{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UMLLQDJQY3V2WIGG4FXGRCTVXG","short_pith_number":"pith:UMLLQDJQ","canonical_record":{"source":{"id":"2506.12538","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-14T15:27:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"78b7693ff2df078f76a0bce50c8aaa94bab8e432890ac88963a2e71a1d9235a0","abstract_canon_sha256":"705c9a3ef17d9a8651e1b4ae0a2e14f6dab227b3acf5487678e27d59749f35bc"},"schema_version":"1.0"},"canonical_sha256":"a316b80d30c6ebab20c6e16e688a75b9a0df797a9903eda4903ed877ccb3b5fb","source":{"kind":"arxiv","id":"2506.12538","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12538","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12538v1","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12538","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"pith_short_12","alias_value":"UMLLQDJQY3V2","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"pith_short_16","alias_value":"UMLLQDJQY3V2WIGG","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"pith_short_8","alias_value":"UMLLQDJQ","created_at":"2026-07-05T11:21:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UMLLQDJQY3V2WIGG4FXGRCTVXG","target":"record","payload":{"canonical_record":{"source":{"id":"2506.12538","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-14T15:27:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"78b7693ff2df078f76a0bce50c8aaa94bab8e432890ac88963a2e71a1d9235a0","abstract_canon_sha256":"705c9a3ef17d9a8651e1b4ae0a2e14f6dab227b3acf5487678e27d59749f35bc"},"schema_version":"1.0"},"canonical_sha256":"a316b80d30c6ebab20c6e16e688a75b9a0df797a9903eda4903ed877ccb3b5fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:54.956228Z","signature_b64":"1Ei7Z+30UUvzrxejzr8dGNzc2hjGbSERfkZPoUvcnqdEb8iWuKnXkHPlVLZl4PyA4ju7DUNzjuxFcND0EBO8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a316b80d30c6ebab20c6e16e688a75b9a0df797a9903eda4903ed877ccb3b5fb","last_reissued_at":"2026-07-05T11:21:54.955758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:54.955758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.12538","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":"2026-07-05T11:21:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bUcCpg3aeilyk+lug6oq/gbVWb2qk2vnKKYshCBlStx1M0NGXXHUEKSwORyjnSsfdKSsuuAj/fQrbkcMZcn1Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:12:59.083744Z"},"content_sha256":"4ca8d5312d891fb54e6a6cbf9ee6582e6b4d1960bbc4a55f74800cab73d37fa0","schema_version":"1.0","event_id":"sha256:4ca8d5312d891fb54e6a6cbf9ee6582e6b4d1960bbc4a55f74800cab73d37fa0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UMLLQDJQY3V2WIGG4FXGRCTVXG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Edith C.H. Ngai, Guoqing Wang, Jinfeng Xu, Jinze Li, Shuo Yang, Weiqiang Wang, Xinran Zheng, Yuqin Dai, Zhenzhe Ying","submitted_at":"2025-06-14T15:27:44Z","abstract_excerpt":"Large Language Models (LLMs) hold significant potential for advancing fact-checking by leveraging their capabilities in reasoning, evidence retrieval, and explanation generation. However, existing benchmarks fail to comprehensively evaluate LLMs and Multimodal Large Language Models (MLLMs) in realistic misinformation scenarios. To bridge this gap, we introduce RealFactBench, a comprehensive benchmark designed to assess the fact-checking capabilities of LLMs and MLLMs across diverse real-world tasks, including Knowledge Validation, Rumor Detection, and Event Verification. RealFactBench consists"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12538","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/2506.12538/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":"2026-07-05T11:21:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TFdogw7BG20pgvMx8peBJnHgmqMgqU1hVxre/bw/ogcqDXwP8+XkU3Xx7KUzv0CaQczy2aTJn1UM17Ieqy4NCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:12:59.084355Z"},"content_sha256":"7a0938426baa47bc314f43888841c40c6dabacc341a4d77caf4ebc6b748badac","schema_version":"1.0","event_id":"sha256:7a0938426baa47bc314f43888841c40c6dabacc341a4d77caf4ebc6b748badac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UMLLQDJQY3V2WIGG4FXGRCTVXG/bundle.json","state_url":"https://pith.science/