{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G7KSMVWWDXUVNBYZEYEWWUYIAC","short_pith_number":"pith:G7KSMVWW","schema_version":"1.0","canonical_sha256":"37d52656d61de956871926096b5308008f6b92457d6026c1e859bb5282e9703e","source":{"kind":"arxiv","id":"2501.07020","version":1},"attestation_state":"computed","paper":{"title":"ViSoLex: An Open-Source Repository for Vietnamese Social Media Lexical Normalization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anh Thi-Hoang Nguyen, Dung Ha Nguyen, Kiet Van Nguyen","submitted_at":"2025-01-13T02:47:13Z","abstract_excerpt":"ViSoLex is an open-source system designed to address the unique challenges of lexical normalization for Vietnamese social media text. The platform provides two core services: Non-Standard Word (NSW) Lookup and Lexical Normalization, enabling users to retrieve standard forms of informal language and standardize text containing NSWs. ViSoLex's architecture integrates pre-trained language models and weakly supervised learning techniques to ensure accurate and efficient normalization, overcoming the scarcity of labeled data in Vietnamese. This paper details the system's design, functionality, and "},"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":"2501.07020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-13T02:47:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"69ec178bf1dc9376b25628b147f7744ff76a03e2277208cb5c9091a95fdfa424","abstract_canon_sha256":"c851e8e0b04b4becbbcffd138cf20b02093b316005a245f254f3ebeec39f2690"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:13.827740Z","signature_b64":"gCCUKZoWpKuqZoiosf7xfdzLehn95452gWGwWtKTZtRwgbgQs1eBUmA4E+TwwYBuur7TgffW5p4/E9hNrp+sBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37d52656d61de956871926096b5308008f6b92457d6026c1e859bb5282e9703e","last_reissued_at":"2026-07-05T10:00:13.827233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:13.827233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViSoLex: An Open-Source Repository for Vietnamese Social Media Lexical Normalization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anh Thi-Hoang Nguyen, Dung Ha Nguyen, Kiet Van Nguyen","submitted_at":"2025-01-13T02:47:13Z","abstract_excerpt":"ViSoLex is an open-source system designed to address the unique challenges of lexical normalization for Vietnamese social media text. The platform provides two core services: Non-Standard Word (NSW) Lookup and Lexical Normalization, enabling users to retrieve standard forms of informal language and standardize text containing NSWs. ViSoLex's architecture integrates pre-trained language models and weakly supervised learning techniques to ensure accurate and efficient normalization, overcoming the scarcity of labeled data in Vietnamese. This paper details the system's design, functionality, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07020","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/2501.07020/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":"2501.07020","created_at":"2026-07-05T10:00:13.827296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07020v1","created_at":"2026-07-05T10:00:13.827296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07020","created_at":"2026-07-05T10:00:13.827296+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7KSMVWWDXUV","created_at":"2026-07-05T10:00:13.827296+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7KSMVWWDXUVNBYZ","created_at":"2026-07-05T10:00:13.827296+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7KSMVWW","created_at":"2026-07-05T10:00:13.827296+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/G7KSMVWWDXUVNBYZEYEWWUYIAC","json":"https://pith.science/pith/G7KSMVWWDXUVNBYZEYEWWUYIAC.json","graph_json":"https://pith.science/api/pith-number/G7KSMVWWDXUVNBYZEYEWWUYIAC/graph.json","events_json":"https://pith.science/api/pith-number/G7KSMVWWDXUVNBYZEYEWWUYIAC/events.json","paper":"https://pith.science/paper/G7KSMVWW"},"agent_actions":{"view_html":"https://pith.science/pith/G7KSMVWWDXUVNBYZEYEWWUYIAC","download_json":"https://pith.science/pith/G7KSMVWWDXUVNBYZEYEWWUYIAC.json","view_paper":"https://pith.science/paper/G7KSMVWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07020&json=true","fetch_graph":"https://pith.science/api/pith-number/G7KSMVWWDXUVNBYZEYEWWUYIAC/graph.json","fetch_events":"https://pith.science/api/pith-number/G7KSMVWWDXUVNBYZEYEWWUYIAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7KSMVWWDXUVNBYZEYEWWUYIAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7KSMVWWDXUVNBYZEYEWWUYIAC/action/storage_attestation","attest_author":"https://pith.science/pith/G7KSMVWWDXUVNBYZEYEWWUYIAC/action/author_attestation","sign_citation":"https://pith.science/pith/G7KSMVWWDXUVNBYZEYEWWUYIAC/action/citation_signature","submit_replication":"https://pith.science/pith/G7KSMVWWDXUVNBYZEYEWWUYIAC/action/replication_record"}},"created_at":"2026-07-05T10:00:13.827296+00:00","updated_at":"2026-07-05T10:00:13.827296+00:00"}