{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UA3TEVQK5EGGSFB2ZP3QNRGDJF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e0c40c2f933d07b48d674f0301945ea2dbc2b9dfc10d9da3545d06712bcc88f0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-07T14:39:31Z","title_canon_sha256":"2cbc622850c431b88ccfa2fb29d2723435a548e8ec719e871ced77eb9e6ca046"},"schema_version":"1.0","source":{"id":"2206.03352","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.03352","created_at":"2026-07-05T04:29:41Z"},{"alias_kind":"arxiv_version","alias_value":"2206.03352v1","created_at":"2026-07-05T04:29:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03352","created_at":"2026-07-05T04:29:41Z"},{"alias_kind":"pith_short_12","alias_value":"UA3TEVQK5EGG","created_at":"2026-07-05T04:29:41Z"},{"alias_kind":"pith_short_16","alias_value":"UA3TEVQK5EGGSFB2","created_at":"2026-07-05T04:29:41Z"},{"alias_kind":"pith_short_8","alias_value":"UA3TEVQK","created_at":"2026-07-05T04:29:41Z"}],"graph_snapshots":[{"event_id":"sha256:5b2f51866bfcc402b9f64d613b8a45c89159fbcff99b5dc866cba347dba1ba4a","target":"graph","created_at":"2026-07-05T04:29:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2206.03352/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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. ","authors_text":"Di Liang, Qi Zhang, Ruotian Ma, Sirui Wang, Tao Gui, Wei Wu, Xin Zhou, Xuanting Chen, Yiding Tan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-07T14:39:31Z","title":"Searching for Optimal Subword Tokenization in Cross-domain NER"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03352","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4da4e798544e05de0703a9d86a48602cf955605486c8f84a2722f5ee5d407f01","target":"record","created_at":"2026-07-05T04:29:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e0c40c2f933d07b48d674f0301945ea2dbc2b9dfc10d9da3545d06712bcc88f0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-07T14:39:31Z","title_canon_sha256":"2cbc622850c431b88ccfa2fb29d2723435a548e8ec719e871ced77eb9e6ca046"},"schema_version":"1.0","source":{"id":"2206.03352","kind":"arxiv","version":1}},"canonical_sha256":"a03732560ae90c69143acbf706c4c349797c1c129ed252cf2dfc35da929d6461","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a03732560ae90c69143acbf706c4c349797c1c129ed252cf2dfc35da929d6461","first_computed_at":"2026-07-05T04:29:41.707253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:29:41.707253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JS5QJYNj/aOcCM5oEivGZYcYNK5VpHJyvkSoBVxmnlKTkAVYn3pDrZbxGs2ytSbLIrRHcnIqGSEld2UHAJy/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:29:41.707706Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.03352","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4da4e798544e05de0703a9d86a48602cf955605486c8f84a2722f5ee5d407f01","sha256:5b2f51866bfcc402b9f64d613b8a45c89159fbcff99b5dc866cba347dba1ba4a"],"state_sha256":"4fd8fb84bbc6c1591944d9937cbb73a533cc1fc497802b54bae36d2011beacc3"}