{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HEK7RUC7X5BLZH33LLWE3VVVPN","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":"7e66d505621d4aaade126d86521f81915a35e075b0c3ee00b87edf5d37b47ad8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-21T02:25:03Z","title_canon_sha256":"29ed230329e04c12968858fa1596cc5cac6d87cbdebea89b1ef964707d34d577"},"schema_version":"1.0","source":{"id":"2504.14810","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14810","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14810v2","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14810","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"pith_short_12","alias_value":"HEK7RUC7X5BL","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"pith_short_16","alias_value":"HEK7RUC7X5BLZH33","created_at":"2026-07-05T11:50:34Z"},{"alias_kind":"pith_short_8","alias_value":"HEK7RUC7","created_at":"2026-07-05T11:50:34Z"}],"graph_snapshots":[{"event_id":"sha256:3e97f9b645fcb4173f266f982ae2dbd32f01e4ca94bf0425a521951d5a059620","target":"graph","created_at":"2026-07-05T11:50:34Z","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/2504.14810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ad-hoc instruction fine-tuning of large language models (LLMs) is widely adopted for domain-specific adaptation. While domain-specific supervised fine-tuning (SFT) is effective and efficient, it often weakens cross-domain generalization and struggles with noisy training data. To address these challenges, we propose DONOD, a lightweight model-intrinsic data pruning method. Our approach evaluates data using two model-parameter-based metrics: Delta of Norm (DON), which captures the cumulative influence on model weights, and Norm of Delta (NOD), which quantifies weight instability. Moreover, by em","authors_text":"Dongzhan Zhou, Jucheng Hu, Lijun Wu, Surong Yang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-21T02:25:03Z","title":"DONOD: Efficient and Generalizable Instruction Fine-Tuning for LLMs via Model-Intrinsic Dataset Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14810","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":"sha256:2a1af03833200ee1eba349fec147b657294c57670e53d2a596d753ffb2c286af","target":"record","created_at":"2026-07-05T11:50:34Z","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":"7e66d505621d4aaade126d86521f81915a35e075b0c3ee00b87edf5d37b47ad8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-21T02:25:03Z","title_canon_sha256":"29ed230329e04c12968858fa1596cc5cac6d87cbdebea89b1ef964707d34d577"},"schema_version":"1.0","source":{"id":"2504.14810","kind":"arxiv","version":2}},"canonical_sha256":"3915f8d05fbf42bc9f7b5aec4dd6b57b43c1e89f1b46d5e8ceb1099b24830344","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3915f8d05fbf42bc9f7b5aec4dd6b57b43c1e89f1b46d5e8ceb1099b24830344","first_computed_at":"2026-07-05T11:50:34.956076Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:34.956076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aMkIlsyh7chGQGTOd2ZOpBpsTWA5WCblvuFV5dphFcDBXk+gxyAIUBJhrd/eus5bzdL12j8DdbZ69TKI8YBxBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:34.956519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14810","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a1af03833200ee1eba349fec147b657294c57670e53d2a596d753ffb2c286af","sha256:3e97f9b645fcb4173f266f982ae2dbd32f01e4ca94bf0425a521951d5a059620"],"state_sha256":"30019f46a0a1f27143ce6343af5e96b69b39d90cebe928a0a0295450fe48d83f"}