{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RFXJRQWF4JJQJUNCYDBGEUTGJ3","short_pith_number":"pith:RFXJRQWF","schema_version":"1.0","canonical_sha256":"896e98c2c5e25304d1a2c0c26252664ec19ffa69617ed20c005e4ed9f8f4a919","source":{"kind":"arxiv","id":"2409.19019","version":1},"attestation_state":"computed","paper":{"title":"RAGProbe: An Automated Approach for Evaluating RAG Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Rajesh Vasa, Scott Barnett, Shangeetha Sivasothy, Stefanus Kurniawan, Zafaryab Rasool","submitted_at":"2024-09-24T23:33:07Z","abstract_excerpt":"Retrieval Augmented Generation (RAG) is increasingly being used when building Generative AI applications. Evaluating these applications and RAG pipelines is mostly done manually, via a trial and error process. Automating evaluation of RAG pipelines requires overcoming challenges such as context misunderstanding, wrong format, incorrect specificity, and missing content. Prior works therefore focused on improving evaluation metrics as well as enhancing components within the pipeline using available question and answer datasets. However, they have not focused on 1) providing a schema for capturin"},"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":"2409.19019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-24T23:33:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c1018bbab7b995bbcb650e31a2f691216b9d31b8e4ce0825da828ebecdcf3ce6","abstract_canon_sha256":"365681036371b1507bdbd3f694311c1f5e4ba9c3328ba345f35e118b203546e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:09.490830Z","signature_b64":"Yfrkvuo5jUKvrMOkEO6KZwz4kac81j8D7A4EtiSJQxF/zRbIpSw5+5SqiJgGe7Nhvo1F51sl73LqUqf3ebnrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"896e98c2c5e25304d1a2c0c26252664ec19ffa69617ed20c005e4ed9f8f4a919","last_reissued_at":"2026-07-05T09:13:09.490309Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:09.490309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAGProbe: An Automated Approach for Evaluating RAG Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Rajesh Vasa, Scott Barnett, Shangeetha Sivasothy, Stefanus Kurniawan, Zafaryab Rasool","submitted_at":"2024-09-24T23:33:07Z","abstract_excerpt":"Retrieval Augmented Generation (RAG) is increasingly being used when building Generative AI applications. Evaluating these applications and RAG pipelines is mostly done manually, via a trial and error process. Automating evaluation of RAG pipelines requires overcoming challenges such as context misunderstanding, wrong format, incorrect specificity, and missing content. Prior works therefore focused on improving evaluation metrics as well as enhancing components within the pipeline using available question and answer datasets. However, they have not focused on 1) providing a schema for capturin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19019","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/2409.19019/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":"2409.19019","created_at":"2026-07-05T09:13:09.490389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.19019v1","created_at":"2026-07-05T09:13:09.490389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19019","created_at":"2026-07-05T09:13:09.490389+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFXJRQWF4JJQ","created_at":"2026-07-05T09:13:09.490389+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFXJRQWF4JJQJUNC","created_at":"2026-07-05T09:13:09.490389+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFXJRQWF","created_at":"2026-07-05T09:13:09.490389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14345","citing_title":"A Vision for Geo-Temporal Deep Research Systems: Towards Comprehensive, Transparent, and Reproducible Geo-Temporal Information Synthesis","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RFXJRQWF4JJQJUNCYDBGEUTGJ3","json":"https://pith.science/pith/RFXJRQWF4JJQJUNCYDBGEUTGJ3.json","graph_json":"https://pith.science/api/pith-number/RFXJRQWF4JJQJUNCYDBGEUTGJ3/graph.json","events_json":"https://pith.science/api/pith-number/RFXJRQWF4JJQJUNCYDBGEUTGJ3/events.json","paper":"https://pith.science/paper/RFXJRQWF"},"agent_actions":{"view_html":"https://pith.science/pith/RFXJRQWF4JJQJUNCYDBGEUTGJ3","download_json":"https://pith.science/pith/RFXJRQWF4JJQJUNCYDBGEUTGJ3.json","view_paper":"https://pith.science/paper/RFXJRQWF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.19019&json=true","fetch_graph":"https://pith.science/api/pith-number/RFXJRQWF4JJQJUNCYDBGEUTGJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/RFXJRQWF4JJQJUNCYDBGEUTGJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFXJRQWF4JJQJUNCYDBGEUTGJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFXJRQWF4JJQJUNCYDBGEUTGJ3/action/storage_attestation","attest_author":"https://pith.science/pith/RFXJRQWF4JJQJUNCYDBGEUTGJ3/action/author_attestation","sign_citation":"https://pith.science/pith/RFXJRQWF4JJQJUNCYDBGEUTGJ3/action/citation_signature","submit_replication":"https://pith.science/pith/RFXJRQWF4JJQJUNCYDBGEUTGJ3/action/replication_record"}},"created_at":"2026-07-05T09:13:09.490389+00:00","updated_at":"2026-07-05T09:13:09.490389+00:00"}