{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:G7HHZDD3IBYFLOJOUPO3VNVSGZ","short_pith_number":"pith:G7HHZDD3","canonical_record":{"source":{"id":"2105.04623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-10T19:07:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"768bb445a074e6b3887aa75d224f42ab28970da68b35e65a04529874dba890d5","abstract_canon_sha256":"97f84d8a4ba33eedad5725f8b56f5286b15fd44852b7089440e2faf578626beb"},"schema_version":"1.0"},"canonical_sha256":"37ce7c8c7b407055b92ea3ddbab6b236468a3cde04f6a28bc5ff66971266cc05","source":{"kind":"arxiv","id":"2105.04623","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.04623","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"arxiv_version","alias_value":"2105.04623v1","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04623","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"pith_short_12","alias_value":"G7HHZDD3IBYF","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"pith_short_16","alias_value":"G7HHZDD3IBYFLOJO","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"pith_short_8","alias_value":"G7HHZDD3","created_at":"2026-07-05T02:39:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:G7HHZDD3IBYFLOJOUPO3VNVSGZ","target":"record","payload":{"canonical_record":{"source":{"id":"2105.04623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-10T19:07:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"768bb445a074e6b3887aa75d224f42ab28970da68b35e65a04529874dba890d5","abstract_canon_sha256":"97f84d8a4ba33eedad5725f8b56f5286b15fd44852b7089440e2faf578626beb"},"schema_version":"1.0"},"canonical_sha256":"37ce7c8c7b407055b92ea3ddbab6b236468a3cde04f6a28bc5ff66971266cc05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:22.478485Z","signature_b64":"b2FC07yPZ6qHOvyt/Pse5CYQDHHYPl0VfuFTeS++rSA25IVeGkPWn6CWjxuxJ3SDGxZZemW6ccGDXuc8M/pBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37ce7c8c7b407055b92ea3ddbab6b236468a3cde04f6a28bc5ff66971266cc05","last_reissued_at":"2026-07-05T02:39:22.477919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:22.477919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.04623","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":"2026-07-05T02:39:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"thKyA0juC7BRRdvXFxgJwW/qIX6hQUiyevq95cvkNceIhEwkfMF1m3RHURl1F2RG5qMoRDhUK6tAZ2BhLT5oCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:36:25.584747Z"},"content_sha256":"6fccb6a718479036b36ccd417f8382d8a34edcfdce8cf6becb4b1c036afb25e1","schema_version":"1.0","event_id":"sha256:6fccb6a718479036b36ccd417f8382d8a34edcfdce8cf6becb4b1c036afb25e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:G7HHZDD3IBYFLOJOUPO3VNVSGZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Factual Consistency of Abstractive Summarization via Question Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrew O. Arnold, Bing Xiang, Cicero Nogueira dos Santos, Dejiao Zhang, Feng Nan, Henghui Zhu, Kathleen McKeown, Patrick Ng, Ramesh Nallapati, Zhiguo Wang","submitted_at":"2021-05-10T19:07:21Z","abstract_excerpt":"A commonly observed problem with the state-of-the art abstractive summarization models is that the generated summaries can be factually inconsistent with the input documents. The fact that automatic summarization may produce plausible-sounding yet inaccurate summaries is a major concern that limits its wide application. In this paper we present an approach to address factual consistency in summarization. We first propose an efficient automatic evaluation metric to measure factual consistency; next, we propose a novel learning algorithm that maximizes the proposed metric during model training. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04623","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/2105.04623/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":"2026-07-05T02:39:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UdfZdGwKrLo1pprSeIAOGXUc9spUKy8aMypXu6WdCDX4ySwYgPL22TGOwzxadLmaKWa8sGNzG7Ehrd0fJ185DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:36:25.585637Z"},"content_sha256":"f63bbdea7ae75cf4aad76b0a2a85a907e7cd9f31ea86c5ab16276c2dcb38449e","schema_version":"1.0","event_id":"sha256:f63bbdea7ae75cf4aad76b0a2a85a907e7cd9f31ea86c5ab16276c2dcb38449e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G7HHZDD3IBYFLOJOUPO3VNVSGZ/bundle.json","state_url":"https://pith.