{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3TAROGI2PIB62SIYERO7BRQFHZ","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":"38bf66070335295fcffcf23e55f72d8139df5e80de5b5998872fcb9afeb069f7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T17:59:39Z","title_canon_sha256":"cc2885c87395619709b3a5d77ca51850bf22c40bef43656e60b5bd26c36b9560"},"schema_version":"1.0","source":{"id":"2503.13445","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13445","created_at":"2026-07-02T01:18:02Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13445v3","created_at":"2026-07-02T01:18:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13445","created_at":"2026-07-02T01:18:02Z"},{"alias_kind":"pith_short_12","alias_value":"3TAROGI2PIB6","created_at":"2026-07-02T01:18:02Z"},{"alias_kind":"pith_short_16","alias_value":"3TAROGI2PIB62SIY","created_at":"2026-07-02T01:18:02Z"},{"alias_kind":"pith_short_8","alias_value":"3TAROGI2","created_at":"2026-07-02T01:18:02Z"}],"graph_snapshots":[{"event_id":"sha256:8d871df0ddd075b6a59007bd0aad946d04c0321fa005f000930babb7a9e2a786","target":"graph","created_at":"2026-07-02T01:18:02Z","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/2503.13445/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When asked to explain their decisions, LLMs can often give explanations which sound plausible to humans. But are these explanations faithful, i.e. do they convey the factors actually responsible for the decision? In this work, we analyse counterfactual faithfulness across 75 models from 13 families. We analyze the tradeoff between conciseness and comprehensiveness, how correlational faithfulness metrics assess this tradeoff, and the extent to which metrics can be gamed. This analysis motivates two new metrics: the phi-CCT, a simplified variant of the Correlational Counterfactual Test (CCT) whi","authors_text":"Maria Perez-Ortiz, Nicolas Heess, Noah Y. Siegel, Oana-Maria Camburu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T17:59:39Z","title":"Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13445","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":"sha256:2c968b3f06e03dc97fc954d0091cc29579187fc5f9abd491bd5981125f26cf42","target":"record","created_at":"2026-07-02T01:18:02Z","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":"38bf66070335295fcffcf23e55f72d8139df5e80de5b5998872fcb9afeb069f7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T17:59:39Z","title_canon_sha256":"cc2885c87395619709b3a5d77ca51850bf22c40bef43656e60b5bd26c36b9560"},"schema_version":"1.0","source":{"id":"2503.13445","kind":"arxiv","version":3}},"canonical_sha256":"dcc117191a7a03ed4918245df0c6053e62f0c2b75ec0ea0449b5e503ed741e53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcc117191a7a03ed4918245df0c6053e62f0c2b75ec0ea0449b5e503ed741e53","first_computed_at":"2026-07-02T01:18:02.403061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:18:02.403061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mqoXkaJjjSTgNAG7q3DM6xdSXKJ1PQXc38zHvXSqj8FF0qqmrATjEsl7cV2X4mD/6XijVDXUXbngJxAdzTBOCg==","signature_status":"signed_v1","signed_at":"2026-07-02T01:18:02.403511Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.13445","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c968b3f06e03dc97fc954d0091cc29579187fc5f9abd491bd5981125f26cf42","sha256:8d871df0ddd075b6a59007bd0aad946d04c0321fa005f000930babb7a9e2a786"],"state_sha256":"7dc045ce4f6f0b3246ca90a94e2fb71f40affff675029e5900590ee9fd15f423"}