{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FCIJQ3VAECZHGEMHZFA2ZR2OD3","short_pith_number":"pith:FCIJQ3VA","schema_version":"1.0","canonical_sha256":"2890986ea020b2731187c941acc74e1ec4d5612cc481b921faeb54c9a241f3df","source":{"kind":"arxiv","id":"2102.04887","version":2},"attestation_state":"computed","paper":{"title":"NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chuhan Wu, Fangzhao Wu, Qi Liu, Tao Qi, Yang Yu, Yongfeng Huang","submitted_at":"2021-02-09T15:41:12Z","abstract_excerpt":"Pre-trained language models (PLMs) like BERT have made great progress in NLP. News articles usually contain rich textual information, and PLMs have the potentials to enhance news text modeling for various intelligent news applications like news recommendation and retrieval. However, most existing PLMs are in huge size with hundreds of millions of parameters. Many online news applications need to serve millions of users with low latency tolerance, which poses huge challenges to incorporating PLMs in these scenarios. Knowledge distillation techniques can compress a large PLM into a much smaller "},"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":"2102.04887","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-09T15:41:12Z","cross_cats_sorted":[],"title_canon_sha256":"0e26480f04c5dba1ee993a95d6b53ffa77617623bd73c43e60afa1e5030e5ad3","abstract_canon_sha256":"4be6a28e5ea9b2779c2fcac2b06a391d16cf7ad18aeaae0fc0dbf862f02bc827"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:10:52.009779Z","signature_b64":"IJatZiDhntu8D26Cr4/c+7WR6xstq58ZPkgiYuEURIbr3yaoWdtepOZRgloI7ZCe51bIoL0JaO6lQQChkzXeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2890986ea020b2731187c941acc74e1ec4d5612cc481b921faeb54c9a241f3df","last_reissued_at":"2026-07-05T03:10:52.009382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:10:52.009382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chuhan Wu, Fangzhao Wu, Qi Liu, Tao Qi, Yang Yu, Yongfeng Huang","submitted_at":"2021-02-09T15:41:12Z","abstract_excerpt":"Pre-trained language models (PLMs) like BERT have made great progress in NLP. News articles usually contain rich textual information, and PLMs have the potentials to enhance news text modeling for various intelligent news applications like news recommendation and retrieval. However, most existing PLMs are in huge size with hundreds of millions of parameters. Many online news applications need to serve millions of users with low latency tolerance, which poses huge challenges to incorporating PLMs in these scenarios. Knowledge distillation techniques can compress a large PLM into a much smaller "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04887","kind":"arxiv","version":2},"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/2102.04887/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2102.04887","created_at":"2026-07-05T03:10:52.009444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.04887v2","created_at":"2026-07-05T03:10:52.009444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04887","created_at":"2026-07-05T03:10:52.009444+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCIJQ3VAECZH","created_at":"2026-07-05T03:10:52.009444+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCIJQ3VAECZHGEMH","created_at":"2026-07-05T03:10:52.009444+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCIJQ3VA","created_at":"2026-07-05T03:10:52.009444+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09797","citing_title":"A Survey on LLM-based News Recommender Systems","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FCIJQ3VAECZHGEMHZFA2ZR2OD3","json":"https://pith.science/pith/FCIJQ3VAECZHGEMHZFA2ZR2OD3.json","graph_json":"https://pith.science/api/pith-number/FCIJQ3VAECZHGEMHZFA2ZR2OD3/graph.json","events_json":"https://pith.science/api/pith-number/FCIJQ3VAECZHGEMHZFA2ZR2OD3/events.json","paper":"https://pith.science/paper/FCIJQ3VA"},"agent_actions":{"view_html":"https://pith.science/pith/FCIJQ3VAECZHGEMHZFA2ZR2OD3","download_json":"https://pith.science/pith/FCIJQ3VAECZHGEMHZFA2ZR2OD3.json","view_paper":"https://pith.science/paper/FCIJQ3VA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.04887&json=true","fetch_graph":"https://pith.science/api/pith-number/FCIJQ3VAECZHGEMHZFA2ZR2OD3/graph.json","fetch_events":"https://pith.science/api/pith-number/FCIJQ3VAECZHGEMHZFA2ZR2OD3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCIJQ3VAECZHGEMHZFA2ZR2OD3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCIJQ3VAECZHGEMHZFA2ZR2OD3/action/storage_attestation","attest_author":"https://pith.science/pith/FCIJQ3VAECZHGEMHZFA2ZR2OD3/action/author_attestation","sign_citation":"https://pith.science/pith/FCIJQ3VAECZHGEMHZFA2ZR2OD3/action/citation_signature","submit_replication":"https://pith.science/pith/FCIJQ3VAECZHGEMHZFA2ZR2OD3/action/replication_record"}},"created_at":"2026-07-05T03:10:52.009444+00:00","updated_at":"2026-07-05T03:10:52.009444+00:00"}