{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JSAT4EEQIL6RHQ775CIT3R4QDX","short_pith_number":"pith:JSAT4EEQ","schema_version":"1.0","canonical_sha256":"4c813e109042fd13c3ffe8913dc7901dc1c966f2ab27cfabc4329492b8ae36d6","source":{"kind":"arxiv","id":"2111.01231","version":1},"attestation_state":"computed","paper":{"title":"Switch Point biased Self-Training: Re-purposing Pretrained Models for Code-Switching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan W Black, Khyathi Raghavi Chandu, Parul Chopra, Sai Krishna Rallabandi","submitted_at":"2021-11-01T19:42:08Z","abstract_excerpt":"Code-switching (CS), a ubiquitous phenomenon due to the ease of communication it offers in multilingual communities still remains an understudied problem in language processing. The primary reasons behind this are: (1) minimal efforts in leveraging large pretrained multilingual models, and (2) the lack of annotated data. The distinguishing case of low performance of multilingual models in CS is the intra-sentence mixing of languages leading to switch points. We first benchmark two sequence labeling tasks -- POS and NER on 4 different language pairs with a suite of pretrained models to identify"},"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":"2111.01231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-01T19:42:08Z","cross_cats_sorted":[],"title_canon_sha256":"a710d9351567b76bc2c1dba34b1e8af453761ba5cb0f4327a92ec7cb76dd63ff","abstract_canon_sha256":"8cbce399fcd2f931b6227b4b10b7cad405e4530368321238fc55aacbc5eadd04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:28:00.444750Z","signature_b64":"n1Uwp5u5cW1huGknnGOPIeQa3dV+pBA8XGUmbYn/9/wMKluZPLencaLGnSUzdvjASDqQjIe3bJSFeJ3IHsK5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c813e109042fd13c3ffe8913dc7901dc1c966f2ab27cfabc4329492b8ae36d6","last_reissued_at":"2026-07-05T03:28:00.444290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:28:00.444290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Switch Point biased Self-Training: Re-purposing Pretrained Models for Code-Switching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan W Black, Khyathi Raghavi Chandu, Parul Chopra, Sai Krishna Rallabandi","submitted_at":"2021-11-01T19:42:08Z","abstract_excerpt":"Code-switching (CS), a ubiquitous phenomenon due to the ease of communication it offers in multilingual communities still remains an understudied problem in language processing. The primary reasons behind this are: (1) minimal efforts in leveraging large pretrained multilingual models, and (2) the lack of annotated data. The distinguishing case of low performance of multilingual models in CS is the intra-sentence mixing of languages leading to switch points. We first benchmark two sequence labeling tasks -- POS and NER on 4 different language pairs with a suite of pretrained models to identify"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.01231","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/2111.01231/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":"2111.01231","created_at":"2026-07-05T03:28:00.444364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.01231v1","created_at":"2026-07-05T03:28:00.444364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.01231","created_at":"2026-07-05T03:28:00.444364+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSAT4EEQIL6R","created_at":"2026-07-05T03:28:00.444364+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSAT4EEQIL6RHQ77","created_at":"2026-07-05T03:28:00.444364+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSAT4EEQ","created_at":"2026-07-05T03:28:00.444364+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/JSAT4EEQIL6RHQ775CIT3R4QDX","json":"https://pith.science/pith/JSAT4EEQIL6RHQ775CIT3R4QDX.json","graph_json":"https://pith.science/api/pith-number/JSAT4EEQIL6RHQ775CIT3R4QDX/graph.json","events_json":"https://pith.science/api/pith-number/JSAT4EEQIL6RHQ775CIT3R4QDX/events.json","paper":"https://pith.science/paper/JSAT4EEQ"},"agent_actions":{"view_html":"https://pith.science/pith/JSAT4EEQIL6RHQ775CIT3R4QDX","download_json":"https://pith.science/pith/JSAT4EEQIL6RHQ775CIT3R4QDX.json","view_paper":"https://pith.science/paper/JSAT4EEQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.01231&json=true","fetch_graph":"https://pith.science/api/pith-number/JSAT4EEQIL6RHQ775CIT3R4QDX/graph.json","fetch_events":"https://pith.science/api/pith-number/JSAT4EEQIL6RHQ775CIT3R4QDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSAT4EEQIL6RHQ775CIT3R4QDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSAT4EEQIL6RHQ775CIT3R4QDX/action/storage_attestation","attest_author":"https://pith.science/pith/JSAT4EEQIL6RHQ775CIT3R4QDX/action/author_attestation","sign_citation":"https://pith.science/pith/JSAT4EEQIL6RHQ775CIT3R4QDX/action/citation_signature","submit_replication":"https://pith.science/pith/JSAT4EEQIL6RHQ775CIT3R4QDX/action/replication_record"}},"created_at":"2026-07-05T03:28:00.444364+00:00","updated_at":"2026-07-05T03:28:00.444364+00:00"}