{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NFW6LGG7BYYALDUI35ELECLOPW","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":"5f72407658233c75427a149815aad12a2f017b09b28f23dcfcf48726a7681956","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T06:27:53Z","title_canon_sha256":"529b2ba6281218c8943be71a85fa6da6be1a4667d5f50b4ccb8de6fb69dea842"},"schema_version":"1.0","source":{"id":"2410.03727","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03727","created_at":"2026-07-05T10:53:48Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03727v3","created_at":"2026-07-05T10:53:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03727","created_at":"2026-07-05T10:53:48Z"},{"alias_kind":"pith_short_12","alias_value":"NFW6LGG7BYYA","created_at":"2026-07-05T10:53:48Z"},{"alias_kind":"pith_short_16","alias_value":"NFW6LGG7BYYALDUI","created_at":"2026-07-05T10:53:48Z"},{"alias_kind":"pith_short_8","alias_value":"NFW6LGG7","created_at":"2026-07-05T10:53:48Z"}],"graph_snapshots":[{"event_id":"sha256:74e46e9665ff78fb00b2a255048da10521057730eed8ca706fce98edcd03750d","target":"graph","created_at":"2026-07-05T10:53:48Z","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/2410.03727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ensuring faithfulness to context in large language models (LLMs) and retrieval-augmented generation (RAG) systems is crucial for reliable deployment in real-world applications, as incorrect or unsupported information can erode user trust. Despite advancements on standard benchmarks, faithfulness hallucination-where models generate responses misaligned with the provided context-remains a significant challenge. In this work, we introduce FaithEval, a novel and comprehensive benchmark tailored to evaluate the faithfulness of LLMs in contextual scenarios across three diverse tasks: unanswerable, i","authors_text":"Caiming Xiong, Senthil Purushwalkam, Shafiq Joty, Shrey Pandit, Xuan-Phi Nguyen, Yifei Ming, Zixuan Ke","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T06:27:53Z","title":"FaithEval: Can Your Language Model Stay Faithful to Context, Even If \"The Moon is Made of Marshmallows\""},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03727","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:be79e78cfc7fcb7f34b51980a7e1f7ae9b25e9e03438eff9b8efb7a739a1aeee","target":"record","created_at":"2026-07-05T10:53:48Z","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":"5f72407658233c75427a149815aad12a2f017b09b28f23dcfcf48726a7681956","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T06:27:53Z","title_canon_sha256":"529b2ba6281218c8943be71a85fa6da6be1a4667d5f50b4ccb8de6fb69dea842"},"schema_version":"1.0","source":{"id":"2410.03727","kind":"arxiv","version":3}},"canonical_sha256":"696de598df0e30058e88df48b2096e7dadf459dfcf232f6a8ed9420e1fcd0548","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"696de598df0e30058e88df48b2096e7dadf459dfcf232f6a8ed9420e1fcd0548","first_computed_at":"2026-07-05T10:53:48.228492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:48.228492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2ES+1aM21ApQdWGyJX8ckN6FG3ZBwWLfoe2iJvm3Cxbz9iedHJ+U2EcHTO5Zd27YOrNreglJcO9NDFAw7qkWCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:48.229064Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03727","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be79e78cfc7fcb7f34b51980a7e1f7ae9b25e9e03438eff9b8efb7a739a1aeee","sha256:74e46e9665ff78fb00b2a255048da10521057730eed8ca706fce98edcd03750d"],"state_sha256":"8726d64f05356688a71e025e4ec4a0dd94db905ae7af0083e03a5dd748ababb9"}