{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6QFJBFQCM6FLLMMWCEBGMTXYLV","short_pith_number":"pith:6QFJBFQC","canonical_record":{"source":{"id":"2401.07927","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-15T19:39:15Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8509a05a7573a2728b562bc77b082ecd5574afe6e5c9d2379736859f0292d9a3","abstract_canon_sha256":"40aade2d6eb9b10cb68c05171f39b46fdb2b1096c2a95776953e6876105f280c"},"schema_version":"1.0"},"canonical_sha256":"f40a909602678ab5b1961102664ef85d42de30b375cc8808895eb3c825b27fdc","source":{"kind":"arxiv","id":"2401.07927","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.07927","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"arxiv_version","alias_value":"2401.07927v4","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07927","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"pith_short_12","alias_value":"6QFJBFQCM6FL","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"pith_short_16","alias_value":"6QFJBFQCM6FLLMMW","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"pith_short_8","alias_value":"6QFJBFQC","created_at":"2026-07-05T08:19:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6QFJBFQCM6FLLMMWCEBGMTXYLV","target":"record","payload":{"canonical_record":{"source":{"id":"2401.07927","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-15T19:39:15Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8509a05a7573a2728b562bc77b082ecd5574afe6e5c9d2379736859f0292d9a3","abstract_canon_sha256":"40aade2d6eb9b10cb68c05171f39b46fdb2b1096c2a95776953e6876105f280c"},"schema_version":"1.0"},"canonical_sha256":"f40a909602678ab5b1961102664ef85d42de30b375cc8808895eb3c825b27fdc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:57.939153Z","signature_b64":"fdXueT98YPTVBhYK4QyKoRLKkB3SS/aIN6BtyytxdG/OmNWO/EWasq12T1n0jP8DZFZzot0HeDeuE/2qQqE+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f40a909602678ab5b1961102664ef85d42de30b375cc8808895eb3c825b27fdc","last_reissued_at":"2026-07-05T08:19:57.938650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:57.938650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.07927","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":"2026-07-05T08:19:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oEIYwx6xVLRgLI6Wck1o4GHZ/DYl6YV8tf+9c7dk1NXRjHGu92UIBidndTJ4SZFDZ/scLjYHAFE+I9B/RQ+tBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:38:40.222590Z"},"content_sha256":"d8e855da299f673cd9732352b78d721ae2601f41a4fa539fff3da82e41b7373c","schema_version":"1.0","event_id":"sha256:d8e855da299f673cd9732352b78d721ae2601f41a4fa539fff3da82e41b7373c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6QFJBFQCM6FLLMMWCEBGMTXYLV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Are self-explanations from Large Language Models faithful?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andreas Madsen, Sarath Chandar, Siva Reddy","submitted_at":"2024-01-15T19:39:15Z","abstract_excerpt":"Instruction-tuned Large Language Models (LLMs) excel at many tasks and will even explain their reasoning, so-called self-explanations. However, convincing and wrong self-explanations can lead to unsupported confidence in LLMs, thus increasing risk. Therefore, it's important to measure if self-explanations truly reflect the model's behavior. Such a measure is called interpretability-faithfulness and is challenging to perform since the ground truth is inaccessible, and many LLMs only have an inference API. To address this, we propose employing self-consistency checks to measure faithfulness. For"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07927","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/2401.07927/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":"2026-07-05T08:19:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xKg1rLy7gurZGwzSc2ch/7xege2bah3QlKQeOElWVOy2HgzdVgjUfMaU7j/rh+Ys04dMIIXHBLr5rJmIpoMwAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:38:40.223132Z"},"content_sha256":"4b5a71a7417c0433a3dabdbb350f79f49cef24e02aacf06ffa8646562be7937f","schema_version":"1.0","event_id":"sha256:4b5a71a7417c0433a3dabdbb350f79f49cef24e02aacf06ffa8646562be7937f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6QFJBFQCM6FLLMMWCEBGMTXYLV/bundle.json","state_url":"https