{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JUGBZX3SD4WWZE34J5ESX5ICX5","short_pith_number":"pith:JUGBZX3S","schema_version":"1.0","canonical_sha256":"4d0c1cdf721f2d6c937c4f492bf502bf4d83fd9b4717480d8f67c21812d0635e","source":{"kind":"arxiv","id":"2406.06263","version":1},"attestation_state":"computed","paper":{"title":"MaskLID: Code-Switching Language Identification through Iterative Masking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir Hossein Kargaran, Fran\\c{c}ois Yvon, Hinrich Sch\\\"utze","submitted_at":"2024-06-10T13:44:29Z","abstract_excerpt":"We present MaskLID, a simple, yet effective, code-switching (CS) language identification (LID) method. MaskLID does not require any training and is designed to complement current high-performance sentence-level LIDs. Sentence-level LIDs are classifiers trained on monolingual texts to provide single labels, typically using a softmax layer to turn scores into probabilities. However, in cases where a sentence is composed in both L1 and L2 languages, the LID classifier often only returns the dominant label L1. To address this limitation, MaskLID employs a strategy to mask text features associated "},"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":"2406.06263","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T13:44:29Z","cross_cats_sorted":[],"title_canon_sha256":"234ffa2501cad51926d0141424f95b4a55a92e0edf64a6ffef38382de8980f5e","abstract_canon_sha256":"7479746f85218ab8d4ea8a37c2218c1a3e30d8f91c60f5151ca71674849b3b91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:39.931387Z","signature_b64":"ow21GjbLetg0mWvOh42BxByR7C1LdnJporOFqUwsJ8c11BjQCUYtn+7iizJ7HYPto4MvC85rCjEZPKJFZLDzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d0c1cdf721f2d6c937c4f492bf502bf4d83fd9b4717480d8f67c21812d0635e","last_reissued_at":"2026-07-05T08:29:39.930975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:39.930975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MaskLID: Code-Switching Language Identification through Iterative Masking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir Hossein Kargaran, Fran\\c{c}ois Yvon, Hinrich Sch\\\"utze","submitted_at":"2024-06-10T13:44:29Z","abstract_excerpt":"We present MaskLID, a simple, yet effective, code-switching (CS) language identification (LID) method. MaskLID does not require any training and is designed to complement current high-performance sentence-level LIDs. Sentence-level LIDs are classifiers trained on monolingual texts to provide single labels, typically using a softmax layer to turn scores into probabilities. However, in cases where a sentence is composed in both L1 and L2 languages, the LID classifier often only returns the dominant label L1. To address this limitation, MaskLID employs a strategy to mask text features associated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06263","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/2406.06263/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":"2406.06263","created_at":"2026-07-05T08:29:39.931031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06263v1","created_at":"2026-07-05T08:29:39.931031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06263","created_at":"2026-07-05T08:29:39.931031+00:00"},{"alias_kind":"pith_short_12","alias_value":"JUGBZX3SD4WW","created_at":"2026-07-05T08:29:39.931031+00:00"},{"alias_kind":"pith_short_16","alias_value":"JUGBZX3SD4WWZE34","created_at":"2026-07-05T08:29:39.931031+00:00"},{"alias_kind":"pith_short_8","alias_value":"JUGBZX3S","created_at":"2026-07-05T08:29:39.931031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.11746","citing_title":"Token Masking Improves Transformer-Based Text Classification","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JUGBZX3SD4WWZE34J5ESX5ICX5","json":"https://pith.science/pith/JUGBZX3SD4WWZE34J5ESX5ICX5.json","graph_json":"https://pith.science/api/pith-number/JUGBZX3SD4WWZE34J5ESX5ICX5/graph.json","events_json":"https://pith.science/api/pith-number/JUGBZX3SD4WWZE34J5ESX5ICX5/events.json","paper":"https://pith.science/paper/JUGBZX3S"},"agent_actions":{"view_html":"https://pith.science/pith/JUGBZX3SD4WWZE34J5ESX5ICX5","download_json":"https://pith.science/pith/JUGBZX3SD4WWZE34J5ESX5ICX5.json","view_paper":"https://pith.science/paper/JUGBZX3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06263&json=true","fetch_graph":"https://pith.science/api/pith-number/JUGBZX3SD4WWZE34J5ESX5ICX5/graph.json","fetch_events":"https://pith.science/api/pith-number/JUGBZX3SD4WWZE34J5ESX5ICX5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JUGBZX3SD4WWZE34J5ESX5ICX5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JUGBZX3SD4WWZE34J5ESX5ICX5/action/storage_attestation","attest_author":"https://pith.science/pith/JUGBZX3SD4WWZE34J5ESX5ICX5/action/author_attestation","sign_citation":"https://pith.science/pith/JUGBZX3SD4WWZE34J5ESX5ICX5/action/citation_signature","submit_replication":"https://pith.science/pith/JUGBZX3SD4WWZE34J5ESX5ICX5/action/replication_record"}},"created_at":"2026-07-05T08:29:39.931031+00:00","updated_at":"2026-07-05T08:29:39.931031+00:00"}