{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MCV2U6A5CKVW3VZIGRBPGE6IKI","short_pith_number":"pith:MCV2U6A5","canonical_record":{"source":{"id":"2406.01855","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T00:01:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ec8232354b92cd0cef77e016a486935620d62d6f267c16e4e144138730fd3501","abstract_canon_sha256":"971e382576d9e413078e6a97ed18d5d19ae5b160ba47b7e5a12df8784b65a2ad"},"schema_version":"1.0"},"canonical_sha256":"60abaa781d12ab6dd7283442f313c8522fd6b08adf8a58c1a0ba6d2314ea1128","source":{"kind":"arxiv","id":"2406.01855","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01855","created_at":"2026-07-05T08:26:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01855v1","created_at":"2026-07-05T08:26:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01855","created_at":"2026-07-05T08:26:49Z"},{"alias_kind":"pith_short_12","alias_value":"MCV2U6A5CKVW","created_at":"2026-07-05T08:26:49Z"},{"alias_kind":"pith_short_16","alias_value":"MCV2U6A5CKVW3VZI","created_at":"2026-07-05T08:26:49Z"},{"alias_kind":"pith_short_8","alias_value":"MCV2U6A5","created_at":"2026-07-05T08:26:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MCV2U6A5CKVW3VZIGRBPGE6IKI","target":"record","payload":{"canonical_record":{"source":{"id":"2406.01855","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T00:01:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ec8232354b92cd0cef77e016a486935620d62d6f267c16e4e144138730fd3501","abstract_canon_sha256":"971e382576d9e413078e6a97ed18d5d19ae5b160ba47b7e5a12df8784b65a2ad"},"schema_version":"1.0"},"canonical_sha256":"60abaa781d12ab6dd7283442f313c8522fd6b08adf8a58c1a0ba6d2314ea1128","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:49.592246Z","signature_b64":"A9JbdgFkQC+LqiG7nHnzbWr+8e663QVykdYaj5NYsOq4mMOIbvH7x7mfkQORFz9GaHtHRdXiF0GV2AZfqpeCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60abaa781d12ab6dd7283442f313c8522fd6b08adf8a58c1a0ba6d2314ea1128","last_reissued_at":"2026-07-05T08:26:49.591550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:49.591550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.01855","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":"2026-07-05T08:26:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yq4sK86RRfGzFBONNg+c2w3D6M3xft715Pbg4/woZzOGBSlE7mo+e1NTRn93yQXefBwaUUgYJnEvS9Nfm9o2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T09:42:38.487672Z"},"content_sha256":"7a185a0a823a82d18f332e71ea58c96bdd4e258f408ed96aaeffe956509dfa9a","schema_version":"1.0","event_id":"sha256:7a185a0a823a82d18f332e71ea58c96bdd4e258f408ed96aaeffe956509dfa9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MCV2U6A5CKVW3VZIGRBPGE6IKI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TruthEval: A Dataset to Evaluate LLM Truthfulness and Reliability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aisha Khatun, Daniel G. Brown","submitted_at":"2024-06-04T00:01:35Z","abstract_excerpt":"Large Language Model (LLM) evaluation is currently one of the most important areas of research, with existing benchmarks proving to be insufficient and not completely representative of LLMs' various capabilities. We present a curated collection of challenging statements on sensitive topics for LLM benchmarking called TruthEval. These statements were curated by hand and contain known truth values. The categories were chosen to distinguish LLMs' abilities from their stochastic nature. We perform some initial analyses using this dataset and find several instances of LLMs failing in simple tasks s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01855","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/2406.01855/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":"2026-07-05T08:26:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"du55m73b9TqEq29mKA2nPGeBWj7jIe4SXtzb40K7I2iPW8b+R6vMQcUntUVmyASjy0Ago9xYsvcmgEi9UkKwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T09:42:38.488182Z"},"content_sha256":"56bb2b6e26838d315b2c0e8e901515632c6af7dfec17c575d54d9d8b7d7f2fca","schema_version":"1.0","event_id":"sha256:56bb2b6e26838d315b2c0e8e901515632c6af7dfec17c575d54d9d8b7d7f2fca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MCV2U6A5CKVW3VZIGRBPGE6IKI/bundle.json","state_url":"https