{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4ARFAADXWP5FKXWOKPAMLPYGL4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"10b1f089478337116d82c79c8446fee09b5afe2c837277bff8ed566b11c7bf0b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T11:16:54Z","title_canon_sha256":"c884685f03991625618de2ce812cbaa42a0415106c7e8755391221f460bb20c9"},"schema_version":"1.0","source":{"id":"2407.12830","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12830","created_at":"2026-07-05T11:53:41Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12830v3","created_at":"2026-07-05T11:53:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12830","created_at":"2026-07-05T11:53:41Z"},{"alias_kind":"pith_short_12","alias_value":"4ARFAADXWP5F","created_at":"2026-07-05T11:53:41Z"},{"alias_kind":"pith_short_16","alias_value":"4ARFAADXWP5FKXWO","created_at":"2026-07-05T11:53:41Z"},{"alias_kind":"pith_short_8","alias_value":"4ARFAADX","created_at":"2026-07-05T11:53:41Z"}],"graph_snapshots":[{"event_id":"sha256:fb8f2436f24c1cccb46acaac40dee2d85a82a710a95afc031d4d9e0ef5b96204","target":"graph","created_at":"2026-07-05T11:53:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.12830/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we systematically expose and measure the inconsistency and knowledge gaps of Large Language Models (LLMs). Specifically, we propose an automated testing framework (called KonTest) which leverages a knowledge graph to construct test cases. KonTest probes and measures the inconsistencies in the LLM's knowledge of the world via a combination of semantically-equivalent queries and test oracles (metamorphic or ontological oracle). KonTest further mitigates knowledge gaps via a weighted LLM model ensemble. Using four state-of-the-art LLMs (Falcon, Gemini, GPT3.5, and Llama2), we show t","authors_text":"Ezekiel Soremekun, Sai Sathiesh Rajan, Sudipta Chattopadhyay","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T11:16:54Z","title":"Knowledge-based Consistency Testing of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12830","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bf2cfc0d56da70ad7df8ccc88d597c0eb9dde0670ab76d31fb06d565f590f93a","target":"record","created_at":"2026-07-05T11:53:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"10b1f089478337116d82c79c8446fee09b5afe2c837277bff8ed566b11c7bf0b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T11:16:54Z","title_canon_sha256":"c884685f03991625618de2ce812cbaa42a0415106c7e8755391221f460bb20c9"},"schema_version":"1.0","source":{"id":"2407.12830","kind":"arxiv","version":3}},"canonical_sha256":"e022500077b3fa555ece53c0c5bf065f2eaef2841f548b99038f7ab8c28305a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e022500077b3fa555ece53c0c5bf065f2eaef2841f548b99038f7ab8c28305a2","first_computed_at":"2026-07-05T11:53:41.191393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:41.191393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NoBywhLMGgpSgbQsIgRo5rZX6EHsJmPFjVagoSZx3q5gIXWr139I8wIpOwR/3aUY/nPAcBTqcUk0C87hDqCzAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:41.191880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12830","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf2cfc0d56da70ad7df8ccc88d597c0eb9dde0670ab76d31fb06d565f590f93a","sha256:fb8f2436f24c1cccb46acaac40dee2d85a82a710a95afc031d4d9e0ef5b96204"],"state_sha256":"14a93946a423559e835faa88b691d157ca7a1fe1408447a3874d8b8ced3303ba"}