{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3ZWON3SAPYDSK2NPI7TQ5HURHY","short_pith_number":"pith:3ZWON3SA","canonical_record":{"source":{"id":"2311.07466","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T16:53:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"69a727c62d7eca1ef7650311535fb8a0f07bd68d6f81d8da2bd733730b45c556","abstract_canon_sha256":"bddc6ee5c9d19d78795de375e1779b1803b5fc2375507eec37442cd67f246b7a"},"schema_version":"1.0"},"canonical_sha256":"de6ce6ee407e072569af47e70e9e913e3b97f5b2ed98be05ac84b215945fcfac","source":{"kind":"arxiv","id":"2311.07466","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07466","created_at":"2026-07-05T09:08:45Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07466v4","created_at":"2026-07-05T09:08:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07466","created_at":"2026-07-05T09:08:45Z"},{"alias_kind":"pith_short_12","alias_value":"3ZWON3SAPYDS","created_at":"2026-07-05T09:08:45Z"},{"alias_kind":"pith_short_16","alias_value":"3ZWON3SAPYDSK2NP","created_at":"2026-07-05T09:08:45Z"},{"alias_kind":"pith_short_8","alias_value":"3ZWON3SA","created_at":"2026-07-05T09:08:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3ZWON3SAPYDSK2NPI7TQ5HURHY","target":"record","payload":{"canonical_record":{"source":{"id":"2311.07466","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T16:53:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"69a727c62d7eca1ef7650311535fb8a0f07bd68d6f81d8da2bd733730b45c556","abstract_canon_sha256":"bddc6ee5c9d19d78795de375e1779b1803b5fc2375507eec37442cd67f246b7a"},"schema_version":"1.0"},"canonical_sha256":"de6ce6ee407e072569af47e70e9e913e3b97f5b2ed98be05ac84b215945fcfac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:45.871062Z","signature_b64":"JFdlfViSUOwJvc4x2Ou6WUlBcOUz9tfY9gCmUsprbvqD4eRghyiY5Bxnxqh/hO0yAX550lTj6cUS2mlmTEwiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de6ce6ee407e072569af47e70e9e913e3b97f5b2ed98be05ac84b215945fcfac","last_reissued_at":"2026-07-05T09:08:45.870504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:45.870504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.07466","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:08:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Oz5KoVcmKWzMt8sRc15G4rkwqGm0zDkNrBVurOaSHgMoYsld8bkPGECtBNDnDiTSWu97tFUQexxHgmoOjV40Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T08:20:33.053125Z"},"content_sha256":"61ed205f27fe03ccfce0d7f8abbf3d161df9afaf0b38198d0f3b51d5761286ea","schema_version":"1.0","event_id":"sha256:61ed205f27fe03ccfce0d7f8abbf3d161df9afaf0b38198d0f3b51d5761286ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3ZWON3SAPYDSK2NPI7TQ5HURHY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Measuring Faithfulness or Self-consistency of Natural Language Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anette Frank, Letitia Parcalabescu","submitted_at":"2023-11-13T16:53:51Z","abstract_excerpt":"Large language models (LLMs) can explain their predictions through post-hoc or Chain-of-Thought (CoT) explanations. But an LLM could make up reasonably sounding explanations that are unfaithful to its underlying reasoning. Recent work has designed tests that aim to judge the faithfulness of post-hoc or CoT explanations. In this work we argue that these faithfulness tests do not measure faithfulness to the models' inner workings -- but rather their self-consistency at output level. Our contributions are three-fold: i) We clarify the status of faithfulness tests in view of model explainability, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07466","kind":"arxiv","version":4},"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/2311.07466/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:08:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hGF1Dh4jQK7gcETCZl+491MLsduoMH1uSIE6Gff0hv6ZxtnXGqs6oU/d9+M2BS5XYoHJ1k2gu3PgKuEqFl8ADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T08:20:33.053520Z"},"content_sha256":"d3c2c323c5a7a9d4495e914e2a2fbbc22f81e6a53c5084583e62efd3e806bb93","schema_version":"1.0","event_id":"sha256:d3c2c323c5a7a9d4495e914e2a2fbbc22f81e6a53c5084583e62efd3e806bb93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3ZWON3SAPYDSK2NPI7TQ5HURHY/bundle.json","state_url":"https://pith.