{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YIMQP2JSNDVFWD33ICWISNB7ER","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":"83e6346298fa371b45c4bbb7d578093ef878697a37bcdc0c1c088e4e28370002","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T09:00:51Z","title_canon_sha256":"9b319eccb59454204d9887033b653c640edbccfc856863f0fc6e0d4f934a6eb5"},"schema_version":"1.0","source":{"id":"2501.00353","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00353","created_at":"2026-07-05T09:55:43Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00353v1","created_at":"2026-07-05T09:55:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00353","created_at":"2026-07-05T09:55:43Z"},{"alias_kind":"pith_short_12","alias_value":"YIMQP2JSNDVF","created_at":"2026-07-05T09:55:43Z"},{"alias_kind":"pith_short_16","alias_value":"YIMQP2JSNDVFWD33","created_at":"2026-07-05T09:55:43Z"},{"alias_kind":"pith_short_8","alias_value":"YIMQP2JS","created_at":"2026-07-05T09:55:43Z"}],"graph_snapshots":[{"event_id":"sha256:8888c2e8b4c8e16de41232f26b2f6452f353f8e141179a44fe594b6f7590928f","target":"graph","created_at":"2026-07-05T09:55:43Z","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/2501.00353/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) has emerged as a key paradigm for enhancing large language models (LLMs) by incorporating external knowledge. However, current RAG methods face two limitations: (1) they only cover limited RAG scenarios. (2) They suffer from limited task diversity due to the lack of a general RAG dataset. To address these limitations, we propose RAG-Instruct, a general method for synthesizing diverse and high-quality RAG instruction data based on any source corpus. Our approach leverages (1) five RAG paradigms, which encompass diverse query-document relationships, and (2) i","authors_text":"Benyou Wang, Junying Chen, Ke Ji, Li Zhou, Wanlong Liu, Wenyu Chen","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T09:00:51Z","title":"RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00353","kind":"arxiv","version":1},"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":"sha256:611d118203c7c4bda4fc5cb4e2059dac6c8cce3c00f80679170d93141c20c1e4","target":"record","created_at":"2026-07-05T09:55:43Z","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":"83e6346298fa371b45c4bbb7d578093ef878697a37bcdc0c1c088e4e28370002","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T09:00:51Z","title_canon_sha256":"9b319eccb59454204d9887033b653c640edbccfc856863f0fc6e0d4f934a6eb5"},"schema_version":"1.0","source":{"id":"2501.00353","kind":"arxiv","version":1}},"canonical_sha256":"c21907e93268ea5b0f7b40ac89343f24757e75a5a81d3c646aa29a41c85a8318","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c21907e93268ea5b0f7b40ac89343f24757e75a5a81d3c646aa29a41c85a8318","first_computed_at":"2026-07-05T09:55:43.627920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:43.627920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sosKxTxVZWXca6nJCI9jVM6cMHVvLPKo6Lbqpnma2G+Zoo9C4ZiBUYqvrrC9GPHVbmvk24FlTbGfEU6d34afBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:43.628397Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00353","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:611d118203c7c4bda4fc5cb4e2059dac6c8cce3c00f80679170d93141c20c1e4","sha256:8888c2e8b4c8e16de41232f26b2f6452f353f8e141179a44fe594b6f7590928f"],"state_sha256":"01f5c4d266d0abd005e2d7ceaecad290fe383b0f4c3cccc54fc917d7f8126b85"}