{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7MR4O4DE3BDH6RJE6FNGRX4HE6","short_pith_number":"pith:7MR4O4DE","canonical_record":{"source":{"id":"2502.17920","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T07:35:36Z","cross_cats_sorted":[],"title_canon_sha256":"36dffbf657a24eddecda2ecbc8a71a8ecb6feaa3b52b9277e2acbf2c31d4c48d","abstract_canon_sha256":"567bc7fb3693f8265f55b2a38ded7eed6a532cee59947142a7bf74cd4bda30c5"},"schema_version":"1.0"},"canonical_sha256":"fb23c77064d8467f4524f15a68df8727bff2cac262704e6ab3763c5fb82c9ee5","source":{"kind":"arxiv","id":"2502.17920","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17920","created_at":"2026-07-05T10:19:46Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17920v1","created_at":"2026-07-05T10:19:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17920","created_at":"2026-07-05T10:19:46Z"},{"alias_kind":"pith_short_12","alias_value":"7MR4O4DE3BDH","created_at":"2026-07-05T10:19:46Z"},{"alias_kind":"pith_short_16","alias_value":"7MR4O4DE3BDH6RJE","created_at":"2026-07-05T10:19:46Z"},{"alias_kind":"pith_short_8","alias_value":"7MR4O4DE","created_at":"2026-07-05T10:19:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7MR4O4DE3BDH6RJE6FNGRX4HE6","target":"record","payload":{"canonical_record":{"source":{"id":"2502.17920","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T07:35:36Z","cross_cats_sorted":[],"title_canon_sha256":"36dffbf657a24eddecda2ecbc8a71a8ecb6feaa3b52b9277e2acbf2c31d4c48d","abstract_canon_sha256":"567bc7fb3693f8265f55b2a38ded7eed6a532cee59947142a7bf74cd4bda30c5"},"schema_version":"1.0"},"canonical_sha256":"fb23c77064d8467f4524f15a68df8727bff2cac262704e6ab3763c5fb82c9ee5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:46.184968Z","signature_b64":"2AZCnHSaKazVYe8KgSSaKyzyvW3/kPWL13xXbyAI9H9wm+75hdd18ydIVHmqAdDeIejy0wwzLn3jsp2CTH8WDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb23c77064d8467f4524f15a68df8727bff2cac262704e6ab3763c5fb82c9ee5","last_reissued_at":"2026-07-05T10:19:46.184545Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:46.184545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.17920","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:19:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3EHcMLIbGbbb/74TTYze81NKZuc1VXRdJ/ew+HXiKDAfYDOCJS1CAK2mcRUEbPHxps3Q30yq2M+ujaBeZT1mBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:00:12.853778Z"},"content_sha256":"4387999edb7f7f0c7c88eac5035c6aa5c099f212c9c211854947e9a80694cc80","schema_version":"1.0","event_id":"sha256:4387999edb7f7f0c7c88eac5035c6aa5c099f212c9c211854947e9a80694cc80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7MR4O4DE3BDH6RJE6FNGRX4HE6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiye Liang, Liang Bai, Xian Yang, Xin Zhang","submitted_at":"2025-02-25T07:35:36Z","abstract_excerpt":"Low-Rank Adaptation (LoRA) is an efficient fine-tuning method that has been extensively applied in areas such as natural language processing and computer vision. Existing LoRA fine-tuning approaches excel in static environments but struggle in dynamic learning due to reliance on multiple adapter modules, increasing overhead and complicating inference. We propose Continual Low-Rank Adaptation (C-LoRA), a novel extension of LoRA for continual learning. C-LoRA uses a learnable routing matrix to dynamically manage parameter updates across tasks, ensuring efficient reuse of learned subspaces while "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17920","kind":"arxiv","version":1},"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/2502.17920/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":"2026-07-05T10:19:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1VpyS2nIWVSRLK1Dcd+OWpNX4yp3MnWZExqaKlcePco4NKroMsLKcxAFytgiVLcBztouX4HWRPiKVN66Y5mzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:00:12.854289Z"},"content_sha256":"c5dad324da18ab7b7e02c1b9022469f8966057b95644cc9c0a3d684f969fe4b2","schema_version":"1.0","event_id":"sha256:c5dad324da18ab7b7e02c1b9022469f8966057b95644cc9c0a3d684f969fe4b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7MR4O4DE3BDH6RJE6FNGRX4HE6/bundle.json","state_url":"https://pith.science/pith/7MR4O