{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YHEMZCTAE6YZTFQAFAY2KFCJ4U","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":"b8808c3d788d985ec7101547ff37cbe6e98595941672cf5a8b6b34f8312ea4f3","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-27T02:31:00Z","title_canon_sha256":"1af17290de1aca09b5df77ed7c7430c707b128208f440cc46ca9745b644b2781"},"schema_version":"1.0","source":{"id":"2603.00191","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.00191","created_at":"2026-05-26T01:03:26Z"},{"alias_kind":"arxiv_version","alias_value":"2603.00191v4","created_at":"2026-05-26T01:03:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.00191","created_at":"2026-05-26T01:03:26Z"},{"alias_kind":"pith_short_12","alias_value":"YHEMZCTAE6YZ","created_at":"2026-05-26T01:03:26Z"},{"alias_kind":"pith_short_16","alias_value":"YHEMZCTAE6YZTFQA","created_at":"2026-05-26T01:03:26Z"},{"alias_kind":"pith_short_8","alias_value":"YHEMZCTA","created_at":"2026-05-26T01:03:26Z"}],"graph_snapshots":[{"event_id":"sha256:5ccec34e744aac6794a700cc8d9121db67f50edfe891ac0234228610d683dc8a","target":"graph","created_at":"2026-05-26T01:03:26Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"LoDA outperforms existing CL methods by performing task-driven decomposition to build general and truly task-specific LoRA subspaces, fixing down-projections and using GAO plus closed-form recalibration for the general update."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That solving the two energy-based objectives will reliably produce effective shared and task-specific directions, and that the null-space limitations of prior methods are the primary bottleneck rather than other factors such as optimization dynamics or data distribution shifts."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"LoDA introduces task-driven subspace decomposition in LoRA for continual learning to separate knowledge-sharing and isolation directions via energy objectives and closed-form recalibration, outperforming prior null-space methods."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"LoDA decomposes LoRA updates into shared general and task-specific subspaces via energy-based objectives to enable knowledge transfer without catastrophic forgetting."}],"snapshot_sha256":"7c8ed58ac5108b75aff7fa0846d4f5367d92ca76946dfe310a1aae805db71049"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9f2b9ada3c4306b0400aef4cfb5c269e4a13701c96cc272741c1871248e1619d"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.00191/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continual Learning (CL) requires models to sequentially adapt to new tasks without forgetting old knowledge. Recently, Low-Rank Adaptation (LoRA), a representative Parameter-Efficient Fine-Tuning (PEFT) method, has gained increasing attention in CL. Several LoRA-based CL methods reduce interference across tasks by separating their update spaces, typically building the new space from the estimated null space of past tasks. However, they (i) overlook task-shared directions, which suppresses knowledge transfer, and (ii) fail to capture truly effective task-specific directions since these ``null b","authors_text":"De Cheng, Huaijie Wang, Lingfeng He, Nannan Wang, Xinbo Gao, Xi Yang","cross_cats":["cs.CV"],"headline":"LoDA decomposes LoRA updates into shared general and task-specific subspaces via energy-based objectives to enable knowledge transfer without catastrophic forgetting.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-27T02:31:00Z","title":"Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.00191","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-15T18:57:44.672935Z","id":"d06e7625-f9bd-41a7-b0f4-9733442cc3e6","model_set":{"reader":"grok-4.3"},"one_line_summary":"LoDA introduces task-driven subspace decomposition in LoRA for continual learning to separate knowledge-sharing and isolation directions via energy objectives and closed-form recalibration, outperforming prior null-space methods.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"LoDA decomposes LoRA updates into shared general and task-specific subspaces via energy-based objectives to enable knowledge transfer without catastrophic forgetting.","strongest_claim":"LoDA outperforms existing CL methods by performing task-driven decomposition to build general and truly task-specific LoRA subspaces, fixing down-projections and using GAO plus closed-form recalibration for the general update.","weakest_assumption":"That solving the two energy-based objectives will reliably produce effective shared and task-specific directions, and that the null-space limitations of prior methods are the primary bottleneck rather than other factors such as optimization dynamics or data distribution shifts."}},"verdict_id":"d06e7625-f9bd-41a7-b0f4-9733442cc3e6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6e58950c45664f69621f754118199578f8afd60c671408ddef6be99656231912","target":"record","created_at":"2026-05-26T01:03:26Z","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":"b8808c3d788d985ec7101547ff37cbe6e98595941672cf5a8b6b34f8312ea4f3","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-27T02:31:00Z","title_canon_sha256":"1af17290de1aca09b5df77ed7c7430c707b128208f440cc46ca9745b644b2781"},"schema_version":"1.0","source":{"id":"2603.00191","kind":"arxiv","version":4}},"canonical_sha256":"c1c8cc8a6027b19996002831a51449e503f461d3bae3951bcf32be82162dfe46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1c8cc8a6027b19996002831a51449e503f461d3bae3951bcf32be82162dfe46","first_computed_at":"2026-05-26T01:03:26.854634Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:26.854634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i4Spwesa+f7q7Gs0GWYTGnjXredqd4FfahoNLvUXUxYkPNzugXDAXmUhDLz7MhRdL/UJadErObVTU39f8oRaCw==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:26.855497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.00191","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e58950c45664f69621f754118199578f8afd60c671408ddef6be99656231912","sha256:5ccec34e744aac6794a700cc8d9121db67f50edfe891ac0234228610d683dc8a"],"state_sha256":"d5c527bf2ada32c235b451235a36ec4fc46d1fea3319bc54610e8bb631bea535"}