{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JMRCVMN5DUIBHEPMTELAD3UHBA","short_pith_number":"pith:JMRCVMN5","schema_version":"1.0","canonical_sha256":"4b222ab1bd1d101391ec991601ee87081af76f4e77510c13682da34c5027a243","source":{"kind":"arxiv","id":"1810.07156","version":2},"attestation_state":"computed","paper":{"title":"Strategies for Language Identification in Code-Mixed Low Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sankalp Sanand, Soumil Mandal","submitted_at":"2018-10-16T17:35:31Z","abstract_excerpt":"In recent years, substantial work has been done on language tagging of code-mixed data, but most of them use large amounts of data to build their models. In this article, we present three strategies to build a word level language tagger for code-mixed data using very low resources. Each of them secured an accuracy higher than our baseline model, and the best performing system got an accuracy around 91%. Combining all, the ensemble system achieved an accuracy of around 92.6%."},"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":"1810.07156","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-16T17:35:31Z","cross_cats_sorted":[],"title_canon_sha256":"8e26d742ef08236805a2d89dd52d34d10ca476a4baa876192f94a5213c936252","abstract_canon_sha256":"9477e0a1996b7415885bc2e4ca6486e7cafb76083fb0a51251b4f74fc67dbdda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:48.602266Z","signature_b64":"iZInYX0fWMK9nCQeK5BzpFDfeWBzF2Ek2cc/6Xw+YC32e6Hqmaf5tfnUvXBv3sT99kjbR+tIVF/yXS0wFRQXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b222ab1bd1d101391ec991601ee87081af76f4e77510c13682da34c5027a243","last_reissued_at":"2026-05-18T00:01:48.601703Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:48.601703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Strategies for Language Identification in Code-Mixed Low Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sankalp Sanand, Soumil Mandal","submitted_at":"2018-10-16T17:35:31Z","abstract_excerpt":"In recent years, substantial work has been done on language tagging of code-mixed data, but most of them use large amounts of data to build their models. In this article, we present three strategies to build a word level language tagger for code-mixed data using very low resources. Each of them secured an accuracy higher than our baseline model, and the best performing system got an accuracy around 91%. Combining all, the ensemble system achieved an accuracy of around 92.6%."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07156","kind":"arxiv","version":2},"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":"1810.07156","created_at":"2026-05-18T00:01:48.601767+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.07156v2","created_at":"2026-05-18T00:01:48.601767+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07156","created_at":"2026-05-18T00:01:48.601767+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMRCVMN5DUIB","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMRCVMN5DUIBHEPM","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMRCVMN5","created_at":"2026-05-18T12:32:31.084164+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/JMRCVMN5DUIBHEPMTELAD3UHBA","json":"https://pith.science/pith/JMRCVMN5DUIBHEPMTELAD3UHBA.json","graph_json":"https://pith.science/api/pith-number/JMRCVMN5DUIBHEPMTELAD3UHBA/graph.json","events_json":"https://pith.science/api/pith-number/JMRCVMN5DUIBHEPMTELAD3UHBA/events.json","paper":"https://pith.science/paper/JMRCVMN5"},"agent_actions":{"view_html":"https://pith.science/pith/JMRCVMN5DUIBHEPMTELAD3UHBA","download_json":"https://pith.science/pith/JMRCVMN5DUIBHEPMTELAD3UHBA.json","view_paper":"https://pith.science/paper/JMRCVMN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.07156&json=true","fetch_graph":"https://pith.science/api/pith-number/JMRCVMN5DUIBHEPMTELAD3UHBA/graph.json","fetch_events":"https://pith.science/api/pith-number/JMRCVMN5DUIBHEPMTELAD3UHBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMRCVMN5DUIBHEPMTELAD3UHBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMRCVMN5DUIBHEPMTELAD3UHBA/action/storage_attestation","attest_author":"https://pith.science/pith/JMRCVMN5DUIBHEPMTELAD3UHBA/action/author_attestation","sign_citation":"https://pith.science/pith/JMRCVMN5DUIBHEPMTELAD3UHBA/action/citation_signature","submit_replication":"https://pith.science/pith/JMRCVMN5DUIBHEPMTELAD3UHBA/action/replication_record"}},"created_at":"2026-05-18T00:01:48.601767+00:00","updated_at":"2026-05-18T00:01:48.601767+00:00"}