{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JEEPV7J6USTKJSRQY4QGGUU52C","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":"8521e1d6d81e577f1c4fc1239508b81df6c90caa57b7cf41658dce198eadc778","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-16T08:27:40Z","title_canon_sha256":"eda60d2cad23d13f52542a6c5ddd9e34d1eccf0762bafecb651fce575b0708bf"},"schema_version":"1.0","source":{"id":"2501.09368","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09368","created_at":"2026-07-05T11:51:21Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09368v4","created_at":"2026-07-05T11:51:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09368","created_at":"2026-07-05T11:51:21Z"},{"alias_kind":"pith_short_12","alias_value":"JEEPV7J6USTK","created_at":"2026-07-05T11:51:21Z"},{"alias_kind":"pith_short_16","alias_value":"JEEPV7J6USTKJSRQ","created_at":"2026-07-05T11:51:21Z"},{"alias_kind":"pith_short_8","alias_value":"JEEPV7J6","created_at":"2026-07-05T11:51:21Z"}],"graph_snapshots":[{"event_id":"sha256:7a0952acf438c77511b0847d156072ff5749cdd53c633891215144e56c0bcc88","target":"graph","created_at":"2026-07-05T11:51:21Z","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/2501.09368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning enhances large language models (LLMs) to follow human instructions across diverse tasks, relying on high-quality datasets to guide behavior. However, these datasets, whether manually curated or synthetically generated, are often narrowly focused and misaligned with the broad distributions captured during pre-training, limiting LLM generalization and effective use of pre-trained knowledge. We propose Aligning Instruction Tuning with Pre-training (AITP), a method that bridges this gap by identifying coverage shortfalls in instruction-tuning datasets and rewriting underrepresen","authors_text":"Chujie Zheng, Ge Zhang, Guoyin Wang, Jiaheng Liu, Jiajun Zhang, Lei Ma, Tianyu Zheng, Wenhao Huang, Wenqiang Zu, Xiang Yue, Xingrun Xing, Xingwei Qu, Xinrun Du, Yiming Liang, Zhaoxiang Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-16T08:27:40Z","title":"Aligning Instruction Tuning with Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09368","kind":"arxiv","version":4},"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":"sha256:2ae34c38dbef1e38ad950f8094c4dbf45e64488a51173f572ca153e785f3fde4","target":"record","created_at":"2026-07-05T11:51:21Z","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":"8521e1d6d81e577f1c4fc1239508b81df6c90caa57b7cf41658dce198eadc778","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-16T08:27:40Z","title_canon_sha256":"eda60d2cad23d13f52542a6c5ddd9e34d1eccf0762bafecb651fce575b0708bf"},"schema_version":"1.0","source":{"id":"2501.09368","kind":"arxiv","version":4}},"canonical_sha256":"4908fafd3ea4a6a4ca30c72063529dd09591f21ab4e047072710c6a19c6242ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4908fafd3ea4a6a4ca30c72063529dd09591f21ab4e047072710c6a19c6242ea","first_computed_at":"2026-07-05T11:51:21.026885Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:21.026885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"plCX6ak0tLZFpIJH+PE40NytJLOeI8D5SP0atH6eV1apY3qsp/Rgey8cskw4cj2Q03Gul2E4Wks1hMz4PPy7Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:21.027374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.09368","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ae34c38dbef1e38ad950f8094c4dbf45e64488a51173f572ca153e785f3fde4","sha256:7a0952acf438c77511b0847d156072ff5749cdd53c633891215144e56c0bcc88"],"state_sha256":"3079b94ac3ad053058d867d729723093771c46536e3d92dc1152073ef3109cf0"}