{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R3P4QRJPKD4UR3NHRVVB5ROXOU","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":"07fbf061a9ea9efaee60d0105e77ceebea1b61ae4aa7579636efd9da70b7a8e6","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-08T14:26:49Z","title_canon_sha256":"cd22383522708e3aeb2005cdc1230ba585997fbd8a940c1e9954abde3c5cce51"},"schema_version":"1.0","source":{"id":"2401.04151","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.04151","created_at":"2026-07-05T07:31:38Z"},{"alias_kind":"arxiv_version","alias_value":"2401.04151v1","created_at":"2026-07-05T07:31:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04151","created_at":"2026-07-05T07:31:38Z"},{"alias_kind":"pith_short_12","alias_value":"R3P4QRJPKD4U","created_at":"2026-07-05T07:31:38Z"},{"alias_kind":"pith_short_16","alias_value":"R3P4QRJPKD4UR3NH","created_at":"2026-07-05T07:31:38Z"},{"alias_kind":"pith_short_8","alias_value":"R3P4QRJP","created_at":"2026-07-05T07:31:38Z"}],"graph_snapshots":[{"event_id":"sha256:acf1e5a9d8ad5185f22e31e1b7376cf978dcc86f7891f214d1d4bd9c96f82d5f","target":"graph","created_at":"2026-07-05T07:31:38Z","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/2401.04151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning is the primary methodology for tailoring pre-trained large language models to specific tasks. As the model's scale and the diversity of tasks expand, parameter-efficient fine-tuning methods are of paramount importance. One of the most widely used family of methods is low-rank adaptation (LoRA) and its variants. LoRA encodes weight update as the product of two low-rank matrices. Despite its advantages, LoRA falls short of full-parameter fine-tuning in terms of generalization error for certain tasks.\n  We introduce Chain of LoRA (COLA), an iterative optimization framework inspired by","authors_text":"Chengwei Qin, Elad Hazan, Wenhan Xia","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-08T14:26:49Z","title":"Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04151","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":"sha256:4f43ee48ff7a8888a6175b3ab4f70b2d5f0f7ca3028ebc6fce32b10cb18a245e","target":"record","created_at":"2026-07-05T07:31:38Z","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":"07fbf061a9ea9efaee60d0105e77ceebea1b61ae4aa7579636efd9da70b7a8e6","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-08T14:26:49Z","title_canon_sha256":"cd22383522708e3aeb2005cdc1230ba585997fbd8a940c1e9954abde3c5cce51"},"schema_version":"1.0","source":{"id":"2401.04151","kind":"arxiv","version":1}},"canonical_sha256":"8edfc8452f50f948eda78d6a1ec5d7751bb2921a77a0b0506e237f8e7b6e1127","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8edfc8452f50f948eda78d6a1ec5d7751bb2921a77a0b0506e237f8e7b6e1127","first_computed_at":"2026-07-05T07:31:38.225648Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:31:38.225648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wTkgLhuVhbbFdjDDxJMUeobgBX48OZPHTuRU1juI4/H0ktJIgK5QBO9xrnZY4yRx1pUwnp/cx7TRmPssEIizAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:31:38.226027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.04151","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f43ee48ff7a8888a6175b3ab4f70b2d5f0f7ca3028ebc6fce32b10cb18a245e","sha256:acf1e5a9d8ad5185f22e31e1b7376cf978dcc86f7891f214d1d4bd9c96f82d5f"],"state_sha256":"bc9830cd0eee58badc40fb8e36626662be5a29c4fba747fc6c1fb16a35fe863e"}