4DE3BDH6RJE6FNGRX4HE6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7MR4O4DE3BDH6RJE6FNGRX4HE6/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":"2026-08-19T04:00:12Z","links":{"resolver":"https://pith.science/pith/7MR4O4DE3BDH6RJE6FNGRX4HE6","bundle":"https://pith.science/pith/7MR4O4DE3BDH6RJE6FNGRX4HE6/bundle.json","state":"https://pith.science/pith/7MR4O4DE3BDH6RJE6FNGRX4HE6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7MR4O4DE3BDH6RJE6FNGRX4HE6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7MR4O4DE3BDH6RJE6FNGRX4HE6","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":"567bc7fb3693f8265f55b2a38ded7eed6a532cee59947142a7bf74cd4bda30c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T07:35:36Z","title_canon_sha256":"36dffbf657a24eddecda2ecbc8a71a8ecb6feaa3b52b9277e2acbf2c31d4c48d"},"schema_version":"1.0","source":{"id":"2502.17920","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17920","created_at":"2026-07-05T10:19:46Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17920v1","created_at":"2026-07-05T10:19:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17920","created_at":"2026-07-05T10:19:46Z"},{"alias_kind":"pith_short_12","alias_value":"7MR4O4DE3BDH","created_at":"2026-07-05T10:19:46Z"},{"alias_kind":"pith_short_16","alias_value":"7MR4O4DE3BDH6RJE","created_at":"2026-07-05T10:19:46Z"},{"alias_kind":"pith_short_8","alias_value":"7MR4O4DE","created_at":"2026-07-05T10:19:46Z"}],"graph_snapshots":[{"event_id":"sha256:c5dad324da18ab7b7e02c1b9022469f8966057b95644cc9c0a3d684f969fe4b2","target":"graph","created_at":"2026-07-05T10:19:46Z","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/2502.17920/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Low-Rank Adaptation (LoRA) is an efficient fine-tuning method that has been extensively applied in areas such as natural language processing and computer vision. Existing LoRA fine-tuning approaches excel in static environments but struggle in dynamic learning due to reliance on multiple adapter modules, increasing overhead and complicating inference. We propose Continual Low-Rank Adaptation (C-LoRA), a novel extension of LoRA for continual learning. C-LoRA uses a learnable routing matrix to dynamically manage parameter updates across tasks, ensuring efficient reuse of learned subspaces while ","authors_text":"Jiye Liang, Liang Bai, Xian Yang, Xin Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T07:35:36Z","title":"C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17920","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":"sha256:4387999edb7f7f0c7c88eac5035c6aa5c099f212c9c211854947e9a80694cc80","target":"record","created_at":"2026-07-05T10:19:46Z","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":"567bc7fb3693f8265f55b2a38ded7eed6a532cee59947142a7bf74cd4bda30c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T07:35:36Z","title_canon_sha256":"36dffbf657a24eddecda2ecbc8a71a8ecb6feaa3b52b9277e2acbf2c31d4c48d"},"schema_version":"1.0","source":{"id":"2502.17920","kind":"arxiv","version":1}},"canonical_sha256":"fb23c77064d8467f4524f15a68df8727bff2cac262704e6ab3763c5fb82c9ee5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb23c77064d8467f4524f15a68df8727bff2cac262704e6ab3763c5fb82c9ee5","first_computed_at":"2026-07-05T10:19:46.184545Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:46.184545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2AZCnHSaKazVYe8KgSSaKyzyvW3/kPWL13xXbyAI9H9wm+75hdd18ydIVHmqAdDeIejy0wwzLn3jsp2CTH8WDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:46.184968Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.17920","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4387999edb7f7f0c7c88eac5035c6aa5c099f212c9c211854947e9a80694cc80","sha256:c5dad324da18ab7b7e02c1b9022469f8966057b95644cc9c0a3d684f969fe4b2"],"state_sha256":"7abc6b4c7a771190f6ca9f254309c9a48746f7eb5c9ae2a2b672b1e0ec1779d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6AZCK50rLVm3Txf4x2kzbhbD8Ke3beFTgAr17r8xQ5BquMq852YOaLsFubJh13GQZyerVzzMd7VBS3+EpYR7BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T04:00:12.858454Z","bundle_sha256":"f80f2b684b137a9ecfc743528e7980b76487e306783df1f3163f57f41f16171c"}}