{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XAQSR45QTJRVSYZ2PXEKBVBUEH","short_pith_number":"pith:XAQSR45Q","canonical_record":{"source":{"id":"2310.14152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-22T02:23:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"44cff7bbe9c5f109031adb9241facaa4f67658f63f3199c8080d8a06b90f8408","abstract_canon_sha256":"f8ff0bd0d84f627ab064669e984e1627cdc886865f220f2248a49ed6d97e8eaf"},"schema_version":"1.0"},"canonical_sha256":"b82128f3b09a6359633a7dc8a0d43421e54d15f005279c0488cb04a932abc0a0","source":{"kind":"arxiv","id":"2310.14152","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14152","created_at":"2026-07-05T07:03:40Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14152v1","created_at":"2026-07-05T07:03:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14152","created_at":"2026-07-05T07:03:40Z"},{"alias_kind":"pith_short_12","alias_value":"XAQSR45QTJRV","created_at":"2026-07-05T07:03:40Z"},{"alias_kind":"pith_short_16","alias_value":"XAQSR45QTJRVSYZ2","created_at":"2026-07-05T07:03:40Z"},{"alias_kind":"pith_short_8","alias_value":"XAQSR45Q","created_at":"2026-07-05T07:03:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XAQSR45QTJRVSYZ2PXEKBVBUEH","target":"record","payload":{"canonical_record":{"source":{"id":"2310.14152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-22T02:23:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"44cff7bbe9c5f109031adb9241facaa4f67658f63f3199c8080d8a06b90f8408","abstract_canon_sha256":"f8ff0bd0d84f627ab064669e984e1627cdc886865f220f2248a49ed6d97e8eaf"},"schema_version":"1.0"},"canonical_sha256":"b82128f3b09a6359633a7dc8a0d43421e54d15f005279c0488cb04a932abc0a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:40.379491Z","signature_b64":"2QRO7P3uVPslnTZ3XU74qPqU4m4f2KFf36M4dpjfSmK2h9ceIkNmUnNXPnVO6xgcyqQxmka7FpGkp+DpbEfSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b82128f3b09a6359633a7dc8a0d43421e54d15f005279c0488cb04a932abc0a0","last_reissued_at":"2026-07-05T07:03:40.378996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:40.378996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.14152","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":"2026-07-05T07:03:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xWwyp3KImslkeONGR1ss96Bxxvz28LAN9TmaCknUwgzDLpAyBlcI2HF10HJPe2AcnhlEqVc9Ob6+Xg2IzeOWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:28:53.082180Z"},"content_sha256":"dd2dbee1fdc2e92fb67ae40f99c0e3279160b26a4a099504628c1244fbc25d44","schema_version":"1.0","event_id":"sha256:dd2dbee1fdc2e92fb67ae40f99c0e3279160b26a4a099504628c1244fbc25d44"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XAQSR45QTJRVSYZ2PXEKBVBUEH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Orthogonal Subspace Learning for Language Model Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Han Xia, Qiming Ge, Qi Zhang, Rong Bao, Rui Zheng, Tao Gui, Tianze Chen, Xiao Wang, Xuanjing Huang","submitted_at":"2023-10-22T02:23:44Z","abstract_excerpt":"Benefiting from massive corpora and advanced hardware, large language models (LLMs) exhibit remarkable capabilities in language understanding and generation. However, their performance degrades in scenarios where multiple tasks are encountered sequentially, also known as catastrophic forgetting. In this paper, we propose orthogonal low-rank adaptation (O-LoRA), a simple and efficient approach for continual learning in language models, effectively mitigating catastrophic forgetting while learning new tasks. Specifically, O-LoRA learns tasks in different (low-rank) vector subspaces that are kept"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14152","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/2310.14152/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":"2026-07-05T07:03:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vtibwmRSRJOIMp1vdu3sXVAMCfyLvq8bW6KjkF/szPHXdEyuM24hLWLfWDh+h0xf0RjkLOxpJBAa5cEWKTIACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:28:53.082953Z"},"content_sha256":"ead1e08325c12d3d4d1a4acdea2ec94134ecd027c0af57ea8462a7b5e3dea932","schema_version":"1.0","event_id":"sha256:ead1e08325c12d3d4d1a4acdea2ec94134ecd027c0af57ea8462a7b5e3dea932"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XAQSR45QTJRVSYZ2PXEKBVBUEH/bundle.json","state_url":"https://pith.science