{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Y7PVJMZL7A6B5RMOWPMKII4TZX","short_pith_number":"pith:Y7PVJMZL","schema_version":"1.0","canonical_sha256":"c7df54b32bf83c1ec58eb3d8a42393cdd06157d8b414d9b0e657ac27ff0335f0","source":{"kind":"arxiv","id":"2211.00430","version":1},"attestation_state":"computed","paper":{"title":"VarMAE: Pre-training of Variational Masked Autoencoder for Domain-adaptive Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dou Hu, Lianxin Jiang, Mengyuan Zhou, Xiaofeng Shi, Xiaolong Hou, Xiyang Du, Yang Mo","submitted_at":"2022-11-01T12:51:51Z","abstract_excerpt":"Pre-trained language models have achieved promising performance on general benchmarks, but underperform when migrated to a specific domain. Recent works perform pre-training from scratch or continual pre-training on domain corpora. However, in many specific domains, the limited corpus can hardly support obtaining precise representations. To address this issue, we propose a novel Transformer-based language model named VarMAE for domain-adaptive language understanding. Under the masked autoencoding objective, we design a context uncertainty learning module to encode the token's context into a sm"},"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":"2211.00430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-01T12:51:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2bb12dff09e78c9c002dfdcca3bcd42386075dafe3942ff1e2e09bfbdbb41d3b","abstract_canon_sha256":"b8ff07f4ec774ceffaca932bd22802511492ca127df1eb62003cf4f867bef1de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:22.506364Z","signature_b64":"jYJSZ6O04eAVqSa0KlGD2tiTPzvxUFotxo9AK0dMHb2yXO1YRCQZclPer3KQkw77r0U2CExgVO7xdKcxgBmpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7df54b32bf83c1ec58eb3d8a42393cdd06157d8b414d9b0e657ac27ff0335f0","last_reissued_at":"2026-07-05T05:12:22.505909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:22.505909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VarMAE: Pre-training of Variational Masked Autoencoder for Domain-adaptive Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dou Hu, Lianxin Jiang, Mengyuan Zhou, Xiaofeng Shi, Xiaolong Hou, Xiyang Du, Yang Mo","submitted_at":"2022-11-01T12:51:51Z","abstract_excerpt":"Pre-trained language models have achieved promising performance on general benchmarks, but underperform when migrated to a specific domain. Recent works perform pre-training from scratch or continual pre-training on domain corpora. However, in many specific domains, the limited corpus can hardly support obtaining precise representations. To address this issue, we propose a novel Transformer-based language model named VarMAE for domain-adaptive language understanding. Under the masked autoencoding objective, we design a context uncertainty learning module to encode the token's context into a sm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00430","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.00430/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":"2211.00430","created_at":"2026-07-05T05:12:22.505968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.00430v1","created_at":"2026-07-05T05:12:22.505968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00430","created_at":"2026-07-05T05:12:22.505968+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7PVJMZL7A6B","created_at":"2026-07-05T05:12:22.505968+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7PVJMZL7A6B5RMO","created_at":"2026-07-05T05:12:22.505968+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7PVJMZL","created_at":"2026-07-05T05:12:22.505968+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/Y7PVJMZL7A6B5RMOWPMKII4TZX","json":"https://pith.science/pith/Y7PVJMZL7A6B5RMOWPMKII4TZX.json","graph_json":"https://pith.science/api/pith-number/Y7PVJMZL7A6B5RMOWPMKII4TZX/graph.json","events_json":"https://pith.science/api/pith-number/Y7PVJMZL7A6B5RMOWPMKII4TZX/events.json","paper":"https://pith.science/paper/Y7PVJMZL"},"agent_actions":{"view_html":"https://pith.science/pith/Y7PVJMZL7A6B5RMOWPMKII4TZX","download_json":"https://pith.science/pith/Y7PVJMZL7A6B5RMOWPMKII4TZX.json","view_paper":"https://pith.science/paper/Y7PVJMZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.00430&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7PVJMZL7A6B5RMOWPMKII4TZX/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7PVJMZL7A6B5RMOWPMKII4TZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7PVJMZL7A6B5RMOWPMKII4TZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7PVJMZL7A6B5RMOWPMKII4TZX/action/storage_attestation","attest_author":"https://pith.science/pith/Y7PVJMZL7A6B5RMOWPMKII4TZX/action/author_attestation","sign_citation":"https://pith.science/pith/Y7PVJMZL7A6B5RMOWPMKII4TZX/action/citation_signature","submit_replication":"https://pith.science/pith/Y7PVJMZL7A6B5RMOWPMKII4TZX/action/replication_record"}},"created_at":"2026-07-05T05:12:22.505968+00:00","updated_at":"2026-07-05T05:12:22.505968+00:00"}