{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6JWMVFESRUWD2ST6IQXATRI22I","short_pith_number":"pith:6JWMVFES","schema_version":"1.0","canonical_sha256":"f26cca94928d2c3d4a7e442e09c51ad220f8b901cae095ef3d222d76bf884238","source":{"kind":"arxiv","id":"1805.08701","version":1},"attestation_state":"computed","paper":{"title":"Normalization of Transliterated Words in Code-Mixed Data Using Seq2Seq Model & Levenshtein Distance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Karthick Nanmaran, Soumil Mandal","submitted_at":"2018-05-22T16:11:12Z","abstract_excerpt":"Building tools for code-mixed data is rapidly gaining popularity in the NLP research community as such data is exponentially rising on social media. Working with code-mixed data contains several challenges, especially due to grammatical inconsistencies and spelling variations in addition to all the previous known challenges for social media scenarios. In this article, we present a novel architecture focusing on normalizing phonetic typing variations, which is commonly seen in code-mixed data. One of the main features of our architecture is that in addition to normalizing, it can also be utiliz"},"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":"1805.08701","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-22T16:11:12Z","cross_cats_sorted":[],"title_canon_sha256":"4e07a80cefb7571cf25f16d0e5cf84a7a61e0e3899b09401fb2c63c379c7b2d6","abstract_canon_sha256":"4944e3197169ba61bf21f81def54eab84760c7af362252d1de49ca1cecad1f41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:25.317995Z","signature_b64":"mEPICSM4flrF+CYIu2fLOZojptXnDg+RoilIXkTgOH4wwGSA8QYT2vF668P6PyxP4IHasfMJMChdTtpQb8LzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f26cca94928d2c3d4a7e442e09c51ad220f8b901cae095ef3d222d76bf884238","last_reissued_at":"2026-05-18T00:15:25.317348Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:25.317348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Normalization of Transliterated Words in Code-Mixed Data Using Seq2Seq Model & Levenshtein Distance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Karthick Nanmaran, Soumil Mandal","submitted_at":"2018-05-22T16:11:12Z","abstract_excerpt":"Building tools for code-mixed data is rapidly gaining popularity in the NLP research community as such data is exponentially rising on social media. Working with code-mixed data contains several challenges, especially due to grammatical inconsistencies and spelling variations in addition to all the previous known challenges for social media scenarios. In this article, we present a novel architecture focusing on normalizing phonetic typing variations, which is commonly seen in code-mixed data. One of the main features of our architecture is that in addition to normalizing, it can also be utiliz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08701","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":"1805.08701","created_at":"2026-05-18T00:15:25.317464+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08701v1","created_at":"2026-05-18T00:15:25.317464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08701","created_at":"2026-05-18T00:15:25.317464+00:00"},{"alias_kind":"pith_short_12","alias_value":"6JWMVFESRUWD","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"6JWMVFESRUWD2ST6","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"6JWMVFES","created_at":"2026-05-18T12:32:08.215937+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/6JWMVFESRUWD2ST6IQXATRI22I","json":"https://pith.science/pith/6JWMVFESRUWD2ST6IQXATRI22I.json","graph_json":"https://pith.science/api/pith-number/6JWMVFESRUWD2ST6IQXATRI22I/graph.json","events_json":"https://pith.science/api/pith-number/6JWMVFESRUWD2ST6IQXATRI22I/events.json","paper":"https://pith.science/paper/6JWMVFES"},"agent_actions":{"view_html":"https://pith.science/pith/6JWMVFESRUWD2ST6IQXATRI22I","download_json":"https://pith.science/pith/6JWMVFESRUWD2ST6IQXATRI22I.json","view_paper":"https://pith.science/paper/6JWMVFES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08701&json=true","fetch_graph":"https://pith.science/api/pith-number/6JWMVFESRUWD2ST6IQXATRI22I/graph.json","fetch_events":"https://pith.science/api/pith-number/6JWMVFESRUWD2ST6IQXATRI22I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6JWMVFESRUWD2ST6IQXATRI22I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6JWMVFESRUWD2ST6IQXATRI22I/action/storage_attestation","attest_author":"https://pith.science/pith/6JWMVFESRUWD2ST6IQXATRI22I/action/author_attestation","sign_citation":"https://pith.science/pith/6JWMVFESRUWD2ST6IQXATRI22I/action/citation_signature","submit_replication":"https://pith.science/pith/6JWMVFESRUWD2ST6IQXATRI22I/action/replication_record"}},"created_at":"2026-05-18T00:15:25.317464+00:00","updated_at":"2026-05-18T00:15:25.317464+00:00"}