{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7ZNAC3NWAL5FSDPNJ2XHPCCV6N","short_pith_number":"pith:7ZNAC3NW","schema_version":"1.0","canonical_sha256":"fe5a016db602fa590ded4eae778855f34161da58e80b3a91738ca111bfbe4387","source":{"kind":"arxiv","id":"2608.00054","version":1},"attestation_state":"computed","paper":{"title":"RAG-TESTER: Automated End-to-End Testing of Retrieval-Augmented Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Aitor Arrieta, Ange Maiztegi, Jon Ayerdi, Miren Illarramendi","submitted_at":"2026-07-26T21:29:19Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to use external and domain-specific knowledge, but its reliability depends on the interaction between the generative model, embedding model, retrieval mechanism, and prompt construction strategy. We present RagTester, an automated end-to-end testing approach for RAG systems. RagTester generates retrieval documents, test inputs, and expected outputs; executes the tests; and evaluates the resulting answers using an LLM as a judge. Its test-generation strategy targets complex passages, unsupported queries, and document-cove"},"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":"2608.00054","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-26T21:29:19Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"f48087008297dcfe096c3ac1f1330baa3901ee3cc72638be983c4a1ef501029a","abstract_canon_sha256":"c07a2e752ac12938f817c16c91dee968074efa979a164f2c5323932ff4ad5cbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:31:51.564035Z","signature_b64":"jj2P2yBzHYrpE2v9gX/1yQzPFiUzcAtkgyKscNnWyz97/LbqL3lcxkWDAgB786CxI4lBOI0dwm+0jWgFTbB+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe5a016db602fa590ded4eae778855f34161da58e80b3a91738ca111bfbe4387","last_reissued_at":"2026-08-04T00:31:51.562514Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:31:51.562514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAG-TESTER: Automated End-to-End Testing of Retrieval-Augmented Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Aitor Arrieta, Ange Maiztegi, Jon Ayerdi, Miren Illarramendi","submitted_at":"2026-07-26T21:29:19Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to use external and domain-specific knowledge, but its reliability depends on the interaction between the generative model, embedding model, retrieval mechanism, and prompt construction strategy. We present RagTester, an automated end-to-end testing approach for RAG systems. RagTester generates retrieval documents, test inputs, and expected outputs; executes the tests; and evaluates the resulting answers using an LLM as a judge. Its test-generation strategy targets complex passages, unsupported queries, and document-cove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00054","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/2608.00054/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":"2608.00054","created_at":"2026-08-04T00:31:51.563626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00054v1","created_at":"2026-08-04T00:31:51.563626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00054","created_at":"2026-08-04T00:31:51.563626+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ZNAC3NWAL5F","created_at":"2026-08-04T00:31:51.563626+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ZNAC3NWAL5FSDPN","created_at":"2026-08-04T00:31:51.563626+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ZNAC3NW","created_at":"2026-08-04T00:31:51.563626+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/7ZNAC3NWAL5FSDPNJ2XHPCCV6N","json":"https://pith.science/pith/7ZNAC3NWAL5FSDPNJ2XHPCCV6N.json","graph_json":"https://pith.science/api/pith-number/7ZNAC3NWAL5FSDPNJ2XHPCCV6N/graph.json","events_json":"https://pith.science/api/pith-number/7ZNAC3NWAL5FSDPNJ2XHPCCV6N/events.json","paper":"https://pith.science/paper/7ZNAC3NW"},"agent_actions":{"view_html":"https://pith.science/pith/7ZNAC3NWAL5FSDPNJ2XHPCCV6N","download_json":"https://pith.science/pith/7ZNAC3NWAL5FSDPNJ2XHPCCV6N.json","view_paper":"https://pith.science/paper/7ZNAC3NW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00054&json=true","fetch_graph":"https://pith.science/api/pith-number/7ZNAC3NWAL5FSDPNJ2XHPCCV6N/graph.json","fetch_events":"https://pith.science/api/pith-number/7ZNAC3NWAL5FSDPNJ2XHPCCV6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ZNAC3NWAL5FSDPNJ2XHPCCV6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ZNAC3NWAL5FSDPNJ2XHPCCV6N/action/storage_attestation","attest_author":"https://pith.science/pith/7ZNAC3NWAL5FSDPNJ2XHPCCV6N/action/author_attestation","sign_citation":"https://pith.science/pith/7ZNAC3NWAL5FSDPNJ2XHPCCV6N/action/citation_signature","submit_replication":"https://pith.science/pith/7ZNAC3NWAL5FSDPNJ2XHPCCV6N/action/replication_record"}},"created_at":"2026-08-04T00:31:51.563626+00:00","updated_at":"2026-08-04T00:31:51.563626+00:00"}