{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JEEPV7J6USTKJSRQY4QGGUU52C","short_pith_number":"pith:JEEPV7J6","canonical_record":{"source":{"id":"2501.09368","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-16T08:27:40Z","cross_cats_sorted":[],"title_canon_sha256":"eda60d2cad23d13f52542a6c5ddd9e34d1eccf0762bafecb651fce575b0708bf","abstract_canon_sha256":"8521e1d6d81e577f1c4fc1239508b81df6c90caa57b7cf41658dce198eadc778"},"schema_version":"1.0"},"canonical_sha256":"4908fafd3ea4a6a4ca30c72063529dd09591f21ab4e047072710c6a19c6242ea","source":{"kind":"arxiv","id":"2501.09368","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JEEPV7J6USTKJSRQY4QGGUU52C","target":"record","payload":{"canonical_record":{"source":{"id":"2501.09368","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-16T08:27:40Z","cross_cats_sorted":[],"title_canon_sha256":"eda60d2cad23d13f52542a6c5ddd9e34d1eccf0762bafecb651fce575b0708bf","abstract_canon_sha256":"8521e1d6d81e577f1c4fc1239508b81df6c90caa57b7cf41658dce198eadc778"},"schema_version":"1.0"},"canonical_sha256":"4908fafd3ea4a6a4ca30c72063529dd09591f21ab4e047072710c6a19c6242ea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:21.027374Z","signature_b64":"plCX6ak0tLZFpIJH+PE40NytJLOeI8D5SP0atH6eV1apY3qsp/Rgey8cskw4cj2Q03Gul2E4Wks1hMz4PPy7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4908fafd3ea4a6a4ca30c72063529dd09591f21ab4e047072710c6a19c6242ea","last_reissued_at":"2026-07-05T11:51:21.026885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:21.026885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.09368","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:51:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A0mKjNZU2HtTrraHYrXtOZyXWk+fN46D0xQb8ALDrIdlTYRLa5MjJj6XWjczP6QE1NmAL7PMsyoCxcy8YxvlBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:49:34.814879Z"},"content_sha256":"2ae34c38dbef1e38ad950f8094c4dbf45e64488a51173f572ca153e785f3fde4","schema_version":"1.0","event_id":"sha256:2ae34c38dbef1e38ad950f8094c4dbf45e64488a51173f572ca153e785f3fde4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JEEPV7J6USTKJSRQY4QGGUU52C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligning Instruction Tuning with Pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","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","submitted_at":"2025-01-16T08:27:40Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09368","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.09368/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:51:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R2ZVmZ0UBQstbnJG+6YogCOjIIgtawvu5yVTEToNxJ72GmwCk+xdBLT8f6zybgVl0XPPFX60fs+DDOB1b84vCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:49:34.815389Z"},"content_sha256":"7a0952acf438c77511b0847d156072ff5749cdd53c633891215144e56c0bcc88","schema_version":"1.0","event_id":"sha256:7a0952acf438c77511b0847d156072ff5749cdd53c633891215144e56c0bcc88"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JEEPV7J6USTKJSRQY4QGGUU52C/bundle.json","state_url":"https://pith.science/pith/JEEPV7J6USTKJSRQY4QGGUU52C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JEEPV7J6USTKJSRQY4QGGUU52C/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T04:49:34Z","links":{"resolver":"https://pith.science/pith/JEEPV7J6USTKJSRQY4QGGUU52C","bundle":"https://pith.science/pith/JEEPV7J6USTKJSRQY4QGGUU52C/bundle.json","state":"https://pith.science/pith/JEEPV7J6USTKJSRQY4QGGUU52C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JEEPV7J6USTKJSRQY4QGGUU52C/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NUWJqmL/4+L++A9557L+PrtJldSAEw3CbgPRe0Wd9RYLCRMyFMWOWz1cVOC/7O45nTFHW9s6miNoHHdFi/oxBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T04:49:34.819089Z","bundle_sha256":"c6daeb838d0fab467dcf93c2dc1c9274d7bf60ad5a82dc791af6aab6a5cbd519"}}