{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RV7Z5VPTZL33MV5EGZ3XQMUUYH","short_pith_number":"pith:RV7Z5VPT","schema_version":"1.0","canonical_sha256":"8d7f9ed5f3caf7b657a43677783294c1e0f2e98731a4d1c634c71325a85aaf47","source":{"kind":"arxiv","id":"2411.16391","version":2},"attestation_state":"computed","paper":{"title":"Human-Calibrated Automated Testing and Validation of Generative Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Agus Sudjianto, Aijun Zhang, Michal Malohlava, Srinivas Neppalli, Tarun Joshi","submitted_at":"2024-11-25T13:53:36Z","abstract_excerpt":"This paper introduces a comprehensive framework for the evaluation and validation of generative language models (GLMs), with a focus on Retrieval-Augmented Generation (RAG) systems deployed in high-stakes domains such as banking. GLM evaluation is challenging due to open-ended outputs and subjective quality assessments. Leveraging the structured nature of RAG systems, where generated responses are grounded in a predefined document collection, we propose the Human-Calibrated Automated Testing (HCAT) framework. HCAT integrates a) automated test generation using stratified sampling, b) embedding-"},"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":"2411.16391","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-25T13:53:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"26c766e2e58e2f3a03b3d7547f286c010a758bcb7b8e9788d67b2e9de72010b8","abstract_canon_sha256":"ea209b4be013df96699f985ae3844a205a0d5947a69b1e3a4f3cae08ea3f4fd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:58.639377Z","signature_b64":"831U8G4TlD4tbLlqsp5U9dXeYU8xIFjMJL5fieObCiFwBZdpDui1zUPppgjF7r/jReSwTRdi7o0dgtmcT/L8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d7f9ed5f3caf7b657a43677783294c1e0f2e98731a4d1c634c71325a85aaf47","last_reissued_at":"2026-07-05T09:45:58.638948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:58.638948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-Calibrated Automated Testing and Validation of Generative Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Agus Sudjianto, Aijun Zhang, Michal Malohlava, Srinivas Neppalli, Tarun Joshi","submitted_at":"2024-11-25T13:53:36Z","abstract_excerpt":"This paper introduces a comprehensive framework for the evaluation and validation of generative language models (GLMs), with a focus on Retrieval-Augmented Generation (RAG) systems deployed in high-stakes domains such as banking. GLM evaluation is challenging due to open-ended outputs and subjective quality assessments. Leveraging the structured nature of RAG systems, where generated responses are grounded in a predefined document collection, we propose the Human-Calibrated Automated Testing (HCAT) framework. HCAT integrates a) automated test generation using stratified sampling, b) embedding-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16391","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/2411.16391/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":"2411.16391","created_at":"2026-07-05T09:45:58.638997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16391v2","created_at":"2026-07-05T09:45:58.638997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16391","created_at":"2026-07-05T09:45:58.638997+00:00"},{"alias_kind":"pith_short_12","alias_value":"RV7Z5VPTZL33","created_at":"2026-07-05T09:45:58.638997+00:00"},{"alias_kind":"pith_short_16","alias_value":"RV7Z5VPTZL33MV5E","created_at":"2026-07-05T09:45:58.638997+00:00"},{"alias_kind":"pith_short_8","alias_value":"RV7Z5VPT","created_at":"2026-07-05T09:45:58.638997+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01040","citing_title":"As It Was: Aligning LLM Search Evaluation with Historical User Preferences","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RV7Z5VPTZL33MV5EGZ3XQMUUYH","json":"https://pith.science/pith/RV7Z5VPTZL33MV5EGZ3XQMUUYH.json","graph_json":"https://pith.science/api/pith-number/RV7Z5VPTZL33MV5EGZ3XQMUUYH/graph.json","events_json":"https://pith.science/api/pith-number/RV7Z5VPTZL33MV5EGZ3XQMUUYH/events.json","paper":"https://pith.science/paper/RV7Z5VPT"},"agent_actions":{"view_html":"https://pith.science/pith/RV7Z5VPTZL33MV5EGZ3XQMUUYH","download_json":"https://pith.science/pith/RV7Z5VPTZL33MV5EGZ3XQMUUYH.json","view_paper":"https://pith.science/paper/RV7Z5VPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16391&json=true","fetch_graph":"https://pith.science/api/pith-number/RV7Z5VPTZL33MV5EGZ3XQMUUYH/graph.json","fetch_events":"https://pith.science/api/pith-number/RV7Z5VPTZL33MV5EGZ3XQMUUYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RV7Z5VPTZL33MV5EGZ3XQMUUYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RV7Z5VPTZL33MV5EGZ3XQMUUYH/action/storage_attestation","attest_author":"https://pith.science/pith/RV7Z5VPTZL33MV5EGZ3XQMUUYH/action/author_attestation","sign_citation":"https://pith.science/pith/RV7Z5VPTZL33MV5EGZ3XQMUUYH/action/citation_signature","submit_replication":"https://pith.science/pith/RV7Z5VPTZL33MV5EGZ3XQMUUYH/action/replication_record"}},"created_at":"2026-07-05T09:45:58.638997+00:00","updated_at":"2026-07-05T09:45:58.638997+00:00"}