{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PBHTUBKTORVEDTXT36VYDVDEFV","short_pith_number":"pith:PBHTUBKT","schema_version":"1.0","canonical_sha256":"784f3a0553746a41cef3dfab81d4642d5a9ab5d24f5bce8d76a74984a20346d5","source":{"kind":"arxiv","id":"2505.08643","version":1},"attestation_state":"computed","paper":{"title":"WixQA: A Multi-Dataset Benchmark for Enterprise Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Dvir Cohen, Gilad Barkan, Hagit Gur, Lin Burg, Olga Atzmon, Stanislav Kovynov, Sviatoslav Pykhnivskyi","submitted_at":"2025-05-13T15:02:54Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) is a cornerstone of modern question answering (QA) systems, enabling grounded answers based on external knowledge. Although recent progress has been driven by open-domain datasets, enterprise QA systems need datasets that mirror the concrete, domain-specific issues users raise in day-to-day support scenarios. Critically, evaluating end-to-end RAG systems requires benchmarks comprising not only question--answer pairs but also the specific knowledge base (KB) snapshot from which answers were derived. To address this need, we introduce WixQA, a benchmark suite"},"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":"2505.08643","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-13T15:02:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5f1357a047645a27ff97a8ebde6e050b1b863f3779593a9c9d9f93af2398a13b","abstract_canon_sha256":"f2788f152d30d14c48d2519193df01685fa170e6ab7244334b3bed88f98f1e70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:34.025266Z","signature_b64":"r6n9xOb+oNxefeEePi8L2Q4QZxlrI5nF604+g3IiKVJmAKD8yjTvWSk6axLj/Nbno7Cw8VG1qTixz34QJZJJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"784f3a0553746a41cef3dfab81d4642d5a9ab5d24f5bce8d76a74984a20346d5","last_reissued_at":"2026-07-05T11:02:34.024787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:34.024787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WixQA: A Multi-Dataset Benchmark for Enterprise Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Dvir Cohen, Gilad Barkan, Hagit Gur, Lin Burg, Olga Atzmon, Stanislav Kovynov, Sviatoslav Pykhnivskyi","submitted_at":"2025-05-13T15:02:54Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) is a cornerstone of modern question answering (QA) systems, enabling grounded answers based on external knowledge. Although recent progress has been driven by open-domain datasets, enterprise QA systems need datasets that mirror the concrete, domain-specific issues users raise in day-to-day support scenarios. Critically, evaluating end-to-end RAG systems requires benchmarks comprising not only question--answer pairs but also the specific knowledge base (KB) snapshot from which answers were derived. To address this need, we introduce WixQA, a benchmark suite"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08643","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/2505.08643/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":"2505.08643","created_at":"2026-07-05T11:02:34.024839+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.08643v1","created_at":"2026-07-05T11:02:34.024839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08643","created_at":"2026-07-05T11:02:34.024839+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBHTUBKTORVE","created_at":"2026-07-05T11:02:34.024839+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBHTUBKTORVEDTXT","created_at":"2026-07-05T11:02:34.024839+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBHTUBKT","created_at":"2026-07-05T11:02:34.024839+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31156","citing_title":"One Retrieval to Cover Them All: Co-occurrence-Aware Knowledge Base Reorganization for Session-Level RAG","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26891","citing_title":"Telenor Nordics Customer Service self-help corpus","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05538","citing_title":"AgenticRAG: Agentic Retrieval for Enterprise Knowledge Bases","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PBHTUBKTORVEDTXT36VYDVDEFV","json":"https://pith.science/pith/PBHTUBKTORVEDTXT36VYDVDEFV.json","graph_json":"https://pith.science/api/pith-number/PBHTUBKTORVEDTXT36VYDVDEFV/graph.json","events_json":"https://pith.science/api/pith-number/PBHTUBKTORVEDTXT36VYDVDEFV/events.json","paper":"https://pith.science/paper/PBHTUBKT"},"agent_actions":{"view_html":"https://pith.science/pith/PBHTUBKTORVEDTXT36VYDVDEFV","download_json":"https://pith.science/pith/PBHTUBKTORVEDTXT36VYDVDEFV.json","view_paper":"https://pith.science/paper/PBHTUBKT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.08643&json=true","fetch_graph":"https://pith.science/api/pith-number/PBHTUBKTORVEDTXT36VYDVDEFV/graph.json","fetch_events":"https://pith.science/api/pith-number/PBHTUBKTORVEDTXT36VYDVDEFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBHTUBKTORVEDTXT36VYDVDEFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBHTUBKTORVEDTXT36VYDVDEFV/action/storage_attestation","attest_author":"https://pith.science/pith/PBHTUBKTORVEDTXT36VYDVDEFV/action/author_attestation","sign_citation":"https://pith.science/pith/PBHTUBKTORVEDTXT36VYDVDEFV/action/citation_signature","submit_replication":"https://pith.science/pith/PBHTUBKTORVEDTXT36VYDVDEFV/action/replication_record"}},"created_at":"2026-07-05T11:02:34.024839+00:00","updated_at":"2026-07-05T11:02:34.024839+00:00"}