{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MVL6Q7EF3WFUL6RKIEMH7GIYS4","short_pith_number":"pith:MVL6Q7EF","schema_version":"1.0","canonical_sha256":"6557e87c85dd8b45fa2a41187f9918972aed984fd618a3e7a7938922de8560a0","source":{"kind":"arxiv","id":"2412.13378","version":2},"attestation_state":"computed","paper":{"title":"SummExecEdit: A Factual Consistency Benchmark in Summarization with Executable Edits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chien-Sheng Wu, Onkar Thorat, Philippe Laban","submitted_at":"2024-12-17T23:26:44Z","abstract_excerpt":"Detecting factual inconsistencies in summarization is critical, yet existing benchmarks lack the necessary challenge and interpretability for robust evaluation. In this paper, we introduce SummExecEdit, a novel pipeline and benchmark leveraging executable edits to assess models on their ability to both detect factual errors and provide accurate explanations. The top-performing model, Claude3-Opus, achieves a joint detection and explanation score of only 0.49 in our benchmark, with individual scores of 0.67 for detection and 0.73 for explanation. We conduct detailed evaluations to assess the cu"},"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":"2412.13378","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T23:26:44Z","cross_cats_sorted":[],"title_canon_sha256":"c6a1a65f7c6e795bad8b7c5d3f967df829a1ec455a7fde05655ca82ebbfc617e","abstract_canon_sha256":"24d2fa225377d230e7531a7581aeaf09bdeb6caf5081c62950403e11145589e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:17.220693Z","signature_b64":"Lai7V1HuOszGyajCgobV7KkyIh6lmWfge5CRVBxdgtGk1sF/uiVEMgCqAoANwsINwanrUi3WasTTemw6D0PHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6557e87c85dd8b45fa2a41187f9918972aed984fd618a3e7a7938922de8560a0","last_reissued_at":"2026-07-05T11:13:17.220251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:17.220251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SummExecEdit: A Factual Consistency Benchmark in Summarization with Executable Edits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chien-Sheng Wu, Onkar Thorat, Philippe Laban","submitted_at":"2024-12-17T23:26:44Z","abstract_excerpt":"Detecting factual inconsistencies in summarization is critical, yet existing benchmarks lack the necessary challenge and interpretability for robust evaluation. In this paper, we introduce SummExecEdit, a novel pipeline and benchmark leveraging executable edits to assess models on their ability to both detect factual errors and provide accurate explanations. The top-performing model, Claude3-Opus, achieves a joint detection and explanation score of only 0.49 in our benchmark, with individual scores of 0.67 for detection and 0.73 for explanation. We conduct detailed evaluations to assess the cu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13378","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/2412.13378/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":"2412.13378","created_at":"2026-07-05T11:13:17.220304+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13378v2","created_at":"2026-07-05T11:13:17.220304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13378","created_at":"2026-07-05T11:13:17.220304+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVL6Q7EF3WFU","created_at":"2026-07-05T11:13:17.220304+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVL6Q7EF3WFUL6RK","created_at":"2026-07-05T11:13:17.220304+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVL6Q7EF","created_at":"2026-07-05T11:13:17.220304+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/MVL6Q7EF3WFUL6RKIEMH7GIYS4","json":"https://pith.science/pith/MVL6Q7EF3WFUL6RKIEMH7GIYS4.json","graph_json":"https://pith.science/api/pith-number/MVL6Q7EF3WFUL6RKIEMH7GIYS4/graph.json","events_json":"https://pith.science/api/pith-number/MVL6Q7EF3WFUL6RKIEMH7GIYS4/events.json","paper":"https://pith.science/paper/MVL6Q7EF"},"agent_actions":{"view_html":"https://pith.science/pith/MVL6Q7EF3WFUL6RKIEMH7GIYS4","download_json":"https://pith.science/pith/MVL6Q7EF3WFUL6RKIEMH7GIYS4.json","view_paper":"https://pith.science/paper/MVL6Q7EF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13378&json=true","fetch_graph":"https://pith.science/api/pith-number/MVL6Q7EF3WFUL6RKIEMH7GIYS4/graph.json","fetch_events":"https://pith.science/api/pith-number/MVL6Q7EF3WFUL6RKIEMH7GIYS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVL6Q7EF3WFUL6RKIEMH7GIYS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVL6Q7EF3WFUL6RKIEMH7GIYS4/action/storage_attestation","attest_author":"https://pith.science/pith/MVL6Q7EF3WFUL6RKIEMH7GIYS4/action/author_attestation","sign_citation":"https://pith.science/pith/MVL6Q7EF3WFUL6RKIEMH7GIYS4/action/citation_signature","submit_replication":"https://pith.science/pith/MVL6Q7EF3WFUL6RKIEMH7GIYS4/action/replication_record"}},"created_at":"2026-07-05T11:13:17.220304+00:00","updated_at":"2026-07-05T11:13:17.220304+00:00"}