{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MVL6Q7EF3WFUL6RKIEMH7GIYS4","short_pith_number":"pith:MVL6Q7EF","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"},"canonical_sha256":"6557e87c85dd8b45fa2a41187f9918972aed984fd618a3e7a7938922de8560a0","source":{"kind":"arxiv","id":"2412.13378","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13378","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13378v2","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13378","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"pith_short_12","alias_value":"MVL6Q7EF3WFU","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"pith_short_16","alias_value":"MVL6Q7EF3WFUL6RK","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"pith_short_8","alias_value":"MVL6Q7EF","created_at":"2026-07-05T11:13:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MVL6Q7EF3WFUL6RKIEMH7GIYS4","target":"record","payload":{"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"},"canonical_sha256":"6557e87c85dd8b45fa2a41187f9918972aed984fd618a3e7a7938922de8560a0","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"},"source_kind":"arxiv","source_id":"2412.13378","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/xwzYd1S/b59vhwKPoIJqdVYCihihZ6amRst4tm6jsSH4SwyqBtw6FsnoGLoxel4qiNs4viluSsL+VF+eMI7AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T08:46:15.894568Z"},"content_sha256":"e07a5d1cf7a1b4fb97f059189dc0fd247f98112228701a963417b141b0c1ae32","schema_version":"1.0","event_id":"sha256:e07a5d1cf7a1b4fb97f059189dc0fd247f98112228701a963417b141b0c1ae32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MVL6Q7EF3WFUL6RKIEMH7GIYS4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yjZmFpOoP6ebUyYERg2G6m6TMZ7F18feoTq4TFZuOVXIDK3xOjyODUU0C7lQlm2lxRMGDcGo4C17utfvL/n0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T08:46:15.895453Z"},"content_sha256":"c6edc196e1a495ea566fd9d9c8405e74b2aa475d82c7e0debaac8eb6c4eec30b","schema_version":"1.0","event_id":"sha256:c6edc196e1a495ea566fd9d9c8405e74b2aa475d82c7e0debaac8eb6c4eec30b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MVL6Q7EF3WFUL6RKIEMH7GIYS4/bundle.json","state_url":"https://pith.science/pith/MVL6Q7EF3WFUL6RKIEMH7GIYS4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MVL6Q7EF3WFUL6RKIEMH7GIYS4/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":"2026-08-12T08:46:15Z","links":{"resolver":"https://pith.science/pith/MVL6Q7EF3WFUL6RKIEMH7GIYS4","bundle":"https://pith.science/pith/MVL6Q7EF3WFUL6RKIEMH7GIYS4/bundle.json","state":"https://pith.science/pith/MVL6Q7EF3WFUL6RKIEMH7GIYS4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MVL6Q7EF3WFUL6RKIEMH7GIYS4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MVL6Q7EF3WFUL6RKIEMH7GIYS4","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":"24d2fa225377d230e7531a7581aeaf09bdeb6caf5081c62950403e11145589e3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T23:26:44Z","title_canon_sha256":"c6a1a65f7c6e795bad8b7c5d3f967df829a1ec455a7fde05655ca82ebbfc617e"},"schema_version":"1.0","source":{"id":"2412.13378","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13378","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13378v2","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13378","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"pith_short_12","alias_value":"MVL6Q7EF3WFU","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"pith_short_16","alias_value":"MVL6Q7EF3WFUL6RK","created_at":"2026-07-05T11:13:17Z"},{"alias_kind":"pith_short_8","alias_value":"MVL6Q7EF","created_at":"2026-07-05T11:13:17Z"}],"graph_snapshots":[{"event_id":"sha256:c6edc196e1a495ea566fd9d9c8405e74b2aa475d82c7e0debaac8eb6c4eec30b","target":"graph","created_at":"2026-07-05T11:13:17Z","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/2412.13378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chien-Sheng Wu, Onkar Thorat, Philippe Laban","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T23:26:44Z","title":"SummExecEdit: A Factual Consistency Benchmark in Summarization with Executable Edits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13378","kind":"arxiv","version":2},"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:e07a5d1cf7a1b4fb97f059189dc0fd247f98112228701a963417b141b0c1ae32","target":"record","created_at":"2026-07-05T11:13:17Z","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":"24d2fa225377d230e7531a7581aeaf09bdeb6caf5081c62950403e11145589e3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T23:26:44Z","title_canon_sha256":"c6a1a65f7c6e795bad8b7c5d3f967df829a1ec455a7fde05655ca82ebbfc617e"},"schema_version":"1.0","source":{"id":"2412.13378","kind":"arxiv","version":2}},"canonical_sha256":"6557e87c85dd8b45fa2a41187f9918972aed984fd618a3e7a7938922de8560a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6557e87c85dd8b45fa2a41187f9918972aed984fd618a3e7a7938922de8560a0","first_computed_at":"2026-07-05T11:13:17.220251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:17.220251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lai7V1HuOszGyajCgobV7KkyIh6lmWfge5CRVBxdgtGk1sF/uiVEMgCqAoANwsINwanrUi3WasTTemw6D0PHAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:17.220693Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13378","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e07a5d1cf7a1b4fb97f059189dc0fd247f98112228701a963417b141b0c1ae32","sha256:c6edc196e1a495ea566fd9d9c8405e74b2aa475d82c7e0debaac8eb6c4eec30b"],"state_sha256":"ec6fd92ab5974be587807360c72d4892801495c9724af74737400a84809186ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pl/KeCDzDIxSLAMuFk1TnJgCkS1kjklzJxUe5/g+3X2509JmgOb9fFKGw4jOmbEopI3y2TzLVmV0sJd1UbQ0AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T08:46:15.901398Z","bundle_sha256":"91e652e6fcd5e30ddfacbecdea9464a6ce6220e4783621c3ff1555b1b1257594"}}