{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4U6BMSUHS3DO42SHVD52CU5FV2","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":"351dc2a346d2770939be7b666fe9c5e29575a32ccb4b361fcedfda6e22004829","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T10:06:08Z","title_canon_sha256":"49d206943eeaaed8170b68d2d38ff14ca03acb6d8125fe29a41e33e2ddfcac32"},"schema_version":"1.0","source":{"id":"2402.13669","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13669","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13669v2","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13669","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_12","alias_value":"4U6BMSUHS3DO","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_16","alias_value":"4U6BMSUHS3DO42SH","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_8","alias_value":"4U6BMSUH","created_at":"2026-07-05T08:24:02Z"}],"graph_snapshots":[{"event_id":"sha256:497406cfde5ca0d275eed6e640831c2c3aa43b90d4d952e83a02b8b135bfe4f1","target":"graph","created_at":"2026-07-05T08:24:02Z","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/2402.13669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The surge in Large Language Models (LLMs) has revolutionized natural language processing, but fine-tuning them for specific tasks often encounters challenges in balancing performance and preserving general instruction-following abilities. In this paper, we posit that the distribution gap between task datasets and the LLMs serves as the primary underlying cause. To address the problem, we introduce Self-Distillation Fine-Tuning (SDFT), a novel approach that bridges the distribution gap by guiding fine-tuning with a distilled dataset generated by the model itself to match its original distributi","authors_text":"Han Wang, Haozhe Feng, Minfeng Zhu, Qian Liu, Tianyu Pang, Wei Chen, Zhaorui Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T10:06:08Z","title":"Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13669","kind":"arxiv","version":2},"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":"sha256:66e5266b3e2e39b9b893add9aae7d97fd229f6985a036cb478ca6197bf27983f","target":"record","created_at":"2026-07-05T08:24:02Z","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":"351dc2a346d2770939be7b666fe9c5e29575a32ccb4b361fcedfda6e22004829","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T10:06:08Z","title_canon_sha256":"49d206943eeaaed8170b68d2d38ff14ca03acb6d8125fe29a41e33e2ddfcac32"},"schema_version":"1.0","source":{"id":"2402.13669","kind":"arxiv","version":2}},"canonical_sha256":"e53c164a8796c6ee6a47a8fba153a5ae8bb3c9896e25cd9f83afd3d42b564912","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e53c164a8796c6ee6a47a8fba153a5ae8bb3c9896e25cd9f83afd3d42b564912","first_computed_at":"2026-07-05T08:24:02.460836Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:02.460836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CGPLvx2odxv0f1Jhl3xfWf6KEO3YQJlNiP6qDtM5cwijO/u7BiU0KzCRTDQlWILPS4sBFXed6SDjeFYD/T6dBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:02.461391Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13669","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66e5266b3e2e39b9b893add9aae7d97fd229f6985a036cb478ca6197bf27983f","sha256:497406cfde5ca0d275eed6e640831c2c3aa43b90d4d952e83a02b8b135bfe4f1"],"state_sha256":"b69636f1767eb0361d761f4b61e174a5ab199c6df6ff6ad0de244c3e1d98a070"}