{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FKSXEQ2O4T4RFSEO4GSJHROLUT","short_pith_number":"pith:FKSXEQ2O","schema_version":"1.0","canonical_sha256":"2aa572434ee4f912c88ee1a493c5cba4c27dd6d91b82f17a2e0abf55c02967d3","source":{"kind":"arxiv","id":"2112.03024","version":1},"attestation_state":"computed","paper":{"title":"Domain-oriented Language Pre-training with Adaptive Hybrid Masking and Optimal Transport Alignment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Denghui Zhang, Fuzhen Zhuang, Haifeng Chen, Hao Liu, Hui Xiong, Yanchi Liu, Zixuan Yuan","submitted_at":"2021-12-01T15:47:01Z","abstract_excerpt":"Motivated by the success of pre-trained language models such as BERT in a broad range of natural language processing (NLP) tasks, recent research efforts have been made for adapting these models for different application domains. Along this line, existing domain-oriented models have primarily followed the vanilla BERT architecture and have a straightforward use of the domain corpus. However, domain-oriented tasks usually require accurate understanding of domain phrases, and such fine-grained phrase-level knowledge is hard to be captured by existing pre-training scheme. Also, the word co-occurr"},"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":"2112.03024","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-01T15:47:01Z","cross_cats_sorted":[],"title_canon_sha256":"53aff352017ac940d1cab18e6fb62976f8233abe12cd33b3893b558083464f79","abstract_canon_sha256":"d1d2d6554f2cf326fd2c1b9493a07c915e8161f48da650f99b72f076e4ee641a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:00.888767Z","signature_b64":"0uhVn2OaZL6RorcfTFuEK9RkxemQY/VzLEGBIFcQtQgFH8hIh6YfibhvLS0x1B7a3bGYOn4R/mVZR6lox7wyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2aa572434ee4f912c88ee1a493c5cba4c27dd6d91b82f17a2e0abf55c02967d3","last_reissued_at":"2026-07-05T03:38:00.888358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:00.888358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain-oriented Language Pre-training with Adaptive Hybrid Masking and Optimal Transport Alignment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Denghui Zhang, Fuzhen Zhuang, Haifeng Chen, Hao Liu, Hui Xiong, Yanchi Liu, Zixuan Yuan","submitted_at":"2021-12-01T15:47:01Z","abstract_excerpt":"Motivated by the success of pre-trained language models such as BERT in a broad range of natural language processing (NLP) tasks, recent research efforts have been made for adapting these models for different application domains. Along this line, existing domain-oriented models have primarily followed the vanilla BERT architecture and have a straightforward use of the domain corpus. However, domain-oriented tasks usually require accurate understanding of domain phrases, and such fine-grained phrase-level knowledge is hard to be captured by existing pre-training scheme. Also, the word co-occurr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03024","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/2112.03024/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":"2112.03024","created_at":"2026-07-05T03:38:00.888411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.03024v1","created_at":"2026-07-05T03:38:00.888411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03024","created_at":"2026-07-05T03:38:00.888411+00:00"},{"alias_kind":"pith_short_12","alias_value":"FKSXEQ2O4T4R","created_at":"2026-07-05T03:38:00.888411+00:00"},{"alias_kind":"pith_short_16","alias_value":"FKSXEQ2O4T4RFSEO","created_at":"2026-07-05T03:38:00.888411+00:00"},{"alias_kind":"pith_short_8","alias_value":"FKSXEQ2O","created_at":"2026-07-05T03:38:00.888411+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/FKSXEQ2O4T4RFSEO4GSJHROLUT","json":"https://pith.science/pith/FKSXEQ2O4T4RFSEO4GSJHROLUT.json","graph_json":"https://pith.science/api/pith-number/FKSXEQ2O4T4RFSEO4GSJHROLUT/graph.json","events_json":"https://pith.science/api/pith-number/FKSXEQ2O4T4RFSEO4GSJHROLUT/events.json","paper":"https://pith.science/paper/FKSXEQ2O"},"agent_actions":{"view_html":"https://pith.science/pith/FKSXEQ2O4T4RFSEO4GSJHROLUT","download_json":"https://pith.science/pith/FKSXEQ2O4T4RFSEO4GSJHROLUT.json","view_paper":"https://pith.science/paper/FKSXEQ2O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.03024&json=true","fetch_graph":"https://pith.science/api/pith-number/FKSXEQ2O4T4RFSEO4GSJHROLUT/graph.json","fetch_events":"https://pith.science/api/pith-number/FKSXEQ2O4T4RFSEO4GSJHROLUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FKSXEQ2O4T4RFSEO4GSJHROLUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FKSXEQ2O4T4RFSEO4GSJHROLUT/action/storage_attestation","attest_author":"https://pith.science/pith/FKSXEQ2O4T4RFSEO4GSJHROLUT/action/author_attestation","sign_citation":"https://pith.science/pith/FKSXEQ2O4T4RFSEO4GSJHROLUT/action/citation_signature","submit_replication":"https://pith.science/pith/FKSXEQ2O4T4RFSEO4GSJHROLUT/action/replication_record"}},"created_at":"2026-07-05T03:38:00.888411+00:00","updated_at":"2026-07-05T03:38:00.888411+00:00"}