{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5O7LBIGX76TAQWGGXTIE6JLOIP","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":"29b437d66645c2bc5bfaa5ca982c882eec21243933b35e8847566d7e9c9e067e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-02T09:25:29Z","title_canon_sha256":"a081a0827a82a49c341d8dfd633b3f93b5972867092ffcaf52e7c09076b24941"},"schema_version":"1.0","source":{"id":"2207.00779","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.00779","created_at":"2026-07-05T05:26:44Z"},{"alias_kind":"arxiv_version","alias_value":"2207.00779v2","created_at":"2026-07-05T05:26:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00779","created_at":"2026-07-05T05:26:44Z"},{"alias_kind":"pith_short_12","alias_value":"5O7LBIGX76TA","created_at":"2026-07-05T05:26:44Z"},{"alias_kind":"pith_short_16","alias_value":"5O7LBIGX76TAQWGG","created_at":"2026-07-05T05:26:44Z"},{"alias_kind":"pith_short_8","alias_value":"5O7LBIGX","created_at":"2026-07-05T05:26:44Z"}],"graph_snapshots":[{"event_id":"sha256:ef16092687f817266fa02f9460d60dd7a204103a14a544a8c438c11320232ac1","target":"graph","created_at":"2026-07-05T05:26:44Z","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/2207.00779/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Following how humans communicate, free-text rationales aim to use natural language to explain neural language model (LM) behavior. However, free-text rationales' unconstrained nature makes them prone to hallucination, so it is important to have metrics for free-text rationale quality. Existing free-text rationale metrics measure how consistent the rationale is with the LM's predicted label, but there is no protocol for assessing such metrics' reliability. Thus, we propose FRAME, a framework for evaluating rationale-label consistency (RLC) metrics for free-text rationales. FRAME is based on thr","authors_text":"Aaron Chan, Hamed Firooz, Liang Tan, Maziar Sanjabi, Shaoliang Nie, Xiang Ren, Xiaochang Peng","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-02T09:25:29Z","title":"FRAME: Evaluating Rationale-Label Consistency Metrics for Free-Text Rationales"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00779","kind":"arxiv","version":2},"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":"sha256:3c6014d1631fac2004c0208516a13db6c7cbe78809aa5a016f3e8ed5b96faaf8","target":"record","created_at":"2026-07-05T05:26:44Z","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":"29b437d66645c2bc5bfaa5ca982c882eec21243933b35e8847566d7e9c9e067e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-02T09:25:29Z","title_canon_sha256":"a081a0827a82a49c341d8dfd633b3f93b5972867092ffcaf52e7c09076b24941"},"schema_version":"1.0","source":{"id":"2207.00779","kind":"arxiv","version":2}},"canonical_sha256":"ebbeb0a0d7ffa60858c6bcd04f256e43e6331674a9aa47e9afe935d7102b4931","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebbeb0a0d7ffa60858c6bcd04f256e43e6331674a9aa47e9afe935d7102b4931","first_computed_at":"2026-07-05T05:26:44.424916Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:26:44.424916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zpklJnMMuRHvV3qesULV8jCEBOoGSaBhfHH8xThClUEsNyQeulBjo+3FxC4bl/+diHKVYn8fd+N3obIyR8OfBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:26:44.425344Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.00779","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c6014d1631fac2004c0208516a13db6c7cbe78809aa5a016f3e8ed5b96faaf8","sha256:ef16092687f817266fa02f9460d60dd7a204103a14a544a8c438c11320232ac1"],"state_sha256":"03cea17b434dca854ab6980aec977e9e506983eeacf6f5f7b6e0d0665336a3bf"}