{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RGE4K5AOBONUQOS2FN7QCRKFDL","short_pith_number":"pith:RGE4K5AO","schema_version":"1.0","canonical_sha256":"8989c5740e0b9b483a5a2b7f0145451af8e17151d36d18cf4fa6fd709e6de403","source":{"kind":"arxiv","id":"1810.06065","version":1},"attestation_state":"computed","paper":{"title":"Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dong Yu, Lisa Fan, Lu Wang","submitted_at":"2018-10-14T17:08:54Z","abstract_excerpt":"Sequence-to-sequence (seq2seq) neural models have been actively investigated for abstractive summarization. Nevertheless, existing neural abstractive systems frequently generate factually incorrect summaries and are vulnerable to adversarial information, suggesting a crucial lack of semantic understanding. In this paper, we propose a novel semantic-aware neural abstractive summarization model that learns to generate high quality summaries through semantic interpretation over salient content. A novel evaluation scheme with adversarial samples is introduced to measure how well a model identifies"},"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":"1810.06065","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-14T17:08:54Z","cross_cats_sorted":[],"title_canon_sha256":"1ac359ed4e5e41a5abba7e9a1bcc5e0acb83d42a3e5998debc890f5bce58dbbb","abstract_canon_sha256":"a1a9ea9ee737181ac622a1119fa852f0620303d740e7938b63d10b8d2616eee6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:21.519546Z","signature_b64":"550nAES4YmxomWmb84W28Jq7jt29IIEMDEX7HQaCelUnfEtLijcsLhOxNNqlSfQLhESL1Uh/Eaho6wui2R0oCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8989c5740e0b9b483a5a2b7f0145451af8e17151d36d18cf4fa6fd709e6de403","last_reissued_at":"2026-05-18T00:03:21.518925Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:21.518925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dong Yu, Lisa Fan, Lu Wang","submitted_at":"2018-10-14T17:08:54Z","abstract_excerpt":"Sequence-to-sequence (seq2seq) neural models have been actively investigated for abstractive summarization. Nevertheless, existing neural abstractive systems frequently generate factually incorrect summaries and are vulnerable to adversarial information, suggesting a crucial lack of semantic understanding. In this paper, we propose a novel semantic-aware neural abstractive summarization model that learns to generate high quality summaries through semantic interpretation over salient content. A novel evaluation scheme with adversarial samples is introduced to measure how well a model identifies"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06065","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1810.06065","created_at":"2026-05-18T00:03:21.519010+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.06065v1","created_at":"2026-05-18T00:03:21.519010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06065","created_at":"2026-05-18T00:03:21.519010+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGE4K5AOBONU","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGE4K5AOBONUQOS2","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGE4K5AO","created_at":"2026-05-18T12:32:50.500415+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/RGE4K5AOBONUQOS2FN7QCRKFDL","json":"https://pith.science/pith/RGE4K5AOBONUQOS2FN7QCRKFDL.json","graph_json":"https://pith.science/api/pith-number/RGE4K5AOBONUQOS2FN7QCRKFDL/graph.json","events_json":"https://pith.science/api/pith-number/RGE4K5AOBONUQOS2FN7QCRKFDL/events.json","paper":"https://pith.science/paper/RGE4K5AO"},"agent_actions":{"view_html":"https://pith.science/pith/RGE4K5AOBONUQOS2FN7QCRKFDL","download_json":"https://pith.science/pith/RGE4K5AOBONUQOS2FN7QCRKFDL.json","view_paper":"https://pith.science/paper/RGE4K5AO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.06065&json=true","fetch_graph":"https://pith.science/api/pith-number/RGE4K5AOBONUQOS2FN7QCRKFDL/graph.json","fetch_events":"https://pith.science/api/pith-number/RGE4K5AOBONUQOS2FN7QCRKFDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGE4K5AOBONUQOS2FN7QCRKFDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGE4K5AOBONUQOS2FN7QCRKFDL/action/storage_attestation","attest_author":"https://pith.science/pith/RGE4K5AOBONUQOS2FN7QCRKFDL/action/author_attestation","sign_citation":"https://pith.science/pith/RGE4K5AOBONUQOS2FN7QCRKFDL/action/citation_signature","submit_replication":"https://pith.science/pith/RGE4K5AOBONUQOS2FN7QCRKFDL/action/replication_record"}},"created_at":"2026-05-18T00:03:21.519010+00:00","updated_at":"2026-05-18T00:03:21.519010+00:00"}