{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZK5G2SYAE32IHFH3KCQIMFYL2S","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":"15ec47d14fb98a8acd3a0808257f087dfc27ab78e7c670634350eb7ec87c25e3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T09:20:32Z","title_canon_sha256":"cbc6780e455f7f5a4a7d86768845c0257d55cdbd2536b784dd15c4a9f010b880"},"schema_version":"1.0","source":{"id":"2402.12847","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12847","created_at":"2026-07-05T08:23:18Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12847v2","created_at":"2026-07-05T08:23:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12847","created_at":"2026-07-05T08:23:18Z"},{"alias_kind":"pith_short_12","alias_value":"ZK5G2SYAE32I","created_at":"2026-07-05T08:23:18Z"},{"alias_kind":"pith_short_16","alias_value":"ZK5G2SYAE32IHFH3","created_at":"2026-07-05T08:23:18Z"},{"alias_kind":"pith_short_8","alias_value":"ZK5G2SYA","created_at":"2026-07-05T08:23:18Z"}],"graph_snapshots":[{"event_id":"sha256:84966117501e8be834ba63f5464c6b0f541ee804d159b9f6a115f9142e16b161","target":"graph","created_at":"2026-07-05T08:23:18Z","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/2402.12847/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In order for large language model (LLM)-based assistants to effectively adapt to evolving information needs, it must be possible to update their factual knowledge through continued training on new data. The standard recipe for doing so involves continued pre-training on new documents followed by instruction-tuning on question-answer (QA) pairs. However, we find that LLMs trained with this recipe struggle to answer questions, even though the perplexity of documents is minimized. We found that QA pairs are generally straightforward, while documents are more complex, weaving many factual statemen","authors_text":"Chunting Zhou, Graham Neubig, Pedro Rodriguez, Srinivasan Iyer, Weijia Shi, Wen-tau Yih, Xi Victoria Lin, Zhengbao Jiang, Zhiqing Sun","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T09:20:32Z","title":"Instruction-tuned Language Models are Better Knowledge Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12847","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":"sha256:97b7173d8108495bfd6b7ae6d6e872cf512d9de8173a9c2dec66da377a57e4c1","target":"record","created_at":"2026-07-05T08:23:18Z","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":"15ec47d14fb98a8acd3a0808257f087dfc27ab78e7c670634350eb7ec87c25e3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T09:20:32Z","title_canon_sha256":"cbc6780e455f7f5a4a7d86768845c0257d55cdbd2536b784dd15c4a9f010b880"},"schema_version":"1.0","source":{"id":"2402.12847","kind":"arxiv","version":2}},"canonical_sha256":"caba6d4b0026f48394fb50a086170bd4ba6c90dbcacd81ece57223786b55eb4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"caba6d4b0026f48394fb50a086170bd4ba6c90dbcacd81ece57223786b55eb4b","first_computed_at":"2026-07-05T08:23:18.315726Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:18.315726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WYQ+tuV70q0XCO+3+U90joO/b3xHk+3PLUS/JLNRkI46TlnPVMUtTAvOmBN3wNlgP3Vi2cdDH9bSGiHCaZasBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:18.316304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12847","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97b7173d8108495bfd6b7ae6d6e872cf512d9de8173a9c2dec66da377a57e4c1","sha256:84966117501e8be834ba63f5464c6b0f541ee804d159b9f6a115f9142e16b161"],"state_sha256":"326dd64a38100764cdf7dfe8843cd5b1448dece0b3c80fdb98af931a93169089"}