{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UHKR2VFXWK5EBS5ESRHZKAWZX3","short_pith_number":"pith:UHKR2VFX","schema_version":"1.0","canonical_sha256":"a1d51d54b7b2ba40cba4944f9502d9beec63b842cf73797fa6622bb666bf96d1","source":{"kind":"arxiv","id":"2407.03572","version":2},"attestation_state":"computed","paper":{"title":"Core: Robust Factual Precision with Informative Sub-Claim Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anqi Liu, Benjamin Van Durme, Daniel Khashabi, Jingyu Zhang, Kate Sanders, Miriam Wanner, Nathaniel Weir, Seth Ebner, Zhengping Jiang","submitted_at":"2024-07-04T01:51:38Z","abstract_excerpt":"Hallucinations pose a challenge to the application of large language models (LLMs) thereby motivating the development of metrics to evaluate factual precision. We observe that popular metrics using the Decompose-Then-Verify framework, such as \\FActScore, can be manipulated by adding obvious or repetitive subclaims to artificially inflate scores. This observation motivates our new customizable plug-and-play subclaim selection component called Core, which filters down individual subclaims according to their uniqueness and informativeness. We show that many popular factual precision metrics augme"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.03572","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-04T01:51:38Z","cross_cats_sorted":[],"title_canon_sha256":"0424a7310f0db3a61dbdf7528dcfa61d5315b086d0856385f0d45c51ccd5b19a","abstract_canon_sha256":"40f95c71c1ff6017e126ed4c7654faec77ce9ddcf92003f9378a0c77154a8999"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:06.092878Z","signature_b64":"PqsJbjGiAe/XxsjzSIog/d1LkN7Wt0gSS8lh8WHX8W+FHrzcgu/OGbhaKM6OqK18JnX+EYHQUfHM7ychwXAbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1d51d54b7b2ba40cba4944f9502d9beec63b842cf73797fa6622bb666bf96d1","last_reissued_at":"2026-07-05T09:21:06.092405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:06.092405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Core: Robust Factual Precision with Informative Sub-Claim Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anqi Liu, Benjamin Van Durme, Daniel Khashabi, Jingyu Zhang, Kate Sanders, Miriam Wanner, Nathaniel Weir, Seth Ebner, Zhengping Jiang","submitted_at":"2024-07-04T01:51:38Z","abstract_excerpt":"Hallucinations pose a challenge to the application of large language models (LLMs) thereby motivating the development of metrics to evaluate factual precision. We observe that popular metrics using the Decompose-Then-Verify framework, such as \\FActScore, can be manipulated by adding obvious or repetitive subclaims to artificially inflate scores. This observation motivates our new customizable plug-and-play subclaim selection component called Core, which filters down individual subclaims according to their uniqueness and informativeness. We show that many popular factual precision metrics augme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03572","kind":"arxiv","version":2},"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/2407.03572/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.03572","created_at":"2026-07-05T09:21:06.092470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03572v2","created_at":"2026-07-05T09:21:06.092470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03572","created_at":"2026-07-05T09:21:06.092470+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHKR2VFXWK5E","created_at":"2026-07-05T09:21:06.092470+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHKR2VFXWK5EBS5E","created_at":"2026-07-05T09:21:06.092470+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHKR2VFX","created_at":"2026-07-05T09:21:06.092470+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UHKR2VFXWK5EBS5ESRHZKAWZX3","json":"https://pith.science/pith/UHKR2VFXWK5EBS5ESRHZKAWZX3.json","graph_json":"https://pith.science/api/pith-number/UHKR2VFXWK5EBS5ESRHZKAWZX3/graph.json","events_json":"https://pith.science/api/pith-number/UHKR2VFXWK5EBS5ESRHZKAWZX3/events.json","paper":"https://pith.science/paper/UHKR2VFX"},"agent_actions":{"view_html":"https://pith.science/pith/UHKR2VFXWK5EBS5ESRHZKAWZX3","download_json":"https://pith.science/pith/UHKR2VFXWK5EBS5ESRHZKAWZX3.json","view_paper":"https://pith.science/paper/UHKR2VFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03572&json=true","fetch_graph":"https://pith.science/api/pith-number/UHKR2VFXWK5EBS5ESRHZKAWZX3/graph.json","fetch_events":"https://pith.science/api/pith-number/UHKR2VFXWK5EBS5ESRHZKAWZX3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHKR2VFXWK5EBS5ESRHZKAWZX3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHKR2VFXWK5EBS5ESRHZKAWZX3/action/storage_attestation","attest_author":"https://pith.science/pith/UHKR2VFXWK5EBS5ESRHZKAWZX3/action/author_attestation","sign_citation":"https://pith.science/pith/UHKR2VFXWK5EBS5ESRHZKAWZX3/action/citation_signature","submit_replication":"https://pith.science/pith/UHKR2VFXWK5EBS5ESRHZKAWZX3/action/replication_record"}},"created_at":"2026-07-05T09:21:06.092470+00:00","updated_at":"2026-07-05T09:21:06.092470+00:00"}