{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:46M5OIGU2I5I2PPCOEOI72NN4M","short_pith_number":"pith:46M5OIGU","schema_version":"1.0","canonical_sha256":"e799d720d4d23a8d3de2711c8fe9ade31a44ff3b82aa48a4e83e3f1e52b2c0c7","source":{"kind":"arxiv","id":"2508.20131","version":1},"attestation_state":"computed","paper":{"title":"ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bo Xiong, Daniel Hern\\'andez, Dongzhuoran Zhou, Evgeny Kharlamov, Nico Potyka, Steffen Staab, Yuan He, Yuqicheng Zhu, Zifeng Ding","submitted_at":"2025-08-26T13:54:51Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, yet suffers from critical limitations in high-stakes domains -- namely, sensitivity to noisy or contradictory evidence and opaque, stochastic decision-making. We propose ArgRAG, an explainable, and contestable alternative that replaces black-box reasoning with structured inference using a Quantitative Bipolar Argumentation Framework (QBAF). ArgRAG constructs a QBAF from retrieved documents and performs deterministic reasoning under gradual semantics. This allows faithfully explaining and co"},"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":"2508.20131","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-26T13:54:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bf81ebdef065bc2e227a95ac1490afed8f1f30f0427053200a55b1f3de276275","abstract_canon_sha256":"117d01ab75c45709d085f86b924c797d004176906f5f80fdd01b5e3ba70b17a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:30.029641Z","signature_b64":"RdHAK+qskTHlV4NrpP4N5pU1qy6wWEef4SiyHMrKDbZSjs3Xggz8jpL+VQS36kDvXBgnMcvUq9+YTY5MLQYkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e799d720d4d23a8d3de2711c8fe9ade31a44ff3b82aa48a4e83e3f1e52b2c0c7","last_reissued_at":"2026-07-05T12:00:30.029116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:30.029116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bo Xiong, Daniel Hern\\'andez, Dongzhuoran Zhou, Evgeny Kharlamov, Nico Potyka, Steffen Staab, Yuan He, Yuqicheng Zhu, Zifeng Ding","submitted_at":"2025-08-26T13:54:51Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, yet suffers from critical limitations in high-stakes domains -- namely, sensitivity to noisy or contradictory evidence and opaque, stochastic decision-making. We propose ArgRAG, an explainable, and contestable alternative that replaces black-box reasoning with structured inference using a Quantitative Bipolar Argumentation Framework (QBAF). ArgRAG constructs a QBAF from retrieved documents and performs deterministic reasoning under gradual semantics. This allows faithfully explaining and co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20131","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/2508.20131/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":"2508.20131","created_at":"2026-07-05T12:00:30.029177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20131v1","created_at":"2026-07-05T12:00:30.029177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20131","created_at":"2026-07-05T12:00:30.029177+00:00"},{"alias_kind":"pith_short_12","alias_value":"46M5OIGU2I5I","created_at":"2026-07-05T12:00:30.029177+00:00"},{"alias_kind":"pith_short_16","alias_value":"46M5OIGU2I5I2PPC","created_at":"2026-07-05T12:00:30.029177+00:00"},{"alias_kind":"pith_short_8","alias_value":"46M5OIGU","created_at":"2026-07-05T12:00:30.029177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18362","citing_title":"ArbGraph: Conflict-Aware Evidence Arbitration for Reliable Long-Form Retrieval-Augmented Generation","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/46M5OIGU2I5I2PPCOEOI72NN4M","json":"https://pith.science/pith/46M5OIGU2I5I2PPCOEOI72NN4M.json","graph_json":"https://pith.science/api/pith-number/46M5OIGU2I5I2PPCOEOI72NN4M/graph.json","events_json":"https://pith.science/api/pith-number/46M5OIGU2I5I2PPCOEOI72NN4M/events.json","paper":"https://pith.science/paper/46M5OIGU"},"agent_actions":{"view_html":"https://pith.science/pith/46M5OIGU2I5I2PPCOEOI72NN4M","download_json":"https://pith.science/pith/46M5OIGU2I5I2PPCOEOI72NN4M.json","view_paper":"https://pith.science/paper/46M5OIGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20131&json=true","fetch_graph":"https://pith.science/api/pith-number/46M5OIGU2I5I2PPCOEOI72NN4M/graph.json","fetch_events":"https://pith.science/api/pith-number/46M5OIGU2I5I2PPCOEOI72NN4M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46M5OIGU2I5I2PPCOEOI72NN4M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46M5OIGU2I5I2PPCOEOI72NN4M/action/storage_attestation","attest_author":"https://pith.science/pith/46M5OIGU2I5I2PPCOEOI72NN4M/action/author_attestation","sign_citation":"https://pith.science/pith/46M5OIGU2I5I2PPCOEOI72NN4M/action/citation_signature","submit_replication":"https://pith.science/pith/46M5OIGU2I5I2PPCOEOI72NN4M/action/replication_record"}},"created_at":"2026-07-05T12:00:30.029177+00:00","updated_at":"2026-07-05T12:00:30.029177+00:00"}