science/pith/G7HHZDD3IBYFLOJOUPO3VNVSGZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G7HHZDD3IBYFLOJOUPO3VNVSGZ/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":"2026-07-07T04:36:25Z","links":{"resolver":"https://pith.science/pith/G7HHZDD3IBYFLOJOUPO3VNVSGZ","bundle":"https://pith.science/pith/G7HHZDD3IBYFLOJOUPO3VNVSGZ/bundle.json","state":"https://pith.science/pith/G7HHZDD3IBYFLOJOUPO3VNVSGZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G7HHZDD3IBYFLOJOUPO3VNVSGZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:G7HHZDD3IBYFLOJOUPO3VNVSGZ","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":"97f84d8a4ba33eedad5725f8b56f5286b15fd44852b7089440e2faf578626beb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-10T19:07:21Z","title_canon_sha256":"768bb445a074e6b3887aa75d224f42ab28970da68b35e65a04529874dba890d5"},"schema_version":"1.0","source":{"id":"2105.04623","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.04623","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"arxiv_version","alias_value":"2105.04623v1","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04623","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"pith_short_12","alias_value":"G7HHZDD3IBYF","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"pith_short_16","alias_value":"G7HHZDD3IBYFLOJO","created_at":"2026-07-05T02:39:22Z"},{"alias_kind":"pith_short_8","alias_value":"G7HHZDD3","created_at":"2026-07-05T02:39:22Z"}],"graph_snapshots":[{"event_id":"sha256:f63bbdea7ae75cf4aad76b0a2a85a907e7cd9f31ea86c5ab16276c2dcb38449e","target":"graph","created_at":"2026-07-05T02:39:22Z","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/2105.04623/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A commonly observed problem with the state-of-the art abstractive summarization models is that the generated summaries can be factually inconsistent with the input documents. The fact that automatic summarization may produce plausible-sounding yet inaccurate summaries is a major concern that limits its wide application. In this paper we present an approach to address factual consistency in summarization. We first propose an efficient automatic evaluation metric to measure factual consistency; next, we propose a novel learning algorithm that maximizes the proposed metric during model training. ","authors_text":"Andrew O. Arnold, Bing Xiang, Cicero Nogueira dos Santos, Dejiao Zhang, Feng Nan, Henghui Zhu, Kathleen McKeown, Patrick Ng, Ramesh Nallapati, Zhiguo Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-10T19:07:21Z","title":"Improving Factual Consistency of Abstractive Summarization via Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04623","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":"sha256:6fccb6a718479036b36ccd417f8382d8a34edcfdce8cf6becb4b1c036afb25e1","target":"record","created_at":"2026-07-05T02:39:22Z","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":"97f84d8a4ba33eedad5725f8b56f5286b15fd44852b7089440e2faf578626beb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-10T19:07:21Z","title_canon_sha256":"768bb445a074e6b3887aa75d224f42ab28970da68b35e65a04529874dba890d5"},"schema_version":"1.0","source":{"id":"2105.04623","kind":"arxiv","version":1}},"canonical_sha256":"37ce7c8c7b407055b92ea3ddbab6b236468a3cde04f6a28bc5ff66971266cc05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37ce7c8c7b407055b92ea3ddbab6b236468a3cde04f6a28bc5ff66971266cc05","first_computed_at":"2026-07-05T02:39:22.477919Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:39:22.477919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b2FC07yPZ6qHOvyt/Pse5CYQDHHYPl0VfuFTeS++rSA25IVeGkPWn6CWjxuxJ3SDGxZZemW6ccGDXuc8M/pBCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:39:22.478485Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.04623","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fccb6a718479036b36ccd417f8382d8a34edcfdce8cf6becb4b1c036afb25e1","sha256:f63bbdea7ae75cf4aad76b0a2a85a907e7cd9f31ea86c5ab16276c2dcb38449e"],"state_sha256":"920ac8749a8bc8d65847dbdd84ebd7212ad6926571888aa0a79c6f5c6f45beef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BEfTpXXq0GEBVYkc2kR5xZM6Z/sVSGFf3GvM9/gtXB3qkhbTyC+hheyl1o7Y/SlfK/afmoq3MOUm56O3oV3eBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:36:25.589029Z","bundle_sha256":"8a7c59718e93d54626480b8dce05104b14b2db5151776271d9f3a9a113c1176a"}}