{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WGAU5QJF5Y63TJMJIXDDFCIUSB","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":"d869520c6b26298838e8465ae3e4542364250b644292901973bc5fb4f92612dd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-24T07:38:38Z","title_canon_sha256":"fe06418c1028554757fd33d62ed6a0005a504ec643add05d157c0bb969707cb5"},"schema_version":"1.0","source":{"id":"2409.15825","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15825","created_at":"2026-07-05T10:02:52Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15825v2","created_at":"2026-07-05T10:02:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15825","created_at":"2026-07-05T10:02:52Z"},{"alias_kind":"pith_short_12","alias_value":"WGAU5QJF5Y63","created_at":"2026-07-05T10:02:52Z"},{"alias_kind":"pith_short_16","alias_value":"WGAU5QJF5Y63TJMJ","created_at":"2026-07-05T10:02:52Z"},{"alias_kind":"pith_short_8","alias_value":"WGAU5QJF","created_at":"2026-07-05T10:02:52Z"}],"graph_snapshots":[{"event_id":"sha256:16666710f585c7c83f7154c8ab4758663f0439288941c95b4c9946f7b6ff1a2e","target":"graph","created_at":"2026-07-05T10:02:52Z","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/2409.15825/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) encode extensive world knowledge through pre-training on massive datasets, which can then be fine-tuned for the question-answering (QA) task. However, effective strategies for fine-tuning LLMs for the QA task remain largely unexplored. To address this gap, we categorize supervised fine-tuning (SFT) data based on the extent of knowledge memorized by the pretrained LLMs and conduct a series of empirical analyses. Our experiments, involving four LLMs from three different model families, focus on three key factors: the amount of data required for SFT, the impact of dif","authors_text":"Jianping Fan, Junjie Ye, Peng Wang, Qi Zhang, Tao Gui, Xuanjing Huang, Yuming Yang, Zhongchao Shi","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-24T07:38:38Z","title":"60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15825","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":"sha256:129ccebc430e422c659827ee93a2d9ca1952f64cd220233ec5d9dae6859f3e12","target":"record","created_at":"2026-07-05T10:02:52Z","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":"d869520c6b26298838e8465ae3e4542364250b644292901973bc5fb4f92612dd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-24T07:38:38Z","title_canon_sha256":"fe06418c1028554757fd33d62ed6a0005a504ec643add05d157c0bb969707cb5"},"schema_version":"1.0","source":{"id":"2409.15825","kind":"arxiv","version":2}},"canonical_sha256":"b1814ec125ee3db9a58945c63289149040294443bc0bb892aa99d1f0638d3c54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1814ec125ee3db9a58945c63289149040294443bc0bb892aa99d1f0638d3c54","first_computed_at":"2026-07-05T10:02:52.324567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:52.324567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CxoAX3V5xZCqrmPDT71EDtAtDFbYC0gL4Qv1UxHG+E686IXJtRUR7PUFjzjVbo6qoQ8BW87VgzsKWLHPmrk0Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:52.325211Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.15825","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:129ccebc430e422c659827ee93a2d9ca1952f64cd220233ec5d9dae6859f3e12","sha256:16666710f585c7c83f7154c8ab4758663f0439288941c95b4c9946f7b6ff1a2e"],"state_sha256":"ab5314d9748a906cc3504ded761069e00ea4c73f8dd1b4dc0d4b35c5568d6cd1"}