{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:H5MSPAPPWNPWJOGZLKG7KIVZF4","short_pith_number":"pith:H5MSPAPP","canonical_record":{"source":{"id":"2509.02198","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T11:09:52Z","cross_cats_sorted":[],"title_canon_sha256":"86c66e50948b1005d397e4bcfc74fb169486ccd41d176086b627caaa70184ad7","abstract_canon_sha256":"17b15ba1b207026554037a87bdc22b5199158087ff3ceb3edd6f99179ad00363"},"schema_version":"1.0"},"canonical_sha256":"3f592781efb35f64b8d95a8df522b92f207e6ae758f19697b2222583f8281a91","source":{"kind":"arxiv","id":"2509.02198","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02198","created_at":"2026-07-05T12:03:33Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02198v1","created_at":"2026-07-05T12:03:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02198","created_at":"2026-07-05T12:03:33Z"},{"alias_kind":"pith_short_12","alias_value":"H5MSPAPPWNPW","created_at":"2026-07-05T12:03:33Z"},{"alias_kind":"pith_short_16","alias_value":"H5MSPAPPWNPWJOGZ","created_at":"2026-07-05T12:03:33Z"},{"alias_kind":"pith_short_8","alias_value":"H5MSPAPP","created_at":"2026-07-05T12:03:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:H5MSPAPPWNPWJOGZLKG7KIVZF4","target":"record","payload":{"canonical_record":{"source":{"id":"2509.02198","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T11:09:52Z","cross_cats_sorted":[],"title_canon_sha256":"86c66e50948b1005d397e4bcfc74fb169486ccd41d176086b627caaa70184ad7","abstract_canon_sha256":"17b15ba1b207026554037a87bdc22b5199158087ff3ceb3edd6f99179ad00363"},"schema_version":"1.0"},"canonical_sha256":"3f592781efb35f64b8d95a8df522b92f207e6ae758f19697b2222583f8281a91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:33.817083Z","signature_b64":"uXErBP+h8o6rRSG8QU37AMThj76d4sjQo3RYgEd7XIu6PQ7k1wADrDgDWMpcUP7j8V0Rpid5075M/b/KoNBUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f592781efb35f64b8d95a8df522b92f207e6ae758f19697b2222583f8281a91","last_reissued_at":"2026-07-05T12:03:33.816558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:33.816558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.02198","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":"2026-07-05T12:03:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OX/m6VVr/E71yeOqE+rkSwJxRniU1NzcQQGZtoGjd/UVwmsha1wQL9jGkcHGUc0rtzzPRMcQIX87fQzkBjLZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:49:26.258778Z"},"content_sha256":"800c7feeb380fc4eda5bfc5db639dea78be4549fe9a9d508d17f6b9dbd83953e","schema_version":"1.0","event_id":"sha256:800c7feeb380fc4eda5bfc5db639dea78be4549fe9a9d508d17f6b9dbd83953e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:H5MSPAPPWNPWJOGZLKG7KIVZF4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anum Afzal, Florian Matthes, Juraj Vladika","submitted_at":"2025-09-02T11:09:52Z","abstract_excerpt":"Large Language Models tend to struggle when dealing with specialized domains. While all aspects of evaluation hold importance, factuality is the most critical one. Similarly, reliable fact-checking tools and data sources are essential for hallucination mitigation. We address these issues by providing a comprehensive Fact-checking Benchmark FActBench covering four generation tasks and six state-of-the-art Large Language Models (LLMs) for the Medical domain. We use two state-of-the-art Fact-checking techniques: Chain-of-Thought (CoT) Prompting and Natural Language Inference (NLI). Our experiment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02198","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/2509.02198/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":"2026-07-05T12:03:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"723k8s4ptiSk0hE7kyYgOOVpJQ7CPSjTQdJ9ZJr56vmvrjySE5LVsPJcSuYqvDOuxBahHowgemgSPlhQAKsXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:49:26.259383Z"},"content_sha256":"fae2e786945cf91538015ff8f0efbad21d1f6e5a5951d27c11f32a3a42e38592","schema_version":"1.0","event_id":"sha256:fae2e786945cf91538015ff8f0efbad21d1f6e5a5951d27c11f32a3a42e38592"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H5MSPAPPWNPWJOGZLKG7KIVZF4/bundle.json","state_url":"https://pith.science/pith/H5MSPAPPWNPWJOGZLKG7KIVZF4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H5MSPAPPWNPWJOGZLKG7KIVZF4/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":"2026-08-06T10:49:26Z","links":{"resolver":"https://pith.science/pith/H5MSPAPPWNPWJOGZLKG7KIVZF4","bundle":"https://pith.science/pith/H5MSPAPPWNPWJOGZLKG7KIVZF4/bundle.json","state":"https://pith.science/pith/H5MSPAPPWNPWJOGZLKG7KIVZF4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H5MSPAPPWNPWJOGZLKG7KIVZF4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H5MSPAPPWNPWJOGZLKG7KIVZF4","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":"17b15ba1b207026554037a87bdc22b5199158087ff3ceb3edd6f99179ad00363","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T11:09:52Z","title_canon_sha256":"86c66e50948b1005d397e4bcfc74fb169486ccd41d176086b627caaa70184ad7"},"schema_version":"1.0","source":{"id":"2509.02198","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02198","created_at":"2026-07-05T12:03:33Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02198v1","created_at":"2026-07-05T12:03:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02198","created_at":"2026-07-05T12:03:33Z"},{"alias_kind":"pith_short_12","alias_value":"H5MSPAPPWNPW","created_at":"2026-07-05T12:03:33Z"},{"alias_kind":"pith_short_16","alias_value":"H5MSPAPPWNPWJOGZ","created_at":"2026-07-05T12:03:33Z"},{"alias_kind":"pith_short_8","alias_value":"H5MSPAPP","created_at":"2026-07-05T12:03:33Z"}],"graph_snapshots":[{"event_id":"sha256:fae2e786945cf91538015ff8f0efbad21d1f6e5a5951d27c11f32a3a42e38592","target":"graph","created_at":"2026-07-05T12:03:33Z","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/2509.02198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models tend to struggle when dealing with specialized domains. While all aspects of evaluation hold importance, factuality is the most critical one. Similarly, reliable fact-checking tools and data sources are essential for hallucination mitigation. We address these issues by providing a comprehensive Fact-checking Benchmark FActBench covering four generation tasks and six state-of-the-art Large Language Models (LLMs) for the Medical domain. We use two state-of-the-art Fact-checking techniques: Chain-of-Thought (CoT) Prompting and Natural Language Inference (NLI). Our experiment","authors_text":"Anum Afzal, Florian Matthes, Juraj Vladika","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T11:09:52Z","title":"FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02198","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":"sha256:800c7feeb380fc4eda5bfc5db639dea78be4549fe9a9d508d17f6b9dbd83953e","target":"record","created_at":"2026-07-05T12:03:33Z","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":"17b15ba1b207026554037a87bdc22b5199158087ff3ceb3edd6f99179ad00363","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T11:09:52Z","title_canon_sha256":"86c66e50948b1005d397e4bcfc74fb169486ccd41d176086b627caaa70184ad7"},"schema_version":"1.0","source":{"id":"2509.02198","kind":"arxiv","version":1}},"canonical_sha256":"3f592781efb35f64b8d95a8df522b92f207e6ae758f19697b2222583f8281a91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f592781efb35f64b8d95a8df522b92f207e6ae758f19697b2222583f8281a91","first_computed_at":"2026-07-05T12:03:33.816558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:33.816558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uXErBP+h8o6rRSG8QU37AMThj76d4sjQo3RYgEd7XIu6PQ7k1wADrDgDWMpcUP7j8V0Rpid5075M/b/KoNBUAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:33.817083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02198","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:800c7feeb380fc4eda5bfc5db639dea78be4549fe9a9d508d17f6b9dbd83953e","sha256:fae2e786945cf91538015ff8f0efbad21d1f6e5a5951d27c11f32a3a42e38592"],"state_sha256":"61cd7e05a7dc67130036dba79240a1eb1be623ad6ef95f9024f1f0107937e81f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yS10QXwQJ+Xd0MdRHgaJLjA2V9e4QaehfY4Ringee1glvEAYs9gnXIoitwaaOWLfU2XAZ3KiYv7Drngx5dxvCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T10:49:26.263461Z","bundle_sha256":"91ae94bb3481c8ceecb9c8ce7f36b29fa90e641aae1d8ddd6106ca5e95b3a6c2"}}