{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:I3G36JMEKEZHTFZAK6RXR43CN4","short_pith_number":"pith:I3G36JME","canonical_record":{"source":{"id":"1805.04033","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-10T15:58:09Z","cross_cats_sorted":[],"title_canon_sha256":"d0d2ead8353b66a1612a2a8a241da3b10d2db20d913dcb84db13a903853495f3","abstract_canon_sha256":"ead6e99075e48bdcfdc217b010e3549f9529ac19ce228b60b5a1255797358543"},"schema_version":"1.0"},"canonical_sha256":"46cdbf2584513279972057a378f3626f2a6a7b23212e4190140ffa918ef96d16","source":{"kind":"arxiv","id":"1805.04033","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.04033","created_at":"2026-05-18T00:16:15Z"},{"alias_kind":"arxiv_version","alias_value":"1805.04033v1","created_at":"2026-05-18T00:16:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.04033","created_at":"2026-05-18T00:16:15Z"},{"alias_kind":"pith_short_12","alias_value":"I3G36JMEKEZH","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"I3G36JMEKEZHTFZA","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"I3G36JME","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:I3G36JMEKEZHTFZAK6RXR43CN4","target":"record","payload":{"canonical_record":{"source":{"id":"1805.04033","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-10T15:58:09Z","cross_cats_sorted":[],"title_canon_sha256":"d0d2ead8353b66a1612a2a8a241da3b10d2db20d913dcb84db13a903853495f3","abstract_canon_sha256":"ead6e99075e48bdcfdc217b010e3549f9529ac19ce228b60b5a1255797358543"},"schema_version":"1.0"},"canonical_sha256":"46cdbf2584513279972057a378f3626f2a6a7b23212e4190140ffa918ef96d16","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:15.200853Z","signature_b64":"9hECQv177vZHItDFo/nju5HH0Xg83NYe5MyiVxx7/DGUS15LmMIl/0gs1T5mLyxPXSqe5wcdRnmmkq9z/4VECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46cdbf2584513279972057a378f3626f2a6a7b23212e4190140ffa918ef96d16","last_reissued_at":"2026-05-18T00:16:15.200184Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:15.200184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.04033","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":"2026-05-18T00:16:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t361JobdFpxEY9V/ucdhMqdbV3qd/1CxGY/UQx5zvw6B0BWYsaGJ+5e6xV+5y0KFKwDd0yChyfYotNNfmosTBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T12:01:45.841816Z"},"content_sha256":"916cd8cfbe29f041f663948160b1a4f3d69671a23ec47a5e59c4a840abef7ce1","schema_version":"1.0","event_id":"sha256:916cd8cfbe29f041f663948160b1a4f3d69671a23ec47a5e59c4a840abef7ce1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:I3G36JMEKEZHTFZAK6RXR43CN4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regularizing Output Distribution of Abstractive Chinese Social Media Text Summarization for Improved Semantic Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingzhen Wei, Qi Su, Xiaoyan Cai, Xuancheng Ren, Xu Sun, Yi Zhang","submitted_at":"2018-05-10T15:58:09Z","abstract_excerpt":"Abstractive text summarization is a highly difficult problem, and the sequence-to-sequence model has shown success in improving the performance on the task. However, the generated summaries are often inconsistent with the source content in semantics. In such cases, when generating summaries, the model selects semantically unrelated words with respect to the source content as the most probable output. The problem can be attributed to heuristically constructed training data, where summaries can be unrelated to the source content, thus containing semantically unrelated words and spurious word cor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.04033","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":""},"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":"2026-05-18T00:16:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6lUjMUC1uwShrNwJN0qdTphBMxLT4r2Nrv8hpSX5LOTba1haC8cjhW/26utqU6x0Q+2cWrKv8r9wNfTyHxBJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T12:01:45.842290Z"},"content_sha256":"2948ccf9a5210ad64b9f5fd7888cde6d1d608410776946cce29b628574e8c5f0","schema_version":"1.0","event_id":"sha256:2948ccf9a5210ad64b9f5fd7888cde6d1d608410776946cce29b628574e8c5f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I3G36JMEKEZHTFZAK6RXR43CN4/bundle.json","state_url":"https://