{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7OH56DLYSZRINK5P5QDT6VDBKP","short_pith_number":"pith:7OH56DLY","canonical_record":{"source":{"id":"2605.25052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-24T12:57:01Z","cross_cats_sorted":[],"title_canon_sha256":"de6598d934f89ed8f0d464f562a9ae380f8967c19c5c42e96c7579e8cb1239af","abstract_canon_sha256":"c9ba4cd655f8724bfc6169097fe1a70ef2f511d8ca773b53c5f18d28870776d0"},"schema_version":"1.0"},"canonical_sha256":"fb8fdf0d78966286abafec073f546153e46029729f81bd8e2a8d56e51df20800","source":{"kind":"arxiv","id":"2605.25052","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25052","created_at":"2026-05-26T02:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25052v1","created_at":"2026-05-26T02:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25052","created_at":"2026-05-26T02:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"7OH56DLYSZRI","created_at":"2026-05-26T02:03:37Z"},{"alias_kind":"pith_short_16","alias_value":"7OH56DLYSZRINK5P","created_at":"2026-05-26T02:03:37Z"},{"alias_kind":"pith_short_8","alias_value":"7OH56DLY","created_at":"2026-05-26T02:03:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7OH56DLYSZRINK5P5QDT6VDBKP","target":"record","payload":{"canonical_record":{"source":{"id":"2605.25052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-24T12:57:01Z","cross_cats_sorted":[],"title_canon_sha256":"de6598d934f89ed8f0d464f562a9ae380f8967c19c5c42e96c7579e8cb1239af","abstract_canon_sha256":"c9ba4cd655f8724bfc6169097fe1a70ef2f511d8ca773b53c5f18d28870776d0"},"schema_version":"1.0"},"canonical_sha256":"fb8fdf0d78966286abafec073f546153e46029729f81bd8e2a8d56e51df20800","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:03:37.576838Z","signature_b64":"A/m4btdqRJBkQlvHPh1E8ybT4LHZ+6NizUIyMCsbLouAiDDSLEkm5hFGVf6JwmhI86phyDWD37OzOMs/QdkRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb8fdf0d78966286abafec073f546153e46029729f81bd8e2a8d56e51df20800","last_reissued_at":"2026-05-26T02:03:37.575802Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:03:37.575802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.25052","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:03:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mS74pJG2s92hdt50GFkmuPe1Ej/S0LxnG4Vzdj5Y0RRF7BHDciJOebWM1ECXBzHErQ8LH0pnnDASXc9qzPrdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-19T23:27:27.137552Z"},"content_sha256":"41b0790885ea3cbc961adc223e6ccb586445d0cd0d50fb0c6e5efc7a2b60b6e1","schema_version":"1.0","event_id":"sha256:41b0790885ea3cbc961adc223e6ccb586445d0cd0d50fb0c6e5efc7a2b60b6e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7OH56DLYSZRINK5P5QDT6VDBKP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ana Marasovi\\'c, Mor Geva, Yoav Gur-Arieh","submitted_at":"2026-05-24T12:57:01Z","abstract_excerpt":"Chains of thought (CoTs) have become central in interpreting and auditing behaviors of large language models. Yet growing evidence suggests that these traces often fail to faithfully represent the computations behind a model's predictions. Several faithfulness metrics have been proposed, but whether they indeed measure faithfulness remains unknown. Answering this requires ground-truth labels, which are hard to obtain since internal computations are not directly observable. Consequently, most works proposing metrics report only absolute scores or comparisons to prior metrics, and the few existi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25052","kind":"arxiv","version":1},"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/2605.25052/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":"2026-05-26T02:03:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nl1XbWPi5Q6QFiU2KUnlOOvJoiFK+GNEX9yLsTfvz9SPjA62y13aZBEfu++PhbKzHXWBnGkXzjeSjcq2tcGuCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-19T23:27:27.137930Z"},"content_sha256":"7bfe9bf29598f27ce94c5cfd65b90abc07bfcb5b6bcf0e78da6383e0c039b574","schema_version":"1.0","event_id":"sha256:7bfe9bf29598f27ce94c5cfd65b90abc07bfcb5b6bcf0e78da6383e0c039b574"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7OH56DLYSZRINK5P5QDT6VDBKP/bundle.json","state_url":"https://