{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AAOOEENJNSUXLNO4CB7XAOSG32","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":"f2d40bd80a130a1c7257a5ccb40f267651dbeb58371118ed8efcb34877096189","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T17:23:59Z","title_canon_sha256":"a1b9cb7cedf82ac6bdaffd259851c47c54b6e2f61865d183e1b7d7cb6a6c5516"},"schema_version":"1.0","source":{"id":"2402.13950","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13950","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13950v4","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13950","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"pith_short_12","alias_value":"AAOOEENJNSUX","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"pith_short_16","alias_value":"AAOOEENJNSUXLNO4","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"pith_short_8","alias_value":"AAOOEENJ","created_at":"2026-07-05T09:16:13Z"}],"graph_snapshots":[{"event_id":"sha256:d3ac1a49dfe6a25a6fbab855ac75789c796cf61f5d70749d5774b96aba732382","target":"graph","created_at":"2026-07-05T09:16:13Z","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/2402.13950/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have been shown to perform better when asked to reason step-by-step before answering a question. However, it is unclear to what degree the model's final answer is faithful to the stated reasoning steps. In this paper, we perform a causal mediation analysis on twelve LLMs to examine how intermediate reasoning steps generated by the LLM influence the final outcome and find that LLMs do not reliably use their intermediate reasoning steps when generating an answer. To address this issue, we introduce FRODO, a framework to tailor small-sized LMs to generate correct reas","authors_text":"Antoine Bosselut, Boi Faltings, Debjit Paul, Robert West","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T17:23:59Z","title":"Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13950","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":"sha256:41704109006ba0c7459e12fea2f144819c5e841ec3f84079873cd1290ca7d67f","target":"record","created_at":"2026-07-05T09:16:13Z","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":"f2d40bd80a130a1c7257a5ccb40f267651dbeb58371118ed8efcb34877096189","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T17:23:59Z","title_canon_sha256":"a1b9cb7cedf82ac6bdaffd259851c47c54b6e2f61865d183e1b7d7cb6a6c5516"},"schema_version":"1.0","source":{"id":"2402.13950","kind":"arxiv","version":4}},"canonical_sha256":"001ce211a96ca975b5dc107f703a46de9cb58fc5091ea143333d61e0c68a8683","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"001ce211a96ca975b5dc107f703a46de9cb58fc5091ea143333d61e0c68a8683","first_computed_at":"2026-07-05T09:16:13.016219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:13.016219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fb36Mg9gIjT4+bL6QMfG6ItNiYbLGUGw5iUW+s/hn9qvWCuvtGstkiTO/khm3iHerUrwye/Sk7vOtlBwonxaCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:13.016712Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13950","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41704109006ba0c7459e12fea2f144819c5e841ec3f84079873cd1290ca7d67f","sha256:d3ac1a49dfe6a25a6fbab855ac75789c796cf61f5d70749d5774b96aba732382"],"state_sha256":"73a410c8ac8883e7ac06f96d926420ec33f9568794d653e8f1a3c747e22a5b2e"}