{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:323PFQC3PW2TKTMFNNWCRDIVQS","short_pith_number":"pith:323PFQC3","schema_version":"1.0","canonical_sha256":"deb6f2c05b7db5354d856b6c288d1584be19698c6a24cf5feb0494898cee686a","source":{"kind":"arxiv","id":"1608.03030","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Character-Word Models for Language Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaron Jaech, George Mulcaire, Mari Ostendorf, Noah A. Smith, Shobhit Hathi","submitted_at":"2016-08-10T03:05:26Z","abstract_excerpt":"Social media messages' brevity and unconventional spelling pose a challenge to language identification. We introduce a hierarchical model that learns character and contextualized word-level representations for language identification. Our method performs well against strong base- lines, and can also reveal code-switching."},"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":"1608.03030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-10T03:05:26Z","cross_cats_sorted":[],"title_canon_sha256":"eb2e1294a8695aef6923e6685ff318707451479c485f423cdd54c689c29c6a3b","abstract_canon_sha256":"67cea2fba318a21965ef9b90b62e4750b1df39bec1513db888d83526ef86e1fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:09:30.447494Z","signature_b64":"B/91q/4ahupL+IXFeTk3yq+wEOowTXerqNVtN0kzXVxr6YmeJgq6Q1YRXYGJOdDqi3S3DNrWUsIf1C2d1D6eDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"deb6f2c05b7db5354d856b6c288d1584be19698c6a24cf5feb0494898cee686a","last_reissued_at":"2026-05-18T01:09:30.447051Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:09:30.447051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Character-Word Models for Language Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaron Jaech, George Mulcaire, Mari Ostendorf, Noah A. Smith, Shobhit Hathi","submitted_at":"2016-08-10T03:05:26Z","abstract_excerpt":"Social media messages' brevity and unconventional spelling pose a challenge to language identification. We introduce a hierarchical model that learns character and contextualized word-level representations for language identification. Our method performs well against strong base- lines, and can also reveal code-switching."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.03030","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":""},"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":"1608.03030","created_at":"2026-05-18T01:09:30.447120+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.03030v1","created_at":"2026-05-18T01:09:30.447120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.03030","created_at":"2026-05-18T01:09:30.447120+00:00"},{"alias_kind":"pith_short_12","alias_value":"323PFQC3PW2T","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_16","alias_value":"323PFQC3PW2TKTMF","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_8","alias_value":"323PFQC3","created_at":"2026-05-18T12:29:55.572404+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/323PFQC3PW2TKTMFNNWCRDIVQS","json":"https://pith.science/pith/323PFQC3PW2TKTMFNNWCRDIVQS.json","graph_json":"https://pith.science/api/pith-number/323PFQC3PW2TKTMFNNWCRDIVQS/graph.json","events_json":"https://pith.science/api/pith-number/323PFQC3PW2TKTMFNNWCRDIVQS/events.json","paper":"https://pith.science/paper/323PFQC3"},"agent_actions":{"view_html":"https://pith.science/pith/323PFQC3PW2TKTMFNNWCRDIVQS","download_json":"https://pith.science/pith/323PFQC3PW2TKTMFNNWCRDIVQS.json","view_paper":"https://pith.science/paper/323PFQC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.03030&json=true","fetch_graph":"https://pith.science/api/pith-number/323PFQC3PW2TKTMFNNWCRDIVQS/graph.json","fetch_events":"https://pith.science/api/pith-number/323PFQC3PW2TKTMFNNWCRDIVQS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/323PFQC3PW2TKTMFNNWCRDIVQS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/323PFQC3PW2TKTMFNNWCRDIVQS/action/storage_attestation","attest_author":"https://pith.science/pith/323PFQC3PW2TKTMFNNWCRDIVQS/action/author_attestation","sign_citation":"https://pith.science/pith/323PFQC3PW2TKTMFNNWCRDIVQS/action/citation_signature","submit_replication":"https://pith.science/pith/323PFQC3PW2TKTMFNNWCRDIVQS/action/replication_record"}},"created_at":"2026-05-18T01:09:30.447120+00:00","updated_at":"2026-05-18T01:09:30.447120+00:00"}