{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZJ77AZOKUGL4ZPP6BAYILARK24","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":"e8caf3ae0f0a829a89554bf2ac6c5d062543e985142ff39477d58d1f305083bf","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-03T13:08:12Z","title_canon_sha256":"b06ae974487aed8bb490d9dfa2e77bdecde1f8571687a8253978d5d04b6d50e9"},"schema_version":"1.0","source":{"id":"1904.01989","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.01989","created_at":"2026-05-17T23:49:29Z"},{"alias_kind":"arxiv_version","alias_value":"1904.01989v1","created_at":"2026-05-17T23:49:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01989","created_at":"2026-05-17T23:49:29Z"},{"alias_kind":"pith_short_12","alias_value":"ZJ77AZOKUGL4","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZJ77AZOKUGL4ZPP6","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZJ77AZOK","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:d86f7f0abf463ec99f23f9f0cd88beda85e4339de5ce05c9dbb96cce1e83ddb2","target":"graph","created_at":"2026-05-17T23:49:29Z","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"},"paper":{"abstract_excerpt":"Language identification for code-switching (CS), the phenomenon of alternating between two or more languages in conversations, has traditionally been approached under the assumption of a single language per token. However, if at least one language is morphologically rich, a large number of words can be composed of morphemes from more than one language (intra-word CS). In this paper, we extend the language identification task to the subword-level, such that it includes splitting mixed words while tagging each part with a language ID. We further propose a model for this task, which is based on a","authors_text":"Katharina Kann, Manuel Mager, \\\"Ozlem \\c{C}etino\\u{g}lu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-03T13:08:12Z","title":"Subword-Level Language Identification for Intra-Word Code-Switching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01989","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:e8b446d348728c30bf7ff6451eaf37bae96a0fe15b9aba7c25b9f9165a86bad2","target":"record","created_at":"2026-05-17T23:49:29Z","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":"e8caf3ae0f0a829a89554bf2ac6c5d062543e985142ff39477d58d1f305083bf","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-03T13:08:12Z","title_canon_sha256":"b06ae974487aed8bb490d9dfa2e77bdecde1f8571687a8253978d5d04b6d50e9"},"schema_version":"1.0","source":{"id":"1904.01989","kind":"arxiv","version":1}},"canonical_sha256":"ca7ff065caa197ccbdfe083085822ad70eae056c6e0660c50f0ab63dd95963ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca7ff065caa197ccbdfe083085822ad70eae056c6e0660c50f0ab63dd95963ff","first_computed_at":"2026-05-17T23:49:29.078229Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:29.078229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8NSAMk9TYPTwWn3hu06NZ7SLxZiW6dJzZe/MJDXc+6nAifn9Qe7jjtICfSuBRNx1/quoNF0UHwoJfYDopbULDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:29.078775Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.01989","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8b446d348728c30bf7ff6451eaf37bae96a0fe15b9aba7c25b9f9165a86bad2","sha256:d86f7f0abf463ec99f23f9f0cd88beda85e4339de5ce05c9dbb96cce1e83ddb2"],"state_sha256":"bc3f4880f1113adb092d51a888e5988d70475999a34d209b32b24651cc1d33a7"}