pith.science/pith/7OH56DLYSZRINK5P5QDT6VDBKP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7OH56DLYSZRINK5P5QDT6VDBKP/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":"2026-06-19T23:27:27Z","links":{"resolver":"https://pith.science/pith/7OH56DLYSZRINK5P5QDT6VDBKP","bundle":"https://pith.science/pith/7OH56DLYSZRINK5P5QDT6VDBKP/bundle.json","state":"https://pith.science/pith/7OH56DLYSZRINK5P5QDT6VDBKP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7OH56DLYSZRINK5P5QDT6VDBKP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7OH56DLYSZRINK5P5QDT6VDBKP","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":"c9ba4cd655f8724bfc6169097fe1a70ef2f511d8ca773b53c5f18d28870776d0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-24T12:57:01Z","title_canon_sha256":"de6598d934f89ed8f0d464f562a9ae380f8967c19c5c42e96c7579e8cb1239af"},"schema_version":"1.0","source":{"id":"2605.25052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25052","created_at":"2026-05-26T02:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25052v1","created_at":"2026-05-26T02:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25052","created_at":"2026-05-26T02:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"7OH56DLYSZRI","created_at":"2026-05-26T02:03:37Z"},{"alias_kind":"pith_short_16","alias_value":"7OH56DLYSZRINK5P","created_at":"2026-05-26T02:03:37Z"},{"alias_kind":"pith_short_8","alias_value":"7OH56DLY","created_at":"2026-05-26T02:03:37Z"}],"graph_snapshots":[{"event_id":"sha256:7bfe9bf29598f27ce94c5cfd65b90abc07bfcb5b6bcf0e78da6383e0c039b574","target":"graph","created_at":"2026-05-26T02:03:37Z","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/2605.25052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chains of thought (CoTs) have become central in interpreting and auditing behaviors of large language models. Yet growing evidence suggests that these traces often fail to faithfully represent the computations behind a model's predictions. Several faithfulness metrics have been proposed, but whether they indeed measure faithfulness remains unknown. Answering this requires ground-truth labels, which are hard to obtain since internal computations are not directly observable. Consequently, most works proposing metrics report only absolute scores or comparisons to prior metrics, and the few existi","authors_text":"Ana Marasovi\\'c, Mor Geva, Yoav Gur-Arieh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-24T12:57:01Z","title":"Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25052","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":"sha256:41b0790885ea3cbc961adc223e6ccb586445d0cd0d50fb0c6e5efc7a2b60b6e1","target":"record","created_at":"2026-05-26T02:03:37Z","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":"c9ba4cd655f8724bfc6169097fe1a70ef2f511d8ca773b53c5f18d28870776d0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-24T12:57:01Z","title_canon_sha256":"de6598d934f89ed8f0d464f562a9ae380f8967c19c5c42e96c7579e8cb1239af"},"schema_version":"1.0","source":{"id":"2605.25052","kind":"arxiv","version":1}},"canonical_sha256":"fb8fdf0d78966286abafec073f546153e46029729f81bd8e2a8d56e51df20800","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb8fdf0d78966286abafec073f546153e46029729f81bd8e2a8d56e51df20800","first_computed_at":"2026-05-26T02:03:37.575802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:03:37.575802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A/m4btdqRJBkQlvHPh1E8ybT4LHZ+6NizUIyMCsbLouAiDDSLEkm5hFGVf6JwmhI86phyDWD37OzOMs/QdkRBw==","signature_status":"signed_v1","signed_at":"2026-05-26T02:03:37.576838Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41b0790885ea3cbc961adc223e6ccb586445d0cd0d50fb0c6e5efc7a2b60b6e1","sha256:7bfe9bf29598f27ce94c5cfd65b90abc07bfcb5b6bcf0e78da6383e0c039b574"],"state_sha256":"0d7af16f7d3d06865e24ee30ea084630ece847e98656bbcaddd5476b2c2b7d6e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AVaOlBUNcTc2AJaEpb9oX9RTyrHjP4zj+MVDhXYxuY820HrRGzFz/457Jrx+OYDLhNN3vCiwtk0qahWNNiU8CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-19T23:27:27.139970Z","bundle_sha256":"34ff785ccb2b2c04cea9aa68ea4b48f644926d493573e2f7d2585054ba8520f0"}}