{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NGLIF2E7O7IWE6N2H24RDEQNE3","short_pith_number":"pith:NGLIF2E7","schema_version":"1.0","canonical_sha256":"699682e89f77d16279ba3eb911920d26e5dbaa0e52e824414d3c3f4b780fd1be","source":{"kind":"arxiv","id":"2410.09584","version":1},"attestation_state":"computed","paper":{"title":"Toward General Instruction-Following Alignment for Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Guanting Dong, Ji-Rong Wen, Runqi Qiao, Xiaoshuai Song, Yutao Zhu, Zhicheng Dou","submitted_at":"2024-10-12T16:30:51Z","abstract_excerpt":"Following natural instructions is crucial for the effective application of Retrieval-Augmented Generation (RAG) systems. Despite recent advancements in Large Language Models (LLMs), research on assessing and improving instruction-following (IF) alignment within the RAG domain remains limited. To address this issue, we propose VIF-RAG, the first automated, scalable, and verifiable synthetic pipeline for instruction-following alignment in RAG systems. We start by manually crafting a minimal set of atomic instructions (<100) and developing combination rules to synthesize and verify complex instru"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.09584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-12T16:30:51Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"e166bac0ccca7d5052066275eebcf91265db8bae06e3f7ed8b26d271400b80f2","abstract_canon_sha256":"87a9594a4da9bdad38e8fcdc65ce9a0d79f68d3a754742618fd5b9fa38d17cac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:41.117537Z","signature_b64":"7z4DP1fnwPbNBAAWjaPsL1eQQ8ilQR8fkOS+qo34FETE7GQaQ1e7Cl8d2U2MlQ/hdd2Cw98NsdSPF8RE5Af7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"699682e89f77d16279ba3eb911920d26e5dbaa0e52e824414d3c3f4b780fd1be","last_reissued_at":"2026-07-05T09:19:41.117076Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:41.117076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward General Instruction-Following Alignment for Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Guanting Dong, Ji-Rong Wen, Runqi Qiao, Xiaoshuai Song, Yutao Zhu, Zhicheng Dou","submitted_at":"2024-10-12T16:30:51Z","abstract_excerpt":"Following natural instructions is crucial for the effective application of Retrieval-Augmented Generation (RAG) systems. Despite recent advancements in Large Language Models (LLMs), research on assessing and improving instruction-following (IF) alignment within the RAG domain remains limited. To address this issue, we propose VIF-RAG, the first automated, scalable, and verifiable synthetic pipeline for instruction-following alignment in RAG systems. We start by manually crafting a minimal set of atomic instructions (<100) and developing combination rules to synthesize and verify complex instru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09584","kind":"arxiv","version":1},"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/2410.09584/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.09584","created_at":"2026-07-05T09:19:41.117132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09584v1","created_at":"2026-07-05T09:19:41.117132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09584","created_at":"2026-07-05T09:19:41.117132+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGLIF2E7O7IW","created_at":"2026-07-05T09:19:41.117132+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGLIF2E7O7IWE6N2","created_at":"2026-07-05T09:19:41.117132+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGLIF2E7","created_at":"2026-07-05T09:19:41.117132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07539","citing_title":"Prompt Governance? On Governing Technologies Governed by Natural Language","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29960","citing_title":"IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2501.05366","citing_title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NGLIF2E7O7IWE6N2H24RDEQNE3","json":"https://pith.science/pith/NGLIF2E7O7IWE6N2H24RDEQNE3.json","graph_json":"https://pith.science/api/pith-number/NGLIF2E7O7IWE6N2H24RDEQNE3/graph.json","events_json":"https://pith.science/api/pith-number/NGLIF2E7O7IWE6N2H24RDEQNE3/events.json","paper":"https://pith.science/paper/NGLIF2E7"},"agent_actions":{"view_html":"https://pith.science/pith/NGLIF2E7O7IWE6N2H24RDEQNE3","download_json":"https://pith.science/pith/NGLIF2E7O7IWE6N2H24RDEQNE3.json","view_paper":"https://pith.science/paper/NGLIF2E7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09584&json=true","fetch_graph":"https://pith.science/api/pith-number/NGLIF2E7O7IWE6N2H24RDEQNE3/graph.json","fetch_events":"https://pith.science/api/pith-number/NGLIF2E7O7IWE6N2H24RDEQNE3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGLIF2E7O7IWE6N2H24RDEQNE3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGLIF2E7O7IWE6N2H24RDEQNE3/action/storage_attestation","attest_author":"https://pith.science/pith/NGLIF2E7O7IWE6N2H24RDEQNE3/action/author_attestation","sign_citation":"https://pith.science/pith/NGLIF2E7O7IWE6N2H24RDEQNE3/action/citation_signature","submit_replication":"https://pith.science/pith/NGLIF2E7O7IWE6N2H24RDEQNE3/action/replication_record"}},"created_at":"2026-07-05T09:19:41.117132+00:00","updated_at":"2026-07-05T09:19:41.117132+00:00"}