{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZJU7DOIYDIPPNEFJNVCSMIYBOI","short_pith_number":"pith:ZJU7DOIY","schema_version":"1.0","canonical_sha256":"ca69f1b9181a1ef690a96d45262301723b559b2572fb41cb54eb0bf2a541e91a","source":{"kind":"arxiv","id":"2501.14998","version":1},"attestation_state":"computed","paper":{"title":"Federated Retrieval Augmented Generation for Multi-Product Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akash Maharaj, Dan Luo, Parshin Shojaee, Sai Sree Harsha, Tong Yu, Yunyao Li","submitted_at":"2025-01-25T00:22:27Z","abstract_excerpt":"Recent advancements in Large Language Models and Retrieval-Augmented Generation have boosted interest in domain-specific question-answering for enterprise products. However, AI Assistants often face challenges in multi-product QA settings, requiring accurate responses across diverse domains. Existing multi-domain RAG-QA approaches either query all domains indiscriminately, increasing computational costs and LLM hallucinations, or rely on rigid resource selection, which can limit search results. We introduce MKP-QA, a novel multi-product knowledge-augmented QA framework with probabilistic feder"},"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":"2501.14998","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-25T00:22:27Z","cross_cats_sorted":[],"title_canon_sha256":"c66e1c87218388a8a45129154efdfaca0a946a670ab91d62ab5a92c54ec8765f","abstract_canon_sha256":"dc7ae4383a5263d4cd804e7e778150df25feccf8179f9c7c764e5340d032df4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:21.961014Z","signature_b64":"4ESOKG4wO5SmfmdHHHU7ZbRH9LeqQo2FghnErzV4Ga4A5oTerwu3ZzY4+eidXHGXgtKVdZybxIdoApQdC1SZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca69f1b9181a1ef690a96d45262301723b559b2572fb41cb54eb0bf2a541e91a","last_reissued_at":"2026-07-05T10:05:21.960431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:21.960431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Retrieval Augmented Generation for Multi-Product Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akash Maharaj, Dan Luo, Parshin Shojaee, Sai Sree Harsha, Tong Yu, Yunyao Li","submitted_at":"2025-01-25T00:22:27Z","abstract_excerpt":"Recent advancements in Large Language Models and Retrieval-Augmented Generation have boosted interest in domain-specific question-answering for enterprise products. However, AI Assistants often face challenges in multi-product QA settings, requiring accurate responses across diverse domains. Existing multi-domain RAG-QA approaches either query all domains indiscriminately, increasing computational costs and LLM hallucinations, or rely on rigid resource selection, which can limit search results. We introduce MKP-QA, a novel multi-product knowledge-augmented QA framework with probabilistic feder"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14998","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/2501.14998/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":"2501.14998","created_at":"2026-07-05T10:05:21.960489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14998v1","created_at":"2026-07-05T10:05:21.960489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14998","created_at":"2026-07-05T10:05:21.960489+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJU7DOIYDIPP","created_at":"2026-07-05T10:05:21.960489+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJU7DOIYDIPPNEFJ","created_at":"2026-07-05T10:05:21.960489+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJU7DOIY","created_at":"2026-07-05T10:05:21.960489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18906","citing_title":"Federated Retrieval-Augmented Generation: A Systematic Mapping Study","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJU7DOIYDIPPNEFJNVCSMIYBOI","json":"https://pith.science/pith/ZJU7DOIYDIPPNEFJNVCSMIYBOI.json","graph_json":"https://pith.science/api/pith-number/ZJU7DOIYDIPPNEFJNVCSMIYBOI/graph.json","events_json":"https://pith.science/api/pith-number/ZJU7DOIYDIPPNEFJNVCSMIYBOI/events.json","paper":"https://pith.science/paper/ZJU7DOIY"},"agent_actions":{"view_html":"https://pith.science/pith/ZJU7DOIYDIPPNEFJNVCSMIYBOI","download_json":"https://pith.science/pith/ZJU7DOIYDIPPNEFJNVCSMIYBOI.json","view_paper":"https://pith.science/paper/ZJU7DOIY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14998&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJU7DOIYDIPPNEFJNVCSMIYBOI/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJU7DOIYDIPPNEFJNVCSMIYBOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJU7DOIYDIPPNEFJNVCSMIYBOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJU7DOIYDIPPNEFJNVCSMIYBOI/action/storage_attestation","attest_author":"https://pith.science/pith/ZJU7DOIYDIPPNEFJNVCSMIYBOI/action/author_attestation","sign_citation":"https://pith.science/pith/ZJU7DOIYDIPPNEFJNVCSMIYBOI/action/citation_signature","submit_replication":"https://pith.science/pith/ZJU7DOIYDIPPNEFJNVCSMIYBOI/action/replication_record"}},"created_at":"2026-07-05T10:05:21.960489+00:00","updated_at":"2026-07-05T10:05:21.960489+00:00"}