{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WVLZM56UDY63UPMH6PR4CCZY4E","short_pith_number":"pith:WVLZM56U","schema_version":"1.0","canonical_sha256":"b5579677d41e3dba3d87f3e3c10b38e1186deb52801b0da401525aa26ac95200","source":{"kind":"arxiv","id":"1906.04466","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Learning for Contextualized Extractive Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hong Wang, Mo Yu, Shiyu Chang, Wenhan Xiong, William Yang Wang, Xiaoxiao Guo, Xin Wang","submitted_at":"2019-06-11T09:53:17Z","abstract_excerpt":"Existing models for extractive summarization are usually trained from scratch with a cross-entropy loss, which does not explicitly capture the global context at the document level. In this paper, we aim to improve this task by introducing three auxiliary pre-training tasks that learn to capture the document-level context in a self-supervised fashion. Experiments on the widely-used CNN/DM dataset validate the effectiveness of the proposed auxiliary tasks. Furthermore, we show that after pre-training, a clean model with simple building blocks is able to outperform previous state-of-the-art that "},"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":"1906.04466","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-11T09:53:17Z","cross_cats_sorted":[],"title_canon_sha256":"ea416e02becd9b5d391d66e057e762acec8cbbfd19510760d0faacdc4891d5e4","abstract_canon_sha256":"33bf912364f47aa638bd4c7bd0470f217b367343101c50a47d25baa40451ac05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:39.193378Z","signature_b64":"v7mhVLgScUTma3tEBHz4q3iVt5OPm5MRQnAOTQ7qFNi55Alyk2o82enQcCs8+H8ghOmKqtQUl27C1M8jWW5TCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5579677d41e3dba3d87f3e3c10b38e1186deb52801b0da401525aa26ac95200","last_reissued_at":"2026-05-17T23:43:39.192626Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:39.192626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Learning for Contextualized Extractive Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hong Wang, Mo Yu, Shiyu Chang, Wenhan Xiong, William Yang Wang, Xiaoxiao Guo, Xin Wang","submitted_at":"2019-06-11T09:53:17Z","abstract_excerpt":"Existing models for extractive summarization are usually trained from scratch with a cross-entropy loss, which does not explicitly capture the global context at the document level. In this paper, we aim to improve this task by introducing three auxiliary pre-training tasks that learn to capture the document-level context in a self-supervised fashion. Experiments on the widely-used CNN/DM dataset validate the effectiveness of the proposed auxiliary tasks. Furthermore, we show that after pre-training, a clean model with simple building blocks is able to outperform previous state-of-the-art that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04466","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":"1906.04466","created_at":"2026-05-17T23:43:39.192736+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.04466v1","created_at":"2026-05-17T23:43:39.192736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04466","created_at":"2026-05-17T23:43:39.192736+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVLZM56UDY63","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVLZM56UDY63UPMH","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVLZM56U","created_at":"2026-05-18T12:33:33.725879+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/WVLZM56UDY63UPMH6PR4CCZY4E","json":"https://pith.science/pith/WVLZM56UDY63UPMH6PR4CCZY4E.json","graph_json":"https://pith.science/api/pith-number/WVLZM56UDY63UPMH6PR4CCZY4E/graph.json","events_json":"https://pith.science/api/pith-number/WVLZM56UDY63UPMH6PR4CCZY4E/events.json","paper":"https://pith.science/paper/WVLZM56U"},"agent_actions":{"view_html":"https://pith.science/pith/WVLZM56UDY63UPMH6PR4CCZY4E","download_json":"https://pith.science/pith/WVLZM56UDY63UPMH6PR4CCZY4E.json","view_paper":"https://pith.science/paper/WVLZM56U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.04466&json=true","fetch_graph":"https://pith.science/api/pith-number/WVLZM56UDY63UPMH6PR4CCZY4E/graph.json","fetch_events":"https://pith.science/api/pith-number/WVLZM56UDY63UPMH6PR4CCZY4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVLZM56UDY63UPMH6PR4CCZY4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVLZM56UDY63UPMH6PR4CCZY4E/action/storage_attestation","attest_author":"https://pith.science/pith/WVLZM56UDY63UPMH6PR4CCZY4E/action/author_attestation","sign_citation":"https://pith.science/pith/WVLZM56UDY63UPMH6PR4CCZY4E/action/citation_signature","submit_replication":"https://pith.science/pith/WVLZM56UDY63UPMH6PR4CCZY4E/action/replication_record"}},"created_at":"2026-05-17T23:43:39.192736+00:00","updated_at":"2026-05-17T23:43:39.192736+00:00"}