{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OHF4FMDVZ6CQF2ZVE6OYMPHL3D","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":"d4fe442e93508a6a66512a47103f359e8722d4ae4a882d7e1a4dda585446d8f7","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T17:59:17Z","title_canon_sha256":"b2eb4f2457a09f6fc8b784e59d3c9f22f64fd15a32e15938e15ea6ec9b9aa6fa"},"schema_version":"1.0","source":{"id":"2407.02485","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02485","created_at":"2026-07-05T08:39:24Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02485v1","created_at":"2026-07-05T08:39:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02485","created_at":"2026-07-05T08:39:24Z"},{"alias_kind":"pith_short_12","alias_value":"OHF4FMDVZ6CQ","created_at":"2026-07-05T08:39:24Z"},{"alias_kind":"pith_short_16","alias_value":"OHF4FMDVZ6CQF2ZV","created_at":"2026-07-05T08:39:24Z"},{"alias_kind":"pith_short_8","alias_value":"OHF4FMDV","created_at":"2026-07-05T08:39:24Z"}],"graph_snapshots":[{"event_id":"sha256:eeb8438e128984e3d2762ea82f12df3eccfb4e4f7eabaa16f03bcec235bb7d1b","target":"graph","created_at":"2026-07-05T08:39:24Z","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/2407.02485/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) typically utilize the top-k contexts from a retriever in retrieval-augmented generation (RAG). In this work, we propose a novel instruction fine-tuning framework RankRAG, which instruction-tunes a single LLM for the dual purpose of context ranking and answer generation in RAG. In particular, the instruction-tuned LLMs work surprisingly well by adding a small fraction of ranking data into the training blend, and outperform existing expert ranking models, including the same LLM exclusively fine-tuned on a large amount of ranking data. For generation, we compare our m","authors_text":"Boxin Wang, Bryan Catanzaro, Chao Zhang, Jiaxuan You, Mohammad Shoeybi, Wei Ping, Yue Yu, Zihan Liu","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T17:59:17Z","title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02485","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":"sha256:552789677ff39e9c7b86341e674553b89ff1b1803efb607ce87dde5a7c3191b9","target":"record","created_at":"2026-07-05T08:39:24Z","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":"d4fe442e93508a6a66512a47103f359e8722d4ae4a882d7e1a4dda585446d8f7","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T17:59:17Z","title_canon_sha256":"b2eb4f2457a09f6fc8b784e59d3c9f22f64fd15a32e15938e15ea6ec9b9aa6fa"},"schema_version":"1.0","source":{"id":"2407.02485","kind":"arxiv","version":1}},"canonical_sha256":"71cbc2b075cf8502eb35279d863cebd8d9f112f6d9bff7453219d112be5b1293","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71cbc2b075cf8502eb35279d863cebd8d9f112f6d9bff7453219d112be5b1293","first_computed_at":"2026-07-05T08:39:24.590831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:24.590831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jozRF+Uwc6YQ41ifoN/ltTSIpWY0AChTzCpxbeQQWtTu+/tQDbBB8gE5uzuxmvN2smGCW0sWz48qMkWnD/g7CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:24.591233Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02485","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:552789677ff39e9c7b86341e674553b89ff1b1803efb607ce87dde5a7c3191b9","sha256:eeb8438e128984e3d2762ea82f12df3eccfb4e4f7eabaa16f03bcec235bb7d1b"],"state_sha256":"3d86a9476bdd0b87e559e1bf3bbb5249707ab2a99c5c52c3cdf998e8bb95a6bf"}