://pith.science/pith/6QFJBFQCM6FLLMMWCEBGMTXYLV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6QFJBFQCM6FLLMMWCEBGMTXYLV/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":"2026-08-08T10:38:40Z","links":{"resolver":"https://pith.science/pith/6QFJBFQCM6FLLMMWCEBGMTXYLV","bundle":"https://pith.science/pith/6QFJBFQCM6FLLMMWCEBGMTXYLV/bundle.json","state":"https://pith.science/pith/6QFJBFQCM6FLLMMWCEBGMTXYLV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6QFJBFQCM6FLLMMWCEBGMTXYLV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6QFJBFQCM6FLLMMWCEBGMTXYLV","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":"40aade2d6eb9b10cb68c05171f39b46fdb2b1096c2a95776953e6876105f280c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-15T19:39:15Z","title_canon_sha256":"8509a05a7573a2728b562bc77b082ecd5574afe6e5c9d2379736859f0292d9a3"},"schema_version":"1.0","source":{"id":"2401.07927","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.07927","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"arxiv_version","alias_value":"2401.07927v4","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07927","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"pith_short_12","alias_value":"6QFJBFQCM6FL","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"pith_short_16","alias_value":"6QFJBFQCM6FLLMMW","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"pith_short_8","alias_value":"6QFJBFQC","created_at":"2026-07-05T08:19:57Z"}],"graph_snapshots":[{"event_id":"sha256:4b5a71a7417c0433a3dabdbb350f79f49cef24e02aacf06ffa8646562be7937f","target":"graph","created_at":"2026-07-05T08:19:57Z","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/2401.07927/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction-tuned Large Language Models (LLMs) excel at many tasks and will even explain their reasoning, so-called self-explanations. However, convincing and wrong self-explanations can lead to unsupported confidence in LLMs, thus increasing risk. Therefore, it's important to measure if self-explanations truly reflect the model's behavior. Such a measure is called interpretability-faithfulness and is challenging to perform since the ground truth is inaccessible, and many LLMs only have an inference API. To address this, we propose employing self-consistency checks to measure faithfulness. For","authors_text":"Andreas Madsen, Sarath Chandar, Siva Reddy","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-15T19:39:15Z","title":"Are self-explanations from Large Language Models faithful?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07927","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:d8e855da299f673cd9732352b78d721ae2601f41a4fa539fff3da82e41b7373c","target":"record","created_at":"2026-07-05T08:19:57Z","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":"40aade2d6eb9b10cb68c05171f39b46fdb2b1096c2a95776953e6876105f280c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-15T19:39:15Z","title_canon_sha256":"8509a05a7573a2728b562bc77b082ecd5574afe6e5c9d2379736859f0292d9a3"},"schema_version":"1.0","source":{"id":"2401.07927","kind":"arxiv","version":4}},"canonical_sha256":"f40a909602678ab5b1961102664ef85d42de30b375cc8808895eb3c825b27fdc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f40a909602678ab5b1961102664ef85d42de30b375cc8808895eb3c825b27fdc","first_computed_at":"2026-07-05T08:19:57.938650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:19:57.938650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fdXueT98YPTVBhYK4QyKoRLKkB3SS/aIN6BtyytxdG/OmNWO/EWasq12T1n0jP8DZFZzot0HeDeuE/2qQqE+DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:19:57.939153Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.07927","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8e855da299f673cd9732352b78d721ae2601f41a4fa539fff3da82e41b7373c","sha256:4b5a71a7417c0433a3dabdbb350f79f49cef24e02aacf06ffa8646562be7937f"],"state_sha256":"16418ebda0c272e551c48c3dec0d64bb71a05b16ca5b61315e1f084ae17496a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xRYYmo5HhLBWA4uHB8fgPJJuSoEC7Gd2RNiTvbMwcruozVL4MjJP53k3q4ooJWXQbYYXVDJyMPujesd2RaxTAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:38:40.228386Z","bundle_sha256":"cea3b6c6df2fbbc9abdbb4b998ec662132bfde99bbbf6abe1ca37d7b7cf9388a"}}