{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3TLFM7ULSZM5ZUAYKK4F46IYAD","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":"d24612f3f19ba0e925a669dc5ac51e2f8a7eac9a7ea8e714047e4ec8018de029","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-01T17:56:57Z","title_canon_sha256":"f9013531a5bff8ef155801ce943ee6889d97d62078f83a55e3f3db2d676ab965"},"schema_version":"1.0","source":{"id":"2211.00635","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.00635","created_at":"2026-07-05T07:55:19Z"},{"alias_kind":"arxiv_version","alias_value":"2211.00635v3","created_at":"2026-07-05T07:55:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00635","created_at":"2026-07-05T07:55:19Z"},{"alias_kind":"pith_short_12","alias_value":"3TLFM7ULSZM5","created_at":"2026-07-05T07:55:19Z"},{"alias_kind":"pith_short_16","alias_value":"3TLFM7ULSZM5ZUAY","created_at":"2026-07-05T07:55:19Z"},{"alias_kind":"pith_short_8","alias_value":"3TLFM7UL","created_at":"2026-07-05T07:55:19Z"}],"graph_snapshots":[{"event_id":"sha256:57a3f071354673afee4944bf0c272a69b7c8104048009be2c03fb664eaf9095c","target":"graph","created_at":"2026-07-05T07:55:19Z","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/2211.00635/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained large language models (LLMs) are general purpose problem solvers applicable to a diverse set of tasks with prompts. They can be further improved towards a specific task by fine-tuning on a specialized dataset. However, fine-tuning usually makes the model narrowly specialized on this dataset with reduced general in-context learning performances, which is undesirable whenever the fine-tuned model needs to handle additional tasks where no fine-tuning data is available. In this work, we first demonstrate that fine-tuning on a single task indeed decreases LLMs' general in-context learnin","authors_text":"Cho-Jui Hsieh, Daliang Li, Felix Yu, Inderjit S Dhillon, Michal Lukasik, Sanjiv Kumar, Si Si, Yihan Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-01T17:56:57Z","title":"Two-stage LLM Fine-tuning with Less Specialization and More Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00635","kind":"arxiv","version":3},"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":"sha256:6c93955f901e51990a62871acbc9e3e600166dae5079a1714b279e2c0d9cee3b","target":"record","created_at":"2026-07-05T07:55:19Z","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":"d24612f3f19ba0e925a669dc5ac51e2f8a7eac9a7ea8e714047e4ec8018de029","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-01T17:56:57Z","title_canon_sha256":"f9013531a5bff8ef155801ce943ee6889d97d62078f83a55e3f3db2d676ab965"},"schema_version":"1.0","source":{"id":"2211.00635","kind":"arxiv","version":3}},"canonical_sha256":"dcd6567e8b9659dcd01852b85e791800cd336d6739f6ad2775e1e19462f3db9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcd6567e8b9659dcd01852b85e791800cd336d6739f6ad2775e1e19462f3db9f","first_computed_at":"2026-07-05T07:55:19.226889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:19.226889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lk2wG1Z9HekmJ5qMvJZ0vBPMzW0kiGWX34ycRldExixK97uWESaj8fTInolwl0ujBORt8WlAUYtS8br0b0cmBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:19.227419Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.00635","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c93955f901e51990a62871acbc9e3e600166dae5079a1714b279e2c0d9cee3b","sha256:57a3f071354673afee4944bf0c272a69b7c8104048009be2c03fb664eaf9095c"],"state_sha256":"eb499d0ec2dbbccf778ba90e1b40d068d43ad2b2c0e3f7ef113e125882b829ca"}