{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GLRNSZBYNA57XVPPKI7XO72YVD","short_pith_number":"pith:GLRNSZBY","canonical_record":{"source":{"id":"2502.02896","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T05:37:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"85e8fc219092d6ca8e6b129be0e1550ce90125d53e3f4f213132f0148c7ca281","abstract_canon_sha256":"fe05cfb60bd338aea34223310bf09befc48c79a0be1701be2cfe88dd02c51b64"},"schema_version":"1.0"},"canonical_sha256":"32e2d96438683bfbd5ef523f777f58a8c62214efec21c3714aea3c926b70c6b1","source":{"kind":"arxiv","id":"2502.02896","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02896","created_at":"2026-07-05T10:09:56Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02896v1","created_at":"2026-07-05T10:09:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02896","created_at":"2026-07-05T10:09:56Z"},{"alias_kind":"pith_short_12","alias_value":"GLRNSZBYNA57","created_at":"2026-07-05T10:09:56Z"},{"alias_kind":"pith_short_16","alias_value":"GLRNSZBYNA57XVPP","created_at":"2026-07-05T10:09:56Z"},{"alias_kind":"pith_short_8","alias_value":"GLRNSZBY","created_at":"2026-07-05T10:09:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GLRNSZBYNA57XVPPKI7XO72YVD","target":"record","payload":{"canonical_record":{"source":{"id":"2502.02896","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T05:37:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"85e8fc219092d6ca8e6b129be0e1550ce90125d53e3f4f213132f0148c7ca281","abstract_canon_sha256":"fe05cfb60bd338aea34223310bf09befc48c79a0be1701be2cfe88dd02c51b64"},"schema_version":"1.0"},"canonical_sha256":"32e2d96438683bfbd5ef523f777f58a8c62214efec21c3714aea3c926b70c6b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:56.492646Z","signature_b64":"bkoBzKU/Axz9IDjkW5SZ7fvEBKV6+ncqsnii91S4OQfyDw8mVPFvAWP7HstSKKhyYGN4IY101yRih5xn9Tz9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32e2d96438683bfbd5ef523f777f58a8c62214efec21c3714aea3c926b70c6b1","last_reissued_at":"2026-07-05T10:09:56.492196Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:56.492196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.02896","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":"2026-07-05T10:09:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HExRVUhMYO480LQH584JfRExbxAErnvX3Jw8lnR64Jheds9koxopTtWX6pdrFlwI75XFcd3LgGyVijOufKDaCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:37:13.225004Z"},"content_sha256":"5dd333dd8097bdfec2fb378792deb7d590c097dff88bb481f80b4c2f136d0b05","schema_version":"1.0","event_id":"sha256:5dd333dd8097bdfec2fb378792deb7d590c097dff88bb481f80b4c2f136d0b05"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GLRNSZBYNA57XVPPKI7XO72YVD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Benchmark for the Detection of Metalinguistic Disagreements between LLMs and Knowledge Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bradley P. Allen, Paul T. Groth","submitted_at":"2025-02-05T05:37:26Z","abstract_excerpt":"Evaluating large language models (LLMs) for tasks like fact extraction in support of knowledge graph construction frequently involves computing accuracy metrics using a ground truth benchmark based on a knowledge graph (KG). These evaluations assume that errors represent factual disagreements. However, human discourse frequently features metalinguistic disagreement, where agents differ not on facts but on the meaning of the language used to express them. Given the complexity of natural language processing and generation using LLMs, we ask: do metalinguistic disagreements occur between LLMs and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02896","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/2502.02896/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":"2026-07-05T10:09:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZmRG9WvwKD/EL5qNwU52LpJccoWeHEahJQHO6jGgvvflWBzCwgina9bQ5UylvSPO/sRlU0qWZbtS7GpD1KMgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:37:13.225509Z"},"content_sha256":"f0f21b0ea7819accbb23085061f7ec42ed4e5c1fb0d4b4d8c4eea95ff70a766a","schema_version":"1.0","event_id":"sha256:f0f21b0ea7819accbb23085061f7ec42ed4e5c1fb0d4b4d8c4eea95ff70a766a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GLRNSZBYNA57XVPPKI7XO72YVD/bundle.json","state_url":"https://pith