science/pith/3ZWON3SAPYDSK2NPI7TQ5HURHY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3ZWON3SAPYDSK2NPI7TQ5HURHY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-26T08:20:33Z","links":{"resolver":"https://pith.science/pith/3ZWON3SAPYDSK2NPI7TQ5HURHY","bundle":"https://pith.science/pith/3ZWON3SAPYDSK2NPI7TQ5HURHY/bundle.json","state":"https://pith.science/pith/3ZWON3SAPYDSK2NPI7TQ5HURHY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3ZWON3SAPYDSK2NPI7TQ5HURHY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3ZWON3SAPYDSK2NPI7TQ5HURHY","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":"bddc6ee5c9d19d78795de375e1779b1803b5fc2375507eec37442cd67f246b7a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T16:53:51Z","title_canon_sha256":"69a727c62d7eca1ef7650311535fb8a0f07bd68d6f81d8da2bd733730b45c556"},"schema_version":"1.0","source":{"id":"2311.07466","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07466","created_at":"2026-07-05T09:08:45Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07466v4","created_at":"2026-07-05T09:08:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07466","created_at":"2026-07-05T09:08:45Z"},{"alias_kind":"pith_short_12","alias_value":"3ZWON3SAPYDS","created_at":"2026-07-05T09:08:45Z"},{"alias_kind":"pith_short_16","alias_value":"3ZWON3SAPYDSK2NP","created_at":"2026-07-05T09:08:45Z"},{"alias_kind":"pith_short_8","alias_value":"3ZWON3SA","created_at":"2026-07-05T09:08:45Z"}],"graph_snapshots":[{"event_id":"sha256:d3c2c323c5a7a9d4495e914e2a2fbbc22f81e6a53c5084583e62efd3e806bb93","target":"graph","created_at":"2026-07-05T09:08:45Z","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/2311.07466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) can explain their predictions through post-hoc or Chain-of-Thought (CoT) explanations. But an LLM could make up reasonably sounding explanations that are unfaithful to its underlying reasoning. Recent work has designed tests that aim to judge the faithfulness of post-hoc or CoT explanations. In this work we argue that these faithfulness tests do not measure faithfulness to the models' inner workings -- but rather their self-consistency at output level. Our contributions are three-fold: i) We clarify the status of faithfulness tests in view of model explainability, ","authors_text":"Anette Frank, Letitia Parcalabescu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T16:53:51Z","title":"On Measuring Faithfulness or Self-consistency of Natural Language Explanations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07466","kind":"arxiv","version":4},"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":"sha256:61ed205f27fe03ccfce0d7f8abbf3d161df9afaf0b38198d0f3b51d5761286ea","target":"record","created_at":"2026-07-05T09:08:45Z","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":"bddc6ee5c9d19d78795de375e1779b1803b5fc2375507eec37442cd67f246b7a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T16:53:51Z","title_canon_sha256":"69a727c62d7eca1ef7650311535fb8a0f07bd68d6f81d8da2bd733730b45c556"},"schema_version":"1.0","source":{"id":"2311.07466","kind":"arxiv","version":4}},"canonical_sha256":"de6ce6ee407e072569af47e70e9e913e3b97f5b2ed98be05ac84b215945fcfac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de6ce6ee407e072569af47e70e9e913e3b97f5b2ed98be05ac84b215945fcfac","first_computed_at":"2026-07-05T09:08:45.870504Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:45.870504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JFdlfViSUOwJvc4x2Ou6WUlBcOUz9tfY9gCmUsprbvqD4eRghyiY5Bxnxqh/hO0yAX550lTj6cUS2mlmTEwiCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:45.871062Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.07466","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61ed205f27fe03ccfce0d7f8abbf3d161df9afaf0b38198d0f3b51d5761286ea","sha256:d3c2c323c5a7a9d4495e914e2a2fbbc22f81e6a53c5084583e62efd3e806bb93"],"state_sha256":"b3c8862b2107daea5232932c493fa9aae0b7b008cd68dfd410bcffb160a1da73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GiQ9XSB8fvGP9Tl37Sn3ed7Ivyhs7t2R/poY48A21/o5uJgZnHbf/uZxuS/p1/SsN0pgTeV4Mzn9Q6E3I/S3Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T08:20:33.055733Z","bundle_sha256":"dcf05d362d6f121733ca0839a248907c2bd3b762dc27d910fded79289caf9b2e"}}