9Y0wXePeEx/awKjP82p+6N9idMMel/zjcg4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:17:36.993961Z"},"content_sha256":"0cf99d889f26cf38a93faeb1f1fda448cea95278e41bf78b9683149f95d5ffcb","schema_version":"1.0","event_id":"sha256:0cf99d889f26cf38a93faeb1f1fda448cea95278e41bf78b9683149f95d5ffcb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LZHXRTPQFTEKHUIODTK6ZU33WA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lifeng Shang, Tao Li, Xiaolin Huang, Yasheng Wang, Yujun Li, Zhengbao He","submitted_at":"2024-09-22T11:24:10Z","abstract_excerpt":"Fine-tuning large-scale pre-trained models is prohibitively expensive in terms of computation and memory costs. Low-Rank Adaptation (LoRA), a popular Parameter-Efficient Fine-Tuning (PEFT) method, offers an efficient solution by optimizing only low-rank matrices. Despite recent progress in improving LoRA's performance, the relationship between the LoRA optimization space and the full parameter space is often overlooked. A solution that appears flat in the loss landscape of the LoRA space may still exhibit sharp directions in the full parameter space, potentially compromising generalization. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14396","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/2409.14396/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":"2026-07-05T11:09:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8fod0wacpt9bhWi8pcXDvGO+WSIqLHAWpth89Hq+mdJZIJG9ozA9DgYUH8dHOYqGVwCWCgayPhO+yVQj2FwYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:17:36.994543Z"},"content_sha256":"2de75c0297c108dffdfb7c4a43341cf73f41e2dbed9fb2491589f5598c6bea5e","schema_version":"1.0","event_id":"sha256:2de75c0297c108dffdfb7c4a43341cf73f41e2dbed9fb2491589f5598c6bea5e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LZHXRTPQFTEKHUIODTK6ZU33WA/bundle.json","state_url":"https://pith.science/pith/LZHXRTPQFTEKHUIODTK6ZU33WA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LZHXRTPQFTEKHUIODTK6ZU33WA/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":"2026-08-08T17:17:36Z","links":{"resolver":"https://pith.science/pith/LZHXRTPQFTEKHUIODTK6ZU33WA","bundle":"https://pith.science/pith/LZHXRTPQFTEKHUIODTK6ZU33WA/bundle.json","state":"https://pith.science/pith/LZHXRTPQFTEKHUIODTK6ZU33WA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LZHXRTPQFTEKHUIODTK6ZU33WA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LZHXRTPQFTEKHUIODTK6ZU33WA","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":"7616a205e5d11f23f597b195636fded87f384d9dc183a99bcaabc264bc4181d7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-22T11:24:10Z","title_canon_sha256":"3a7400e818fd31700a745d29f2dcb4930a1b87133e7e0875e7eb0f8c5410914b"},"schema_version":"1.0","source":{"id":"2409.14396","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14396","created_at":"2026-07-05T11:09:00Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14396v2","created_at":"2026-07-05T11:09:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14396","created_at":"2026-07-05T11:09:00Z"},{"alias_kind":"pith_short_12","alias_value":"LZHXRTPQFTEK","created_at":"2026-07-05T11:09:00Z"},{"alias_kind":"pith_short_16","alias_value":"LZHXRTPQFTEKHUIO","created_at":"2026-07-05T11:09:00Z"},{"alias_kind":"pith_short_8","alias_value":"LZHXRTPQ","created_at":"2026-07-05T11:09:00Z"}],"graph_snapshots":[{"event_id":"sha256:2de75c0297c108dffdfb7c4a43341cf73f41e2dbed9fb2491589f5598c6bea5e","target":"graph","created_at":"2026-07-05T11:09:00Z","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/2409.14396/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 prohibitively expensive in terms of computation and memory costs. Low-Rank Adaptation (LoRA), a popular Parameter-Efficient Fine-Tuning (PEFT) method, offers an efficient solution by optimizing only low-rank matrices. Despite recent progress in improving LoRA's performance, the relationship between the LoRA optimization space and the full parameter space is often overlooked. A solution that appears flat in the loss landscape of the LoRA space may still exhibit sharp directions in the full parameter space, potentially compromising generalization. We","authors_text":"Lifeng Shang, Tao Li, Xiaolin Huang, Yasheng Wang, Yujun Li, Zhengbao He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-22T11:24:10Z","title":"Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14396","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":"sha256:0cf99d889f26cf38a93faeb1f1fda448cea95278e41bf78b9683149f95d5ffcb","target":"record","created_at":"2026-07-05T11:09:00Z","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":"7616a205e5d11f23f597b195636fded87f384d9dc183a99bcaabc264bc4181d7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-22T11:24:10Z","title_canon_sha256":"3a7400e818fd31700a745d29f2dcb4930a1b87133e7e0875e7eb0f8c5410914b"},"schema_version":"1.0","source":{"id":"2409.14396","kind":"arxiv","version":2}},"canonical_sha256":"5e4f78cdf02cc8a3d10e1cd5ecd37bb00bfe53521c2cc588f1807082228cfa1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e4f78cdf02cc8a3d10e1cd5ecd37bb00bfe53521c2cc588f1807082228cfa1b","first_computed_at":"2026-07-05T11:09:00.569312Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:00.569312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oRG5I9ai0TuAjtVbkUrYEbBlgQFiG0BvOQ4ZpJ7jnOnzJZ79T/SBCMHvj/PJUB57C5/OP4IXJlblx0SDlGUdCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:00.569754Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.14396","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cf99d889f26cf38a93faeb1f1fda448cea95278e41bf78b9683149f95d5ffcb","sha256:2de75c0297c108dffdfb7c4a43341cf73f41e2dbed9fb2491589f5598c6bea5e"],"state_sha256":"ef3aadfd78bac437205d63537fb2a1288f88b5749f76441f6efbd29cedd025b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+HwN+E0UJNyWmIzvaYTdMpsfhHrrAK2QjCROHL0TR5clNAYr4L7nWLcqa9U+e7eUfCQx87A03uH2TWiQKX0DCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:17:36.998649Z","bundle_sha256":"d527177e370e4f9f19cfcd3445812d2c0e2149ae23ca7b28e97082c85610f0ff"}}