{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UA3TEVQK5EGGSFB2ZP3QNRGDJF","short_pith_number":"pith:UA3TEVQK","schema_version":"1.0","canonical_sha256":"a03732560ae90c69143acbf706c4c349797c1c129ed252cf2dfc35da929d6461","source":{"kind":"arxiv","id":"2206.03352","version":1},"attestation_state":"computed","paper":{"title":"Searching for Optimal Subword Tokenization in Cross-domain NER","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Di Liang, Qi Zhang, Ruotian Ma, Sirui Wang, Tao Gui, Wei Wu, Xin Zhou, Xuanting Chen, Yiding Tan","submitted_at":"2022-06-07T14:39:31Z","abstract_excerpt":"Input distribution shift is one of the vital problems in unsupervised domain adaptation (UDA). The most popular UDA approaches focus on domain-invariant representation learning, trying to align the features from different domains into similar feature distributions. However, these approaches ignore the direct alignment of input word distributions between domains, which is a vital factor in word-level classification tasks such as cross-domain NER. In this work, we shed new light on cross-domain NER by introducing a subword-level solution, X-Piece, for input word-level distribution shift in NER. "},"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":"2206.03352","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-07T14:39:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2cbc622850c431b88ccfa2fb29d2723435a548e8ec719e871ced77eb9e6ca046","abstract_canon_sha256":"e0c40c2f933d07b48d674f0301945ea2dbc2b9dfc10d9da3545d06712bcc88f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:41.707706Z","signature_b64":"JS5QJYNj/aOcCM5oEivGZYcYNK5VpHJyvkSoBVxmnlKTkAVYn3pDrZbxGs2ytSbLIrRHcnIqGSEld2UHAJy/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a03732560ae90c69143acbf706c4c349797c1c129ed252cf2dfc35da929d6461","last_reissued_at":"2026-07-05T04:29:41.707253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:41.707253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Searching for Optimal Subword Tokenization in Cross-domain NER","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Di Liang, Qi Zhang, Ruotian Ma, Sirui Wang, Tao Gui, Wei Wu, Xin Zhou, Xuanting Chen, Yiding Tan","submitted_at":"2022-06-07T14:39:31Z","abstract_excerpt":"Input distribution shift is one of the vital problems in unsupervised domain adaptation (UDA). The most popular UDA approaches focus on domain-invariant representation learning, trying to align the features from different domains into similar feature distributions. However, these approaches ignore the direct alignment of input word distributions between domains, which is a vital factor in word-level classification tasks such as cross-domain NER. In this work, we shed new light on cross-domain NER by introducing a subword-level solution, X-Piece, for input word-level distribution shift in NER. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03352","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/2206.03352/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":"2206.03352","created_at":"2026-07-05T04:29:41.707326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.03352v1","created_at":"2026-07-05T04:29:41.707326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03352","created_at":"2026-07-05T04:29:41.707326+00:00"},{"alias_kind":"pith_short_12","alias_value":"UA3TEVQK5EGG","created_at":"2026-07-05T04:29:41.707326+00:00"},{"alias_kind":"pith_short_16","alias_value":"UA3TEVQK5EGGSFB2","created_at":"2026-07-05T04:29:41.707326+00:00"},{"alias_kind":"pith_short_8","alias_value":"UA3TEVQK","created_at":"2026-07-05T04:29:41.707326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17051","citing_title":"Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UA3TEVQK5EGGSFB2ZP3QNRGDJF","json":"https://pith.science/pith/UA3TEVQK5EGGSFB2ZP3QNRGDJF.json","graph_json":"https://pith.science/api/pith-number/UA3TEVQK5EGGSFB2ZP3QNRGDJF/graph.json","events_json":"https://pith.science/api/pith-number/UA3TEVQK5EGGSFB2ZP3QNRGDJF/events.json","paper":"https://pith.science/paper/UA3TEVQK"},"agent_actions":{"view_html":"https://pith.science/pith/UA3TEVQK5EGGSFB2ZP3QNRGDJF","download_json":"https://pith.science/pith/UA3TEVQK5EGGSFB2ZP3QNRGDJF.json","view_paper":"https://pith.science/paper/UA3TEVQK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.03352&json=true","fetch_graph":"https://pith.science/api/pith-number/UA3TEVQK5EGGSFB2ZP3QNRGDJF/graph.json","fetch_events":"https://pith.science/api/pith-number/UA3TEVQK5EGGSFB2ZP3QNRGDJF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UA3TEVQK5EGGSFB2ZP3QNRGDJF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UA3TEVQK5EGGSFB2ZP3QNRGDJF/action/storage_attestation","attest_author":"https://pith.science/pith/UA3TEVQK5EGGSFB2ZP3QNRGDJF/action/author_attestation","sign_citation":"https://pith.science/pith/UA3TEVQK5EGGSFB2ZP3QNRGDJF/action/citation_signature","submit_replication":"https://pith.science/pith/UA3TEVQK5EGGSFB2ZP3QNRGDJF/action/replication_record"}},"created_at":"2026-07-05T04:29:41.707326+00:00","updated_at":"2026-07-05T04:29:41.707326+00:00"}