{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MMOOVAIVPI2JTBSLG6T63D4OOV","short_pith_number":"pith:MMOOVAIV","schema_version":"1.0","canonical_sha256":"631cea81157a3499864b37a7ed8f8e7576abe5bb5008dc77b80342322d66d415","source":{"kind":"arxiv","id":"2010.12148","version":2},"attestation_state":"computed","paper":{"title":"ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Dongling Xiao, HaiFeng Wang, Han Zhang, Hao Tian, Hua Wu, Yu-Kun Li, Yu Sun","submitted_at":"2020-10-23T03:42:20Z","abstract_excerpt":"Coarse-grained linguistic information, such as named entities or phrases, facilitates adequately representation learning in pre-training. Previous works mainly focus on extending the objective of BERT's Masked Language Modeling (MLM) from masking individual tokens to contiguous sequences of n tokens. We argue that such contiguously masking method neglects to model the intra-dependencies and inter-relation of coarse-grained linguistic information. As an alternative, we propose ERNIE-Gram, an explicitly n-gram masking method to enhance the integration of coarse-grained information into pre-train"},"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":"2010.12148","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T03:42:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8d3b37059380ff13c8e4c01e050620c240d59f1f569d2d9e5e6629821c8bd0b0","abstract_canon_sha256":"389edf966ef90c44723815fd5c6d9e5062194bf10457ecbf82651b5af01ca7d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:20.249372Z","signature_b64":"pPnVfZ3rQYazqw7A2m4ToqoFyEMURi7GBii+8ZFM/4WTsdY7HHvp+VadNesRubNxhYC1efmcrzYuGbmt3r0tBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"631cea81157a3499864b37a7ed8f8e7576abe5bb5008dc77b80342322d66d415","last_reissued_at":"2026-07-05T02:31:20.248854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:20.248854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Dongling Xiao, HaiFeng Wang, Han Zhang, Hao Tian, Hua Wu, Yu-Kun Li, Yu Sun","submitted_at":"2020-10-23T03:42:20Z","abstract_excerpt":"Coarse-grained linguistic information, such as named entities or phrases, facilitates adequately representation learning in pre-training. Previous works mainly focus on extending the objective of BERT's Masked Language Modeling (MLM) from masking individual tokens to contiguous sequences of n tokens. We argue that such contiguously masking method neglects to model the intra-dependencies and inter-relation of coarse-grained linguistic information. As an alternative, we propose ERNIE-Gram, an explicitly n-gram masking method to enhance the integration of coarse-grained information into pre-train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12148","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/2010.12148/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":"2010.12148","created_at":"2026-07-05T02:31:20.248920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.12148v2","created_at":"2026-07-05T02:31:20.248920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12148","created_at":"2026-07-05T02:31:20.248920+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMOOVAIVPI2J","created_at":"2026-07-05T02:31:20.248920+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMOOVAIVPI2JTBSL","created_at":"2026-07-05T02:31:20.248920+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMOOVAIV","created_at":"2026-07-05T02:31:20.248920+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/MMOOVAIVPI2JTBSLG6T63D4OOV","json":"https://pith.science/pith/MMOOVAIVPI2JTBSLG6T63D4OOV.json","graph_json":"https://pith.science/api/pith-number/MMOOVAIVPI2JTBSLG6T63D4OOV/graph.json","events_json":"https://pith.science/api/pith-number/MMOOVAIVPI2JTBSLG6T63D4OOV/events.json","paper":"https://pith.science/paper/MMOOVAIV"},"agent_actions":{"view_html":"https://pith.science/pith/MMOOVAIVPI2JTBSLG6T63D4OOV","download_json":"https://pith.science/pith/MMOOVAIVPI2JTBSLG6T63D4OOV.json","view_paper":"https://pith.science/paper/MMOOVAIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.12148&json=true","fetch_graph":"https://pith.science/api/pith-number/MMOOVAIVPI2JTBSLG6T63D4OOV/graph.json","fetch_events":"https://pith.science/api/pith-number/MMOOVAIVPI2JTBSLG6T63D4OOV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMOOVAIVPI2JTBSLG6T63D4OOV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMOOVAIVPI2JTBSLG6T63D4OOV/action/storage_attestation","attest_author":"https://pith.science/pith/MMOOVAIVPI2JTBSLG6T63D4OOV/action/author_attestation","sign_citation":"https://pith.science/pith/MMOOVAIVPI2JTBSLG6T63D4OOV/action/citation_signature","submit_replication":"https://pith.science/pith/MMOOVAIVPI2JTBSLG6T63D4OOV/action/replication_record"}},"created_at":"2026-07-05T02:31:20.248920+00:00","updated_at":"2026-07-05T02:31:20.248920+00:00"}