{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TMJ2XM2ZXXC7BVLZPXQNOLEK6I","short_pith_number":"pith:TMJ2XM2Z","schema_version":"1.0","canonical_sha256":"9b13abb359bdc5f0d5797de0d72c8af202ba95c6676ee75fd95747a375730f92","source":{"kind":"arxiv","id":"2405.20978","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Feiteng Fang, Min Yang, Ruifeng Xu, Shiwen Ni, Xiaojun Chen, Yuelin Bai","submitted_at":"2024-05-31T16:24:53Z","abstract_excerpt":"Large Language Models (LLMs) exhibit substantial capabilities yet encounter challenges, including hallucination, outdated knowledge, and untraceable reasoning processes. Retrieval-augmented generation (RAG) has emerged as a promising solution, integrating knowledge from external databases to mitigate these challenges. However, inappropriate retrieved passages can potentially hinder the LLMs' capacity to generate comprehensive and high-quality responses. Prior RAG studies on the robustness of retrieval noises often confine themselves to a limited set of noise types, deviating from real-world re"},"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":"2405.20978","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-31T16:24:53Z","cross_cats_sorted":[],"title_canon_sha256":"5eb27d9bf945ed52c588076db765705838f7257ede9f95b4202c2b7a3ba39b60","abstract_canon_sha256":"2a5ea51e7ffbe80231254aae135b3b188a26b8601734ec4d9c8ae017c038be4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:44.292446Z","signature_b64":"TNRTAfiUn4yRyO+A1ddt8XUtLADPuEnpj/s+JKKWpj69iSoamexiAvz8gcCwjWWNAUInEM0qhgaJFO4V8tc5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b13abb359bdc5f0d5797de0d72c8af202ba95c6676ee75fd95747a375730f92","last_reissued_at":"2026-07-05T08:25:44.292030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:44.292030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Feiteng Fang, Min Yang, Ruifeng Xu, Shiwen Ni, Xiaojun Chen, Yuelin Bai","submitted_at":"2024-05-31T16:24:53Z","abstract_excerpt":"Large Language Models (LLMs) exhibit substantial capabilities yet encounter challenges, including hallucination, outdated knowledge, and untraceable reasoning processes. Retrieval-augmented generation (RAG) has emerged as a promising solution, integrating knowledge from external databases to mitigate these challenges. However, inappropriate retrieved passages can potentially hinder the LLMs' capacity to generate comprehensive and high-quality responses. Prior RAG studies on the robustness of retrieval noises often confine themselves to a limited set of noise types, deviating from real-world re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20978","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/2405.20978/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":"2405.20978","created_at":"2026-07-05T08:25:44.292085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20978v1","created_at":"2026-07-05T08:25:44.292085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20978","created_at":"2026-07-05T08:25:44.292085+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMJ2XM2ZXXC7","created_at":"2026-07-05T08:25:44.292085+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMJ2XM2ZXXC7BVLZ","created_at":"2026-07-05T08:25:44.292085+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMJ2XM2Z","created_at":"2026-07-05T08:25:44.292085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.13957","citing_title":"Supervising the search process produces reliable and generalizable information-seeking agents","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24332","citing_title":"Mitigating Error Amplification in Fast Adversarial Training","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24350","citing_title":"Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13275","citing_title":"Better and Worse with Scale: How Contextual Entrainment Diverges with Model Size","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TMJ2XM2ZXXC7BVLZPXQNOLEK6I","json":"https://pith.science/pith/TMJ2XM2ZXXC7BVLZPXQNOLEK6I.json","graph_json":"https://pith.science/api/pith-number/TMJ2XM2ZXXC7BVLZPXQNOLEK6I/graph.json","events_json":"https://pith.science/api/pith-number/TMJ2XM2ZXXC7BVLZPXQNOLEK6I/events.json","paper":"https://pith.science/paper/TMJ2XM2Z"},"agent_actions":{"view_html":"https://pith.science/pith/TMJ2XM2ZXXC7BVLZPXQNOLEK6I","download_json":"https://pith.science/pith/TMJ2XM2ZXXC7BVLZPXQNOLEK6I.json","view_paper":"https://pith.science/paper/TMJ2XM2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20978&json=true","fetch_graph":"https://pith.science/api/pith-number/TMJ2XM2ZXXC7BVLZPXQNOLEK6I/graph.json","fetch_events":"https://pith.science/api/pith-number/TMJ2XM2ZXXC7BVLZPXQNOLEK6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMJ2XM2ZXXC7BVLZPXQNOLEK6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMJ2XM2ZXXC7BVLZPXQNOLEK6I/action/storage_attestation","attest_author":"https://pith.science/pith/TMJ2XM2ZXXC7BVLZPXQNOLEK6I/action/author_attestation","sign_citation":"https://pith.science/pith/TMJ2XM2ZXXC7BVLZPXQNOLEK6I/action/citation_signature","submit_replication":"https://pith.science/pith/TMJ2XM2ZXXC7BVLZPXQNOLEK6I/action/replication_record"}},"created_at":"2026-07-05T08:25:44.292085+00:00","updated_at":"2026-07-05T08:25:44.292085+00:00"}