/pith/XAQSR45QTJRVSYZ2PXEKBVBUEH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XAQSR45QTJRVSYZ2PXEKBVBUEH/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":"2026-08-06T15:28:53Z","links":{"resolver":"https://pith.science/pith/XAQSR45QTJRVSYZ2PXEKBVBUEH","bundle":"https://pith.science/pith/XAQSR45QTJRVSYZ2PXEKBVBUEH/bundle.json","state":"https://pith.science/pith/XAQSR45QTJRVSYZ2PXEKBVBUEH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XAQSR45QTJRVSYZ2PXEKBVBUEH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XAQSR45QTJRVSYZ2PXEKBVBUEH","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":"f8ff0bd0d84f627ab064669e984e1627cdc886865f220f2248a49ed6d97e8eaf","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-22T02:23:44Z","title_canon_sha256":"44cff7bbe9c5f109031adb9241facaa4f67658f63f3199c8080d8a06b90f8408"},"schema_version":"1.0","source":{"id":"2310.14152","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14152","created_at":"2026-07-05T07:03:40Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14152v1","created_at":"2026-07-05T07:03:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14152","created_at":"2026-07-05T07:03:40Z"},{"alias_kind":"pith_short_12","alias_value":"XAQSR45QTJRV","created_at":"2026-07-05T07:03:40Z"},{"alias_kind":"pith_short_16","alias_value":"XAQSR45QTJRVSYZ2","created_at":"2026-07-05T07:03:40Z"},{"alias_kind":"pith_short_8","alias_value":"XAQSR45Q","created_at":"2026-07-05T07:03:40Z"}],"graph_snapshots":[{"event_id":"sha256:ead1e08325c12d3d4d1a4acdea2ec94134ecd027c0af57ea8462a7b5e3dea932","target":"graph","created_at":"2026-07-05T07:03:40Z","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/2310.14152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benefiting from massive corpora and advanced hardware, large language models (LLMs) exhibit remarkable capabilities in language understanding and generation. However, their performance degrades in scenarios where multiple tasks are encountered sequentially, also known as catastrophic forgetting. In this paper, we propose orthogonal low-rank adaptation (O-LoRA), a simple and efficient approach for continual learning in language models, effectively mitigating catastrophic forgetting while learning new tasks. Specifically, O-LoRA learns tasks in different (low-rank) vector subspaces that are kept","authors_text":"Han Xia, Qiming Ge, Qi Zhang, Rong Bao, Rui Zheng, Tao Gui, Tianze Chen, Xiao Wang, Xuanjing Huang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-22T02:23:44Z","title":"Orthogonal Subspace Learning for Language Model Continual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14152","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:dd2dbee1fdc2e92fb67ae40f99c0e3279160b26a4a099504628c1244fbc25d44","target":"record","created_at":"2026-07-05T07:03:40Z","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":"f8ff0bd0d84f627ab064669e984e1627cdc886865f220f2248a49ed6d97e8eaf","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-22T02:23:44Z","title_canon_sha256":"44cff7bbe9c5f109031adb9241facaa4f67658f63f3199c8080d8a06b90f8408"},"schema_version":"1.0","source":{"id":"2310.14152","kind":"arxiv","version":1}},"canonical_sha256":"b82128f3b09a6359633a7dc8a0d43421e54d15f005279c0488cb04a932abc0a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b82128f3b09a6359633a7dc8a0d43421e54d15f005279c0488cb04a932abc0a0","first_computed_at":"2026-07-05T07:03:40.378996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:40.378996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2QRO7P3uVPslnTZ3XU74qPqU4m4f2KFf36M4dpjfSmK2h9ceIkNmUnNXPnVO6xgcyqQxmka7FpGkp+DpbEfSBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:40.379491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.14152","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd2dbee1fdc2e92fb67ae40f99c0e3279160b26a4a099504628c1244fbc25d44","sha256:ead1e08325c12d3d4d1a4acdea2ec94134ecd027c0af57ea8462a7b5e3dea932"],"state_sha256":"4b60a88db424949570bbcffa78e6f441e39aee9fa7b2217d6f931ab72c7202fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YsRdl6Jh7O7XxAeSjHddUhS77LbumRoO4HBSaPKjJbRp0yZMzEMBZjgt0GSHcmPXntyrZy2aXkwZJQLkD3lnBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T15:28:53.089211Z","bundle_sha256":"23718cc1d7d21e4f50bb0fa81b4e0f3cda9cb5b2ff109e796c3c25197ed09432"}}