pith.science/pith/I3G36JMEKEZHTFZAK6RXR43CN4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I3G36JMEKEZHTFZAK6RXR43CN4/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":"2026-06-06T12:01:45Z","links":{"resolver":"https://pith.science/pith/I3G36JMEKEZHTFZAK6RXR43CN4","bundle":"https://pith.science/pith/I3G36JMEKEZHTFZAK6RXR43CN4/bundle.json","state":"https://pith.science/pith/I3G36JMEKEZHTFZAK6RXR43CN4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I3G36JMEKEZHTFZAK6RXR43CN4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:I3G36JMEKEZHTFZAK6RXR43CN4","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":"ead6e99075e48bdcfdc217b010e3549f9529ac19ce228b60b5a1255797358543","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-10T15:58:09Z","title_canon_sha256":"d0d2ead8353b66a1612a2a8a241da3b10d2db20d913dcb84db13a903853495f3"},"schema_version":"1.0","source":{"id":"1805.04033","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.04033","created_at":"2026-05-18T00:16:15Z"},{"alias_kind":"arxiv_version","alias_value":"1805.04033v1","created_at":"2026-05-18T00:16:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.04033","created_at":"2026-05-18T00:16:15Z"},{"alias_kind":"pith_short_12","alias_value":"I3G36JMEKEZH","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"I3G36JMEKEZHTFZA","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"I3G36JME","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:2948ccf9a5210ad64b9f5fd7888cde6d1d608410776946cce29b628574e8c5f0","target":"graph","created_at":"2026-05-18T00:16:15Z","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"},"paper":{"abstract_excerpt":"Abstractive text summarization is a highly difficult problem, and the sequence-to-sequence model has shown success in improving the performance on the task. However, the generated summaries are often inconsistent with the source content in semantics. In such cases, when generating summaries, the model selects semantically unrelated words with respect to the source content as the most probable output. The problem can be attributed to heuristically constructed training data, where summaries can be unrelated to the source content, thus containing semantically unrelated words and spurious word cor","authors_text":"Bingzhen Wei, Qi Su, Xiaoyan Cai, Xuancheng Ren, Xu Sun, Yi Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-10T15:58:09Z","title":"Regularizing Output Distribution of Abstractive Chinese Social Media Text Summarization for Improved Semantic Consistency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.04033","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":"sha256:916cd8cfbe29f041f663948160b1a4f3d69671a23ec47a5e59c4a840abef7ce1","target":"record","created_at":"2026-05-18T00:16:15Z","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":"ead6e99075e48bdcfdc217b010e3549f9529ac19ce228b60b5a1255797358543","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-10T15:58:09Z","title_canon_sha256":"d0d2ead8353b66a1612a2a8a241da3b10d2db20d913dcb84db13a903853495f3"},"schema_version":"1.0","source":{"id":"1805.04033","kind":"arxiv","version":1}},"canonical_sha256":"46cdbf2584513279972057a378f3626f2a6a7b23212e4190140ffa918ef96d16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46cdbf2584513279972057a378f3626f2a6a7b23212e4190140ffa918ef96d16","first_computed_at":"2026-05-18T00:16:15.200184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:15.200184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9hECQv177vZHItDFo/nju5HH0Xg83NYe5MyiVxx7/DGUS15LmMIl/0gs1T5mLyxPXSqe5wcdRnmmkq9z/4VECA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:15.200853Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.04033","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:916cd8cfbe29f041f663948160b1a4f3d69671a23ec47a5e59c4a840abef7ce1","sha256:2948ccf9a5210ad64b9f5fd7888cde6d1d608410776946cce29b628574e8c5f0"],"state_sha256":"1f26ceff0863dfe4e1620d90bb60ac742bab6562e21f3ed90ae239e8b1f5414e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w9W4eh0HGMzQeW9NlxYbWYEriFJbBN8255E1j6kRQw+kl87hY2hmPE3cyh4IDVKGA1W46VrJ4GExAEQlPzZyAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T12:01:45.845383Z","bundle_sha256":"1c8b2edd742d367f8162b85660813c2bfe20e31b4f569e621153ebd1db28834a"}}