{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SVUJ7YBIDWHEZHJKQPIPR5NH3Z","short_pith_number":"pith:SVUJ7YBI","schema_version":"1.0","canonical_sha256":"95689fe0281d8e4c9d2a83d0f8f5a7de54a04b9a9098060cdbeaa1d16877fb63","source":{"kind":"arxiv","id":"2403.11903","version":1},"attestation_state":"computed","paper":{"title":"A Closer Look at Claim Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Van Durme, Mark Dredze, Miriam Wanner, Seth Ebner, Zhengping Jiang","submitted_at":"2024-03-18T16:03:45Z","abstract_excerpt":"As generated text becomes more commonplace, it is increasingly important to evaluate how well-supported such text is by external knowledge sources. Many approaches for evaluating textual support rely on some method for decomposing text into its individual subclaims which are scored against a trusted reference. We investigate how various methods of claim decomposition -- especially LLM-based methods -- affect the result of an evaluation approach such as the recently proposed FActScore, finding that it is sensitive to the decomposition method used. This sensitivity arises because such metrics at"},"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":"2403.11903","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T16:03:45Z","cross_cats_sorted":[],"title_canon_sha256":"c6a8195ad77f19719f3d7099bef3019f6af745681403a4997cf70e43fc2ae34b","abstract_canon_sha256":"43f619722faaf524646594e5678bd3bc5c91a8511268881a28a846186d1ebd42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:33.501977Z","signature_b64":"qH7gPMP12MuIfxuIyoSmB8u6lFg3rfzXI5D01f4+eD8G9mnOyxyNwL/iEWGcUGdIMdBpc91eCC7TEC00D/7DAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95689fe0281d8e4c9d2a83d0f8f5a7de54a04b9a9098060cdbeaa1d16877fb63","last_reissued_at":"2026-07-05T07:57:33.501505Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:33.501505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Closer Look at Claim Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Van Durme, Mark Dredze, Miriam Wanner, Seth Ebner, Zhengping Jiang","submitted_at":"2024-03-18T16:03:45Z","abstract_excerpt":"As generated text becomes more commonplace, it is increasingly important to evaluate how well-supported such text is by external knowledge sources. Many approaches for evaluating textual support rely on some method for decomposing text into its individual subclaims which are scored against a trusted reference. We investigate how various methods of claim decomposition -- especially LLM-based methods -- affect the result of an evaluation approach such as the recently proposed FActScore, finding that it is sensitive to the decomposition method used. This sensitivity arises because such metrics at"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11903","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/2403.11903/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":"2403.11903","created_at":"2026-07-05T07:57:33.501564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11903v1","created_at":"2026-07-05T07:57:33.501564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11903","created_at":"2026-07-05T07:57:33.501564+00:00"},{"alias_kind":"pith_short_12","alias_value":"SVUJ7YBIDWHE","created_at":"2026-07-05T07:57:33.501564+00:00"},{"alias_kind":"pith_short_16","alias_value":"SVUJ7YBIDWHEZHJK","created_at":"2026-07-05T07:57:33.501564+00:00"},{"alias_kind":"pith_short_8","alias_value":"SVUJ7YBI","created_at":"2026-07-05T07:57:33.501564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08080","citing_title":"NLI under the Microscope: What Atomic Hypothesis Decomposition Reveals","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SVUJ7YBIDWHEZHJKQPIPR5NH3Z","json":"https://pith.science/pith/SVUJ7YBIDWHEZHJKQPIPR5NH3Z.json","graph_json":"https://pith.science/api/pith-number/SVUJ7YBIDWHEZHJKQPIPR5NH3Z/graph.json","events_json":"https://pith.science/api/pith-number/SVUJ7YBIDWHEZHJKQPIPR5NH3Z/events.json","paper":"https://pith.science/paper/SVUJ7YBI"},"agent_actions":{"view_html":"https://pith.science/pith/SVUJ7YBIDWHEZHJKQPIPR5NH3Z","download_json":"https://pith.science/pith/SVUJ7YBIDWHEZHJKQPIPR5NH3Z.json","view_paper":"https://pith.science/paper/SVUJ7YBI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11903&json=true","fetch_graph":"https://pith.science/api/pith-number/SVUJ7YBIDWHEZHJKQPIPR5NH3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/SVUJ7YBIDWHEZHJKQPIPR5NH3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SVUJ7YBIDWHEZHJKQPIPR5NH3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SVUJ7YBIDWHEZHJKQPIPR5NH3Z/action/storage_attestation","attest_author":"https://pith.science/pith/SVUJ7YBIDWHEZHJKQPIPR5NH3Z/action/author_attestation","sign_citation":"https://pith.science/pith/SVUJ7YBIDWHEZHJKQPIPR5NH3Z/action/citation_signature","submit_replication":"https://pith.science/pith/SVUJ7YBIDWHEZHJKQPIPR5NH3Z/action/replication_record"}},"created_at":"2026-07-05T07:57:33.501564+00:00","updated_at":"2026-07-05T07:57:33.501564+00:00"}