{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VJZW2XPMY3J5CZYXRDKLBKT4DK","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":"a4c14f9ec5e3b4554572246afbc68da8a79f94a8eacdf053e23e2195b59373f6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T16:26:40Z","title_canon_sha256":"851bed48798e049ec5f1c9f6622ec9dbc6b09be5c01266932078a091304bb538"},"schema_version":"1.0","source":{"id":"2409.20467","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.20467","created_at":"2026-07-05T09:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"2409.20467v1","created_at":"2026-07-05T09:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20467","created_at":"2026-07-05T09:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"VJZW2XPMY3J5","created_at":"2026-07-05T09:13:43Z"},{"alias_kind":"pith_short_16","alias_value":"VJZW2XPMY3J5CZYX","created_at":"2026-07-05T09:13:43Z"},{"alias_kind":"pith_short_8","alias_value":"VJZW2XPM","created_at":"2026-07-05T09:13:43Z"}],"graph_snapshots":[{"event_id":"sha256:fcf5d0e19fc1c8e8aec4bbefaff86abf5f025f8a49b5c771bec591fc8ec63664","target":"graph","created_at":"2026-07-05T09:13:43Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.20467/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study introduces an innovative automatic labeling framework to address the challenges of lexical normalization in social media texts for low-resource languages like Vietnamese. Social media data is rich and diverse, but the evolving and varied language used in these contexts makes manual labeling labor-intensive and expensive. To tackle these issues, we propose a framework that integrates semi-supervised learning with weak supervision techniques. This approach enhances the quality of training dataset and expands its size while minimizing manual labeling efforts. Our framework automaticall","authors_text":"Anh Thi Hoang Nguyen, Dung Ha Nguyen, Kiet Van Nguyen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T16:26:40Z","title":"A Weakly Supervised Data Labeling Framework for Machine Lexical Normalization in Vietnamese Social Media"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20467","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":"sha256:0166ea54cc56e06acf49a545e682034a7c4dbc83d40aa10ad35a21b1135f604b","target":"record","created_at":"2026-07-05T09:13:43Z","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":"a4c14f9ec5e3b4554572246afbc68da8a79f94a8eacdf053e23e2195b59373f6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T16:26:40Z","title_canon_sha256":"851bed48798e049ec5f1c9f6622ec9dbc6b09be5c01266932078a091304bb538"},"schema_version":"1.0","source":{"id":"2409.20467","kind":"arxiv","version":1}},"canonical_sha256":"aa736d5decc6d3d1671788d4b0aa7c1abed9819aef72c7c2fc888c887c8630a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa736d5decc6d3d1671788d4b0aa7c1abed9819aef72c7c2fc888c887c8630a8","first_computed_at":"2026-07-05T09:13:43.976783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:43.976783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I9gCwhddnPCLaAQ/CjVi+090NJ9fD3l3hoK31ta2IXdnw1RsY22Xy4wTJ+vbbwTBbiBwsV202F2nrHMSrm+KCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:43.977333Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.20467","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0166ea54cc56e06acf49a545e682034a7c4dbc83d40aa10ad35a21b1135f604b","sha256:fcf5d0e19fc1c8e8aec4bbefaff86abf5f025f8a49b5c771bec591fc8ec63664"],"state_sha256":"5e5d4b6866163651b7d877bd4c1229d5e3e4d6882c22fc24d47c4611d03b9dc4"}