.science/pith/GLRNSZBYNA57XVPPKI7XO72YVD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GLRNSZBYNA57XVPPKI7XO72YVD/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":"2026-08-10T19:37:13Z","links":{"resolver":"https://pith.science/pith/GLRNSZBYNA57XVPPKI7XO72YVD","bundle":"https://pith.science/pith/GLRNSZBYNA57XVPPKI7XO72YVD/bundle.json","state":"https://pith.science/pith/GLRNSZBYNA57XVPPKI7XO72YVD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GLRNSZBYNA57XVPPKI7XO72YVD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GLRNSZBYNA57XVPPKI7XO72YVD","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":"fe05cfb60bd338aea34223310bf09befc48c79a0be1701be2cfe88dd02c51b64","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T05:37:26Z","title_canon_sha256":"85e8fc219092d6ca8e6b129be0e1550ce90125d53e3f4f213132f0148c7ca281"},"schema_version":"1.0","source":{"id":"2502.02896","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02896","created_at":"2026-07-05T10:09:56Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02896v1","created_at":"2026-07-05T10:09:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02896","created_at":"2026-07-05T10:09:56Z"},{"alias_kind":"pith_short_12","alias_value":"GLRNSZBYNA57","created_at":"2026-07-05T10:09:56Z"},{"alias_kind":"pith_short_16","alias_value":"GLRNSZBYNA57XVPP","created_at":"2026-07-05T10:09:56Z"},{"alias_kind":"pith_short_8","alias_value":"GLRNSZBY","created_at":"2026-07-05T10:09:56Z"}],"graph_snapshots":[{"event_id":"sha256:f0f21b0ea7819accbb23085061f7ec42ed4e5c1fb0d4b4d8c4eea95ff70a766a","target":"graph","created_at":"2026-07-05T10:09:56Z","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/2502.02896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating large language models (LLMs) for tasks like fact extraction in support of knowledge graph construction frequently involves computing accuracy metrics using a ground truth benchmark based on a knowledge graph (KG). These evaluations assume that errors represent factual disagreements. However, human discourse frequently features metalinguistic disagreement, where agents differ not on facts but on the meaning of the language used to express them. Given the complexity of natural language processing and generation using LLMs, we ask: do metalinguistic disagreements occur between LLMs and","authors_text":"Bradley P. Allen, Paul T. Groth","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T05:37:26Z","title":"A Benchmark for the Detection of Metalinguistic Disagreements between LLMs and Knowledge Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02896","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":"sha256:5dd333dd8097bdfec2fb378792deb7d590c097dff88bb481f80b4c2f136d0b05","target":"record","created_at":"2026-07-05T10:09:56Z","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":"fe05cfb60bd338aea34223310bf09befc48c79a0be1701be2cfe88dd02c51b64","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T05:37:26Z","title_canon_sha256":"85e8fc219092d6ca8e6b129be0e1550ce90125d53e3f4f213132f0148c7ca281"},"schema_version":"1.0","source":{"id":"2502.02896","kind":"arxiv","version":1}},"canonical_sha256":"32e2d96438683bfbd5ef523f777f58a8c62214efec21c3714aea3c926b70c6b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32e2d96438683bfbd5ef523f777f58a8c62214efec21c3714aea3c926b70c6b1","first_computed_at":"2026-07-05T10:09:56.492196Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:56.492196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bkoBzKU/Axz9IDjkW5SZ7fvEBKV6+ncqsnii91S4OQfyDw8mVPFvAWP7HstSKKhyYGN4IY101yRih5xn9Tz9Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:56.492646Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02896","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5dd333dd8097bdfec2fb378792deb7d590c097dff88bb481f80b4c2f136d0b05","sha256:f0f21b0ea7819accbb23085061f7ec42ed4e5c1fb0d4b4d8c4eea95ff70a766a"],"state_sha256":"559d96e953df472bab5eb8ff667feea739ffbe20dc6f63d872ba2c8981212e06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1+720vCXSUBZPij/CtUh4fY7BscMJU9GkX+olkvdq3TWX/ajHoJ7yfNH8QIEMNsBpvbz8RwT+i7lBcmsYRNKAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T19:37:13.230584Z","bundle_sha256":"7e72c59fb56980562d48438dd8ada246e64170b3349e9fa61ebd28980b398c9a"}}