{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5NGOASOW5CSCALV3N6EBAP5G6G","short_pith_number":"pith:5NGOASOW","schema_version":"1.0","canonical_sha256":"eb4ce049d6e8a4202ebb6f88103fa6f1a0eeba6f67fa0b45eaa9a1fb8d419567","source":{"kind":"arxiv","id":"2404.17347","version":2},"attestation_state":"computed","paper":{"title":"InspectorRAGet: An Introspection Platform for RAG Evaluation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.SE","authors_text":"Benjamin Sznajder, Kshitij Fadnis, Marina Danilevsky, Odellia Boni, Sara Rosenthal, Siva Sankalp Patel, Yannis Katsis","submitted_at":"2024-04-26T11:51:53Z","abstract_excerpt":"Large Language Models (LLM) have become a popular approach for implementing Retrieval Augmented Generation (RAG) systems, and a significant amount of effort has been spent on building good models and metrics. In spite of increased recognition of the need for rigorous evaluation of RAG systems, few tools exist that go beyond the creation of model output and automatic calculation. We present InspectorRAGet, an introspection platform for performing a comprehensive analysis of the quality of RAG system output. InspectorRAGet allows the user to analyze aggregate and instance-level performance of RA"},"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":"2404.17347","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-04-26T11:51:53Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"54c472a76de10c03b07975a8ace54e4b5122d10ec0389b1b0228b11ce7a5e88b","abstract_canon_sha256":"b300cdd7a0be963f3beacb9c2c41af9d1123bf048532322440fe52e4d142f922"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:26.894799Z","signature_b64":"7SIJ2Yvo8b5kF+4K/CR5k2Hbz8rauJfsEHYkbKh1GqNGJaQLRmOgS1hl8oSvtZ6C8gTxTURY/1JKjhOC5ipCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb4ce049d6e8a4202ebb6f88103fa6f1a0eeba6f67fa0b45eaa9a1fb8d419567","last_reissued_at":"2026-07-05T10:57:26.893760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:26.893760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InspectorRAGet: An Introspection Platform for RAG Evaluation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.SE","authors_text":"Benjamin Sznajder, Kshitij Fadnis, Marina Danilevsky, Odellia Boni, Sara Rosenthal, Siva Sankalp Patel, Yannis Katsis","submitted_at":"2024-04-26T11:51:53Z","abstract_excerpt":"Large Language Models (LLM) have become a popular approach for implementing Retrieval Augmented Generation (RAG) systems, and a significant amount of effort has been spent on building good models and metrics. In spite of increased recognition of the need for rigorous evaluation of RAG systems, few tools exist that go beyond the creation of model output and automatic calculation. We present InspectorRAGet, an introspection platform for performing a comprehensive analysis of the quality of RAG system output. InspectorRAGet allows the user to analyze aggregate and instance-level performance of RA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17347","kind":"arxiv","version":2},"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/2404.17347/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":"2404.17347","created_at":"2026-07-05T10:57:26.893822+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.17347v2","created_at":"2026-07-05T10:57:26.893822+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17347","created_at":"2026-07-05T10:57:26.893822+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NGOASOW5CSC","created_at":"2026-07-05T10:57:26.893822+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NGOASOW5CSCALV3","created_at":"2026-07-05T10:57:26.893822+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NGOASOW","created_at":"2026-07-05T10:57:26.893822+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/5NGOASOW5CSCALV3N6EBAP5G6G","json":"https://pith.science/pith/5NGOASOW5CSCALV3N6EBAP5G6G.json","graph_json":"https://pith.science/api/pith-number/5NGOASOW5CSCALV3N6EBAP5G6G/graph.json","events_json":"https://pith.science/api/pith-number/5NGOASOW5CSCALV3N6EBAP5G6G/events.json","paper":"https://pith.science/paper/5NGOASOW"},"agent_actions":{"view_html":"https://pith.science/pith/5NGOASOW5CSCALV3N6EBAP5G6G","download_json":"https://pith.science/pith/5NGOASOW5CSCALV3N6EBAP5G6G.json","view_paper":"https://pith.science/paper/5NGOASOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.17347&json=true","fetch_graph":"https://pith.science/api/pith-number/5NGOASOW5CSCALV3N6EBAP5G6G/graph.json","fetch_events":"https://pith.science/api/pith-number/5NGOASOW5CSCALV3N6EBAP5G6G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NGOASOW5CSCALV3N6EBAP5G6G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NGOASOW5CSCALV3N6EBAP5G6G/action/storage_attestation","attest_author":"https://pith.science/pith/5NGOASOW5CSCALV3N6EBAP5G6G/action/author_attestation","sign_citation":"https://pith.science/pith/5NGOASOW5CSCALV3N6EBAP5G6G/action/citation_signature","submit_replication":"https://pith.science/pith/5NGOASOW5CSCALV3N6EBAP5G6G/action/replication_record"}},"created_at":"2026-07-05T10:57:26.893822+00:00","updated_at":"2026-07-05T10:57:26.893822+00:00"}