://pith.science/pith/MCV2U6A5CKVW3VZIGRBPGE6IKI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MCV2U6A5CKVW3VZIGRBPGE6IKI/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":"2026-08-21T09:42:38Z","links":{"resolver":"https://pith.science/pith/MCV2U6A5CKVW3VZIGRBPGE6IKI","bundle":"https://pith.science/pith/MCV2U6A5CKVW3VZIGRBPGE6IKI/bundle.json","state":"https://pith.science/pith/MCV2U6A5CKVW3VZIGRBPGE6IKI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MCV2U6A5CKVW3VZIGRBPGE6IKI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MCV2U6A5CKVW3VZIGRBPGE6IKI","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":"971e382576d9e413078e6a97ed18d5d19ae5b160ba47b7e5a12df8784b65a2ad","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T00:01:35Z","title_canon_sha256":"ec8232354b92cd0cef77e016a486935620d62d6f267c16e4e144138730fd3501"},"schema_version":"1.0","source":{"id":"2406.01855","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01855","created_at":"2026-07-05T08:26:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01855v1","created_at":"2026-07-05T08:26:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01855","created_at":"2026-07-05T08:26:49Z"},{"alias_kind":"pith_short_12","alias_value":"MCV2U6A5CKVW","created_at":"2026-07-05T08:26:49Z"},{"alias_kind":"pith_short_16","alias_value":"MCV2U6A5CKVW3VZI","created_at":"2026-07-05T08:26:49Z"},{"alias_kind":"pith_short_8","alias_value":"MCV2U6A5","created_at":"2026-07-05T08:26:49Z"}],"graph_snapshots":[{"event_id":"sha256:56bb2b6e26838d315b2c0e8e901515632c6af7dfec17c575d54d9d8b7d7f2fca","target":"graph","created_at":"2026-07-05T08:26:49Z","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/2406.01855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Model (LLM) evaluation is currently one of the most important areas of research, with existing benchmarks proving to be insufficient and not completely representative of LLMs' various capabilities. We present a curated collection of challenging statements on sensitive topics for LLM benchmarking called TruthEval. These statements were curated by hand and contain known truth values. The categories were chosen to distinguish LLMs' abilities from their stochastic nature. We perform some initial analyses using this dataset and find several instances of LLMs failing in simple tasks s","authors_text":"Aisha Khatun, Daniel G. Brown","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T00:01:35Z","title":"TruthEval: A Dataset to Evaluate LLM Truthfulness and Reliability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01855","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":"sha256:7a185a0a823a82d18f332e71ea58c96bdd4e258f408ed96aaeffe956509dfa9a","target":"record","created_at":"2026-07-05T08:26:49Z","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":"971e382576d9e413078e6a97ed18d5d19ae5b160ba47b7e5a12df8784b65a2ad","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T00:01:35Z","title_canon_sha256":"ec8232354b92cd0cef77e016a486935620d62d6f267c16e4e144138730fd3501"},"schema_version":"1.0","source":{"id":"2406.01855","kind":"arxiv","version":1}},"canonical_sha256":"60abaa781d12ab6dd7283442f313c8522fd6b08adf8a58c1a0ba6d2314ea1128","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60abaa781d12ab6dd7283442f313c8522fd6b08adf8a58c1a0ba6d2314ea1128","first_computed_at":"2026-07-05T08:26:49.591550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:49.591550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A9JbdgFkQC+LqiG7nHnzbWr+8e663QVykdYaj5NYsOq4mMOIbvH7x7mfkQORFz9GaHtHRdXiF0GV2AZfqpeCAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:49.592246Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01855","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a185a0a823a82d18f332e71ea58c96bdd4e258f408ed96aaeffe956509dfa9a","sha256:56bb2b6e26838d315b2c0e8e901515632c6af7dfec17c575d54d9d8b7d7f2fca"],"state_sha256":"843a1cb9d8b9e22c0ba6b83d25c77f88bdcb5381eeb540d9674e8080829231c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"enx875CBa+D+AaWsDBCDYk+rZsld78K3+9djfD8cQieHu8Z5IQqasPeMciVpfmrQG05MkKHYV3ZyR2WR8qP2Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T09:42:38.492659Z","bundle_sha256":"d028be5ca6201837097fe0c0b1409bb8c248cd8cd790a1976bd25a9c12f4646f"}}