{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:6JWMVFESRUWD2ST6IQXATRI22I","short_pith_number":"pith:6JWMVFES","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"},"canonical_sha256":"f26cca94928d2c3d4a7e442e09c51ad220f8b901cae095ef3d222d76bf884238","source":{"kind":"arxiv","id":"1805.08701","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08701","created_at":"2026-05-18T00:15:25Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08701v1","created_at":"2026-05-18T00:15:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08701","created_at":"2026-05-18T00:15:25Z"},{"alias_kind":"pith_short_12","alias_value":"6JWMVFESRUWD","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6JWMVFESRUWD2ST6","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6JWMVFES","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:6JWMVFESRUWD2ST6IQXATRI22I","target":"record","payload":{"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"},"canonical_sha256":"f26cca94928d2c3d4a7e442e09c51ad220f8b901cae095ef3d222d76bf884238","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"},"source_kind":"arxiv","source_id":"1805.08701","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+XMDeRh6vR5wdEVNiJmndjsJSHfnn/C8RZdk+srQaWRRyWeG+BKp5Afr3z5lMqWyyCItqwuMVbtGD3VGn1V3AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:37:20.410459Z"},"content_sha256":"e8ebefcdfb27f93f0318371aaaaccb090e8122f3bb197e32a99a52a81db456c2","schema_version":"1.0","event_id":"sha256:e8ebefcdfb27f93f0318371aaaaccb090e8122f3bb197e32a99a52a81db456c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:6JWMVFESRUWD2ST6IQXATRI22I","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nEg9HDQ7g0ToMK0fkLRMd2ikNX1Nifn5doyT0sqnx8wp6hknsC4CVvSwq/YENMKOj2VNcyFllWTltplPTzKEDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:37:20.410800Z"},"content_sha256":"cda7e233aa9f00499881a4f53fdc05bbecf47b0009e790e82e935ad87d1e0cd1","schema_version":"1.0","event_id":"sha256:cda7e233aa9f00499881a4f53fdc05bbecf47b0009e790e82e935ad87d1e0cd1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6JWMVFESRUWD2ST6IQXATRI22I/bundle.json","state_url":"https://pith.science/pith/6JWMVFESRUWD2ST6IQXATRI22I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6JWMVFESRUWD2ST6IQXATRI22I/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T14:37:20Z","links":{"resolver":"https://pith.science/pith/6JWMVFESRUWD2ST6IQXATRI22I","bundle":"https://pith.science/pith/6JWMVFESRUWD2ST6IQXATRI22I/bundle.json","state":"https://pith.science/pith/6JWMVFESRUWD2ST6IQXATRI22I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6JWMVFESRUWD2ST6IQXATRI22I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:6JWMVFESRUWD2ST6IQXATRI22I","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4944e3197169ba61bf21f81def54eab84760c7af362252d1de49ca1cecad1f41","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-22T16:11:12Z","title_canon_sha256":"4e07a80cefb7571cf25f16d0e5cf84a7a61e0e3899b09401fb2c63c379c7b2d6"},"schema_version":"1.0","source":{"id":"1805.08701","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08701","created_at":"2026-05-18T00:15:25Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08701v1","created_at":"2026-05-18T00:15:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08701","created_at":"2026-05-18T00:15:25Z"},{"alias_kind":"pith_short_12","alias_value":"6JWMVFESRUWD","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6JWMVFESRUWD2ST6","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6JWMVFES","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:cda7e233aa9f00499881a4f53fdc05bbecf47b0009e790e82e935ad87d1e0cd1","target":"graph","created_at":"2026-05-18T00:15:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Karthick Nanmaran, Soumil Mandal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-22T16:11:12Z","title":"Normalization of Transliterated Words in Code-Mixed Data Using Seq2Seq Model & Levenshtein Distance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08701","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e8ebefcdfb27f93f0318371aaaaccb090e8122f3bb197e32a99a52a81db456c2","target":"record","created_at":"2026-05-18T00:15:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4944e3197169ba61bf21f81def54eab84760c7af362252d1de49ca1cecad1f41","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-22T16:11:12Z","title_canon_sha256":"4e07a80cefb7571cf25f16d0e5cf84a7a61e0e3899b09401fb2c63c379c7b2d6"},"schema_version":"1.0","source":{"id":"1805.08701","kind":"arxiv","version":1}},"canonical_sha256":"f26cca94928d2c3d4a7e442e09c51ad220f8b901cae095ef3d222d76bf884238","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f26cca94928d2c3d4a7e442e09c51ad220f8b901cae095ef3d222d76bf884238","first_computed_at":"2026-05-18T00:15:25.317348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:25.317348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mEPICSM4flrF+CYIu2fLOZojptXnDg+RoilIXkTgOH4wwGSA8QYT2vF668P6PyxP4IHasfMJMChdTtpQb8LzCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:25.317995Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.08701","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8ebefcdfb27f93f0318371aaaaccb090e8122f3bb197e32a99a52a81db456c2","sha256:cda7e233aa9f00499881a4f53fdc05bbecf47b0009e790e82e935ad87d1e0cd1"],"state_sha256":"dee32a1d6b9558c50cd558372a7358618c48d79641bd1fbc96db7e0e4572404e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XXeIdbc0xNTqEM/dNbbVIh/rYBSZw/9wtJgrWlVM6rl68lickNZHRNfaAMtm/xD1dq02w7j7Dh0K4EDnKR7sCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T14:37:20.413196Z","bundle_sha256":"29984727094fcd647307b1686c6c2945da27fdd064a3eafe35b1829f29a67489"}}