{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YGBKI3PAOL3N3A4JSZAJHZT64D","short_pith_number":"pith:YGBKI3PA","schema_version":"1.0","canonical_sha256":"c182a46de072f6dd8389964093e67ee0dc74d6c5aff8c5c154efc12c28cfde80","source":{"kind":"arxiv","id":"2508.18929","version":1},"attestation_state":"computed","paper":{"title":"Diverse And Private Synthetic Datasets Generation for RAG evaluation: A multi-agent framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eoin Thomas, Hongliu Cao, Ilias Driouich","submitted_at":"2025-08-26T11:16:14Z","abstract_excerpt":"Retrieval-augmented generation (RAG) systems improve large language model outputs by incorporating external knowledge, enabling more informed and context-aware responses. However, the effectiveness and trustworthiness of these systems critically depends on how they are evaluated, particularly on whether the evaluation process captures real-world constraints like protecting sensitive information. While current evaluation efforts for RAG systems have primarily focused on the development of performance metrics, far less attention has been given to the design and quality of the underlying evaluati"},"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":"2508.18929","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-26T11:16:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8997f83cbc3c27888b95e45743cb64f6b3ec1a7b4618d7599e00410398dc0f96","abstract_canon_sha256":"1c327bb51741e4c7a75783b7f6f1310835e0aabfce9f606a7119b0e4e4b0a66a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:33.990531Z","signature_b64":"3j2DvuLnOOz4bHM0wds0PUEkHiuFD+dgs5Dg4p7p2/Mz7ytmIRlfjGcWduUU1A9O945ERHtbvE/p3pT576ZpAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c182a46de072f6dd8389964093e67ee0dc74d6c5aff8c5c154efc12c28cfde80","last_reissued_at":"2026-07-05T11:59:33.990095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:33.990095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diverse And Private Synthetic Datasets Generation for RAG evaluation: A multi-agent framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eoin Thomas, Hongliu Cao, Ilias Driouich","submitted_at":"2025-08-26T11:16:14Z","abstract_excerpt":"Retrieval-augmented generation (RAG) systems improve large language model outputs by incorporating external knowledge, enabling more informed and context-aware responses. However, the effectiveness and trustworthiness of these systems critically depends on how they are evaluated, particularly on whether the evaluation process captures real-world constraints like protecting sensitive information. While current evaluation efforts for RAG systems have primarily focused on the development of performance metrics, far less attention has been given to the design and quality of the underlying evaluati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18929","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/2508.18929/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":"2508.18929","created_at":"2026-07-05T11:59:33.990151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18929v1","created_at":"2026-07-05T11:59:33.990151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18929","created_at":"2026-07-05T11:59:33.990151+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGBKI3PAOL3N","created_at":"2026-07-05T11:59:33.990151+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGBKI3PAOL3N3A4J","created_at":"2026-07-05T11:59:33.990151+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGBKI3PA","created_at":"2026-07-05T11:59:33.990151+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YGBKI3PAOL3N3A4JSZAJHZT64D","json":"https://pith.science/pith/YGBKI3PAOL3N3A4JSZAJHZT64D.json","graph_json":"https://pith.science/api/pith-number/YGBKI3PAOL3N3A4JSZAJHZT64D/graph.json","events_json":"https://pith.science/api/pith-number/YGBKI3PAOL3N3A4JSZAJHZT64D/events.json","paper":"https://pith.science/paper/YGBKI3PA"},"agent_actions":{"view_html":"https://pith.science/pith/YGBKI3PAOL3N3A4JSZAJHZT64D","download_json":"https://pith.science/pith/YGBKI3PAOL3N3A4JSZAJHZT64D.json","view_paper":"https://pith.science/paper/YGBKI3PA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18929&json=true","fetch_graph":"https://pith.science/api/pith-number/YGBKI3PAOL3N3A4JSZAJHZT64D/graph.json","fetch_events":"https://pith.science/api/pith-number/YGBKI3PAOL3N3A4JSZAJHZT64D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGBKI3PAOL3N3A4JSZAJHZT64D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGBKI3PAOL3N3A4JSZAJHZT64D/action/storage_attestation","attest_author":"https://pith.science/pith/YGBKI3PAOL3N3A4JSZAJHZT64D/action/author_attestation","sign_citation":"https://pith.science/pith/YGBKI3PAOL3N3A4JSZAJHZT64D/action/citation_signature","submit_replication":"https://pith.science/pith/YGBKI3PAOL3N3A4JSZAJHZT64D/action/replication_record"}},"created_at":"2026-07-05T11:59:33.990151+00:00","updated_at":"2026-07-05T11:59:33.990151+00:00"}