{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VJZW2XPMY3J5CZYXRDKLBKT4DK","short_pith_number":"pith:VJZW2XPM","canonical_record":{"source":{"id":"2409.20467","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T16:26:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"851bed48798e049ec5f1c9f6622ec9dbc6b09be5c01266932078a091304bb538","abstract_canon_sha256":"a4c14f9ec5e3b4554572246afbc68da8a79f94a8eacdf053e23e2195b59373f6"},"schema_version":"1.0"},"canonical_sha256":"aa736d5decc6d3d1671788d4b0aa7c1abed9819aef72c7c2fc888c887c8630a8","source":{"kind":"arxiv","id":"2409.20467","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VJZW2XPMY3J5CZYXRDKLBKT4DK","target":"record","payload":{"canonical_record":{"source":{"id":"2409.20467","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T16:26:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"851bed48798e049ec5f1c9f6622ec9dbc6b09be5c01266932078a091304bb538","abstract_canon_sha256":"a4c14f9ec5e3b4554572246afbc68da8a79f94a8eacdf053e23e2195b59373f6"},"schema_version":"1.0"},"canonical_sha256":"aa736d5decc6d3d1671788d4b0aa7c1abed9819aef72c7c2fc888c887c8630a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:43.977333Z","signature_b64":"I9gCwhddnPCLaAQ/CjVi+090NJ9fD3l3hoK31ta2IXdnw1RsY22Xy4wTJ+vbbwTBbiBwsV202F2nrHMSrm+KCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa736d5decc6d3d1671788d4b0aa7c1abed9819aef72c7c2fc888c887c8630a8","last_reissued_at":"2026-07-05T09:13:43.976783Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:43.976783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.20467","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":"2026-07-05T09:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gyKhOa61qZJkoDj3uOH7p+woSsmhBGKGnkQvCYlU2kBFDSKEKip03iZ7Z6IVrhH48eV4z/7hGJny7tihBDMMAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T20:43:44.483265Z"},"content_sha256":"0166ea54cc56e06acf49a545e682034a7c4dbc83d40aa10ad35a21b1135f604b","schema_version":"1.0","event_id":"sha256:0166ea54cc56e06acf49a545e682034a7c4dbc83d40aa10ad35a21b1135f604b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VJZW2XPMY3J5CZYXRDKLBKT4DK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Weakly Supervised Data Labeling Framework for Machine Lexical Normalization in Vietnamese Social Media","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":"2024-09-30T16:26:40Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20467","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/2409.20467/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aor3FX35aZ9XgyVZt1bOA6jSokl+tpLBNgLU5xJCczK/YvVQVfnsv3v7nVX3SvceLOsncOxEfwIaVb8t7C6HDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T20:43:44.483884Z"},"content_sha256":"fcf5d0e19fc1c8e8aec4bbefaff86abf5f025f8a49b5c771bec591fc8ec63664","schema_version":"1.0","event_id":"sha256:fcf5d0e19fc1c8e8aec4bbefaff86abf5f025f8a49b5c771bec591fc8ec63664"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VJZW2XPMY3J5CZYXRDKLBKT4DK/bundle.json","state_url":"https://pith.science/pith/VJZW2XPMY3J5CZYXRDKLBKT4DK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VJZW2XPMY3J5CZYXRDKLBKT4DK/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":"2026-08-13T20:43:44Z","links":{"resolver":"https://pith.science/pith/VJZW2XPMY3J5CZYXRDKLBKT4DK","bundle":"https://pith.science/pith/VJZW2XPMY3J5CZYXRDKLBKT4DK/bundle.json","state":"https://pith.science/pith/VJZW2XPMY3J5CZYXRDKLBKT4DK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VJZW2XPMY3J5CZYXRDKLBKT4DK/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/drKC53QBNJG2+3Qj2PcLZvfYSPU+Ej4EpXJxeUJIgfQSCQNrt4tHxpKcjOy2WK3TvDwgj6kQc5SL04xdZIHBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T20:43:44.498141Z","bundle_sha256":"58403a4741417a235ff69e816b3c8100fbf4fc265c1b16e1bdbe9cbd470b679f"}}