{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4WZIP6CZZC54QALZPKZIDDMZOZ","short_pith_number":"pith:4WZIP6CZ","canonical_record":{"source":{"id":"2409.19611","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-29T08:34:54Z","cross_cats_sorted":[],"title_canon_sha256":"c483b8a01473fc4c154c4b45d359fb4c12a88d162bc45df4090c6a854c0da2d9","abstract_canon_sha256":"98dbb88c6de13563b0958d294f2016e3abb116baf0e6ca9571589edf8941a3c5"},"schema_version":"1.0"},"canonical_sha256":"e5b287f859c8bbc801797ab2818d997671706021fbf0c0c6ccec72869efbbc1a","source":{"kind":"arxiv","id":"2409.19611","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19611","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19611v1","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19611","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"4WZIP6CZZC54","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"4WZIP6CZZC54QALZ","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"4WZIP6CZ","created_at":"2026-07-05T09:13:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4WZIP6CZZC54QALZPKZIDDMZOZ","target":"record","payload":{"canonical_record":{"source":{"id":"2409.19611","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-29T08:34:54Z","cross_cats_sorted":[],"title_canon_sha256":"c483b8a01473fc4c154c4b45d359fb4c12a88d162bc45df4090c6a854c0da2d9","abstract_canon_sha256":"98dbb88c6de13563b0958d294f2016e3abb116baf0e6ca9571589edf8941a3c5"},"schema_version":"1.0"},"canonical_sha256":"e5b287f859c8bbc801797ab2818d997671706021fbf0c0c6ccec72869efbbc1a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:18.269809Z","signature_b64":"0aTppEHWxpPwT4swN20FHokIvzbioYcvwvOZir3yVOx8pdJPjpThn/rmCatNfq4d/JC7hXWRyETHjMfq2iI2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5b287f859c8bbc801797ab2818d997671706021fbf0c0c6ccec72869efbbc1a","last_reissued_at":"2026-07-05T09:13:18.269435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:18.269435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.19611","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":"2026-07-05T09:13:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gqRZdNXbALdf7ph/dHIZ12mdiO07SmsxfOvg4oIMCLUa6Cp3jLc9L8az7v6+RXpBOJ/m7vhSIJWBIcQOSDsqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:58:54.472061Z"},"content_sha256":"d9194939b1f0798d5eae0f26c9a13f69cf92ddb2ea16b9f0f430f06b364395b1","schema_version":"1.0","event_id":"sha256:d9194939b1f0798d5eae0f26c9a13f69cf92ddb2ea16b9f0f430f06b364395b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4WZIP6CZZC54QALZPKZIDDMZOZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Attentional Mixture of LoRAs for Language Model Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jialin Liu, Jianhua Wu, Jie Liu, Yutai Duan","submitted_at":"2024-09-29T08:34:54Z","abstract_excerpt":"Fine-tuning large language models (LLMs) with Low-Rank adaption (LoRA) is widely acknowledged as an effective approach for continual learning for new tasks. However, it often suffers from catastrophic forgetting when dealing with multiple tasks sequentially. To this end, we propose Attentional Mixture of LoRAs (AM-LoRA), a continual learning approach tailored for LLMs. Specifically, AM-LoRA learns a sequence of LoRAs for a series of tasks to continually learn knowledge from different tasks. The key of our approach is that we devise an attention mechanism as a knowledge mixture module to adapti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19611","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/2409.19611/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":"2026-07-05T09:13:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4gu1Wy2GRe7WGADIe0yVtrnAJ9dFaIMTxJ2bgb0cuZClSSVt+yfi6xM4f7v6f7TMk/zAQjyN0ucH6tKf4RwvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:58:54.472553Z"},"content_sha256":"81fbcc0f06127f50cc622baf541ae1066f08e9b5ef7323efcea63afbd4ba9aa1","schema_version":"1.0","event_id":"sha256:81fbcc0f06127f50cc622baf541ae1066f08e9b5ef7323efcea63afbd4ba9aa1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4WZIP6CZZC54QALZPKZIDDMZOZ/bundle.json","state_url":"https://pith.science/pith/4WZIP6CZZC54QALZPKZIDDMZOZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4WZIP6CZZC54QALZPKZIDDMZOZ/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":"2026-08-08T09:58:54Z","links":{"resolver":"https://pith.science/pith/4WZIP6CZZC54QALZPKZIDDMZOZ","bundle":"https://pith.science/pith/4WZIP6CZZC54QALZPKZIDDMZOZ/bundle.json","state":"https://pith.science/pith/4WZIP6CZZC54QALZPKZIDDMZOZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4WZIP6CZZC54QALZPKZIDDMZOZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4WZIP6CZZC54QALZPKZIDDMZOZ","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":"98dbb88c6de13563b0958d294f2016e3abb116baf0e6ca9571589edf8941a3c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-29T08:34:54Z","title_canon_sha256":"c483b8a01473fc4c154c4b45d359fb4c12a88d162bc45df4090c6a854c0da2d9"},"schema_version":"1.0","source":{"id":"2409.19611","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19611","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19611v1","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19611","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"4WZIP6CZZC54","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"4WZIP6CZZC54QALZ","created_at":"2026-07-05T09:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"4WZIP6CZ","created_at":"2026-07-05T09:13:18Z"}],"graph_snapshots":[{"event_id":"sha256:81fbcc0f06127f50cc622baf541ae1066f08e9b5ef7323efcea63afbd4ba9aa1","target":"graph","created_at":"2026-07-05T09:13:18Z","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/2409.19611/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning large language models (LLMs) with Low-Rank adaption (LoRA) is widely acknowledged as an effective approach for continual learning for new tasks. However, it often suffers from catastrophic forgetting when dealing with multiple tasks sequentially. To this end, we propose Attentional Mixture of LoRAs (AM-LoRA), a continual learning approach tailored for LLMs. Specifically, AM-LoRA learns a sequence of LoRAs for a series of tasks to continually learn knowledge from different tasks. The key of our approach is that we devise an attention mechanism as a knowledge mixture module to adapti","authors_text":"Jialin Liu, Jianhua Wu, Jie Liu, Yutai Duan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-29T08:34:54Z","title":"Learning Attentional Mixture of LoRAs for Language Model Continual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19611","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:d9194939b1f0798d5eae0f26c9a13f69cf92ddb2ea16b9f0f430f06b364395b1","target":"record","created_at":"2026-07-05T09:13:18Z","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":"98dbb88c6de13563b0958d294f2016e3abb116baf0e6ca9571589edf8941a3c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-29T08:34:54Z","title_canon_sha256":"c483b8a01473fc4c154c4b45d359fb4c12a88d162bc45df4090c6a854c0da2d9"},"schema_version":"1.0","source":{"id":"2409.19611","kind":"arxiv","version":1}},"canonical_sha256":"e5b287f859c8bbc801797ab2818d997671706021fbf0c0c6ccec72869efbbc1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5b287f859c8bbc801797ab2818d997671706021fbf0c0c6ccec72869efbbc1a","first_computed_at":"2026-07-05T09:13:18.269435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:18.269435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0aTppEHWxpPwT4swN20FHokIvzbioYcvwvOZir3yVOx8pdJPjpThn/rmCatNfq4d/JC7hXWRyETHjMfq2iI2DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:18.269809Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.19611","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9194939b1f0798d5eae0f26c9a13f69cf92ddb2ea16b9f0f430f06b364395b1","sha256:81fbcc0f06127f50cc622baf541ae1066f08e9b5ef7323efcea63afbd4ba9aa1"],"state_sha256":"3c8ba54f97315b44c9a9bbb47a4658f4b38bdd56547598e533bd8cd84c280f5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/GA3IL+MSUbhh0ifVpwYYzIa3KMVleIRhauM9xXPC8yZ/KjUFbmcn9YeQ1mwmygK77bv/AyHhKebTMD1hkeLAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:58:54.477311Z","bundle_sha256":"7fd11200104451819ab3595ae6bb8a6770bd5945b495e5a1820224ba3e4078fb"}}