{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:L5BZ62R6LT6HHNAT3ESSRDD3UC","short_pith_number":"pith:L5BZ62R6","schema_version":"1.0","canonical_sha256":"5f439f6a3e5cfc73b413d925288c7ba0abce1b94c0194024aa0f1b64d68ecae8","source":{"kind":"arxiv","id":"1905.06566","version":1},"attestation_state":"computed","paper":{"title":"HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Furu Wei, Ming Zhou, Xingxing Zhang","submitted_at":"2019-05-16T07:20:21Z","abstract_excerpt":"Neural extractive summarization models usually employ a hierarchical encoder for document encoding and they are trained using sentence-level labels, which are created heuristically using rule-based methods. Training the hierarchical encoder with these \\emph{inaccurate} labels is challenging. Inspired by the recent work on pre-training transformer sentence encoders \\cite{devlin:2018:arxiv}, we propose {\\sc Hibert} (as shorthand for {\\bf HI}erachical {\\bf B}idirectional {\\bf E}ncoder {\\bf R}epresentations from {\\bf T}ransformers) for document encoding and a method to pre-train it using unlabeled"},"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":"1905.06566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-16T07:20:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1057a236a347f8d5eac77c52c76a3d9786e864e529a46bee9803ea68ea32c1dd","abstract_canon_sha256":"b2517ba1e0cfddc0bd459cfdb314ac6fa237fb6688258439ebac8a9673f8fa44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:01.858884Z","signature_b64":"SAy9AbWK/PJqXRc4+ZyxO+AehJFr0d44h1l6/oo9CNCRvVby5h/ZPLwiB9CkYYcjcuDxuQjZtAy9V5AUitSsDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f439f6a3e5cfc73b413d925288c7ba0abce1b94c0194024aa0f1b64d68ecae8","last_reissued_at":"2026-05-17T23:46:01.858140Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:01.858140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Furu Wei, Ming Zhou, Xingxing Zhang","submitted_at":"2019-05-16T07:20:21Z","abstract_excerpt":"Neural extractive summarization models usually employ a hierarchical encoder for document encoding and they are trained using sentence-level labels, which are created heuristically using rule-based methods. Training the hierarchical encoder with these \\emph{inaccurate} labels is challenging. Inspired by the recent work on pre-training transformer sentence encoders \\cite{devlin:2018:arxiv}, we propose {\\sc Hibert} (as shorthand for {\\bf HI}erachical {\\bf B}idirectional {\\bf E}ncoder {\\bf R}epresentations from {\\bf T}ransformers) for document encoding and a method to pre-train it using unlabeled"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06566","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":"1905.06566","created_at":"2026-05-17T23:46:01.858270+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.06566v1","created_at":"2026-05-17T23:46:01.858270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06566","created_at":"2026-05-17T23:46:01.858270+00:00"},{"alias_kind":"pith_short_12","alias_value":"L5BZ62R6LT6H","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"L5BZ62R6LT6HHNAT","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"L5BZ62R6","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2109.10616","citing_title":"Enriching and Controlling Global Semantics for Text Summarization","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L5BZ62R6LT6HHNAT3ESSRDD3UC","json":"https://pith.science/pith/L5BZ62R6LT6HHNAT3ESSRDD3UC.json","graph_json":"https://pith.science/api/pith-number/L5BZ62R6LT6HHNAT3ESSRDD3UC/graph.json","events_json":"https://pith.science/api/pith-number/L5BZ62R6LT6HHNAT3ESSRDD3UC/events.json","paper":"https://pith.science/paper/L5BZ62R6"},"agent_actions":{"view_html":"https://pith.science/pith/L5BZ62R6LT6HHNAT3ESSRDD3UC","download_json":"https://pith.science/pith/L5BZ62R6LT6HHNAT3ESSRDD3UC.json","view_paper":"https://pith.science/paper/L5BZ62R6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.06566&json=true","fetch_graph":"https://pith.science/api/pith-number/L5BZ62R6LT6HHNAT3ESSRDD3UC/graph.json","fetch_events":"https://pith.science/api/pith-number/L5BZ62R6LT6HHNAT3ESSRDD3UC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L5BZ62R6LT6HHNAT3ESSRDD3UC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L5BZ62R6LT6HHNAT3ESSRDD3UC/action/storage_attestation","attest_author":"https://pith.science/pith/L5BZ62R6LT6HHNAT3ESSRDD3UC/action/author_attestation","sign_citation":"https://pith.science/pith/L5BZ62R6LT6HHNAT3ESSRDD3UC/action/citation_signature","submit_replication":"https://pith.science/pith/L5BZ62R6LT6HHNAT3ESSRDD3UC/action/replication_record"}},"created_at":"2026-05-17T23:46:01.858270+00:00","updated_at":"2026-05-17T23:46:01.858270+00:00"}