pith/UMLLQDJQY3V2WIGG4FXGRCTVXG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UMLLQDJQY3V2WIGG4FXGRCTVXG/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":"2026-08-05T11:12:59Z","links":{"resolver":"https://pith.science/pith/UMLLQDJQY3V2WIGG4FXGRCTVXG","bundle":"https://pith.science/pith/UMLLQDJQY3V2WIGG4FXGRCTVXG/bundle.json","state":"https://pith.science/pith/UMLLQDJQY3V2WIGG4FXGRCTVXG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UMLLQDJQY3V2WIGG4FXGRCTVXG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UMLLQDJQY3V2WIGG4FXGRCTVXG","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":"705c9a3ef17d9a8651e1b4ae0a2e14f6dab227b3acf5487678e27d59749f35bc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-14T15:27:44Z","title_canon_sha256":"78b7693ff2df078f76a0bce50c8aaa94bab8e432890ac88963a2e71a1d9235a0"},"schema_version":"1.0","source":{"id":"2506.12538","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12538","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12538v1","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12538","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"pith_short_12","alias_value":"UMLLQDJQY3V2","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"pith_short_16","alias_value":"UMLLQDJQY3V2WIGG","created_at":"2026-07-05T11:21:54Z"},{"alias_kind":"pith_short_8","alias_value":"UMLLQDJQ","created_at":"2026-07-05T11:21:54Z"}],"graph_snapshots":[{"event_id":"sha256:7a0938426baa47bc314f43888841c40c6dabacc341a4d77caf4ebc6b748badac","target":"graph","created_at":"2026-07-05T11:21:54Z","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/2506.12538/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) hold significant potential for advancing fact-checking by leveraging their capabilities in reasoning, evidence retrieval, and explanation generation. However, existing benchmarks fail to comprehensively evaluate LLMs and Multimodal Large Language Models (MLLMs) in realistic misinformation scenarios. To bridge this gap, we introduce RealFactBench, a comprehensive benchmark designed to assess the fact-checking capabilities of LLMs and MLLMs across diverse real-world tasks, including Knowledge Validation, Rumor Detection, and Event Verification. RealFactBench consists","authors_text":"Edith C.H. Ngai, Guoqing Wang, Jinfeng Xu, Jinze Li, Shuo Yang, Weiqiang Wang, Xinran Zheng, Yuqin Dai, Zhenzhe Ying","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-14T15:27:44Z","title":"RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12538","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":"sha256:4ca8d5312d891fb54e6a6cbf9ee6582e6b4d1960bbc4a55f74800cab73d37fa0","target":"record","created_at":"2026-07-05T11:21:54Z","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":"705c9a3ef17d9a8651e1b4ae0a2e14f6dab227b3acf5487678e27d59749f35bc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-14T15:27:44Z","title_canon_sha256":"78b7693ff2df078f76a0bce50c8aaa94bab8e432890ac88963a2e71a1d9235a0"},"schema_version":"1.0","source":{"id":"2506.12538","kind":"arxiv","version":1}},"canonical_sha256":"a316b80d30c6ebab20c6e16e688a75b9a0df797a9903eda4903ed877ccb3b5fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a316b80d30c6ebab20c6e16e688a75b9a0df797a9903eda4903ed877ccb3b5fb","first_computed_at":"2026-07-05T11:21:54.955758Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:54.955758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Ei7Z+30UUvzrxejzr8dGNzc2hjGbSERfkZPoUvcnqdEb8iWuKnXkHPlVLZl4PyA4ju7DUNzjuxFcND0EBO8Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:54.956228Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12538","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ca8d5312d891fb54e6a6cbf9ee6582e6b4d1960bbc4a55f74800cab73d37fa0","sha256:7a0938426baa47bc314f43888841c40c6dabacc341a4d77caf4ebc6b748badac"],"state_sha256":"5f01b77670c724d15024fb9deb1e5bdd31d691e3793bdb5f4da9ffbdaf52006f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JeKmldrH/nW+F6AQKYVqKI/NyTBLxghDJpyHNyj7M7ccHIpXKxeXNDtjuBTnvaQKxNzpglXqUEm8tUnz5Z9HAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:12:59.088560Z","bundle_sha256":"d228f1096d6ccb6183703af2966547cff2dd4d729ab3a62589abd61403c4a76e"}}