{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZP34TZYDFW4BTKWISBW4376LGV","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":"6cea1fc211cbd377802526c6d48f68e0729b878cd0346e30db928e546e7109da","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T10:25:46Z","title_canon_sha256":"cc569f6515e502fc17e805cb5780b577b4ee36d9a3f4c437aa8754300718a51e"},"schema_version":"1.0","source":{"id":"2507.22928","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22928","created_at":"2026-07-05T11:46:02Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22928v1","created_at":"2026-07-05T11:46:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22928","created_at":"2026-07-05T11:46:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZP34TZYDFW4B","created_at":"2026-07-05T11:46:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZP34TZYDFW4BTKWI","created_at":"2026-07-05T11:46:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZP34TZYD","created_at":"2026-07-05T11:46:02Z"}],"graph_snapshots":[{"event_id":"sha256:9e8b9a3e80c5149a901e0a4d955e01839f67582a6d038f995fc603ec421d8bc8","target":"graph","created_at":"2026-07-05T11:46:02Z","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/2507.22928/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chain-of-thought (CoT) prompting boosts Large Language Models accuracy on multi-step tasks, yet whether the generated \"thoughts\" reflect the true internal reasoning process is unresolved. We present the first feature-level causal study of CoT faithfulness. Combining sparse autoencoders with activation patching, we extract monosemantic features from Pythia-70M and Pythia-2.8B while they tackle GSM8K math problems under CoT and plain (noCoT) prompting. Swapping a small set of CoT-reasoning features into a noCoT run raises answer log-probabilities significantly in the 2.8B model, but has no relia","authors_text":"Aske Plaat, Niki van Stein, Xi Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T10:25:46Z","title":"How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22928","kind":"arxiv","version":1},"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":"sha256:0edfbffff22d525861dbdd3baba6bf1cb061f906feef19a2d3994816637f6847","target":"record","created_at":"2026-07-05T11:46:02Z","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":"6cea1fc211cbd377802526c6d48f68e0729b878cd0346e30db928e546e7109da","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T10:25:46Z","title_canon_sha256":"cc569f6515e502fc17e805cb5780b577b4ee36d9a3f4c437aa8754300718a51e"},"schema_version":"1.0","source":{"id":"2507.22928","kind":"arxiv","version":1}},"canonical_sha256":"cbf7c9e7032db819aac8906dcdffcb355a8231c9aeeb0dad33792bbcb2f74f40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbf7c9e7032db819aac8906dcdffcb355a8231c9aeeb0dad33792bbcb2f74f40","first_computed_at":"2026-07-05T11:46:02.096466Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:02.096466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vwk8jKb/EL8f6eNoma9ueddSUTel0QE6YZw2ZLGopX1kGhr8MtDZKsLgVMhYLaeq/f7qaj/+dEr6Vl5paC4WAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:02.096960Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.22928","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0edfbffff22d525861dbdd3baba6bf1cb061f906feef19a2d3994816637f6847","sha256:9e8b9a3e80c5149a901e0a4d955e01839f67582a6d038f995fc603ec421d8bc8"],"state_sha256":"4d45e6355fbecacb16472fe28d510850b56c0c3d67cd242e1bc9652e7f9fb3f0"}