{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:G7KSMVWWDXUVNBYZEYEWWUYIAC","short_pith_number":"pith:G7KSMVWW","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"},"canonical_sha256":"37d52656d61de956871926096b5308008f6b92457d6026c1e859bb5282e9703e","source":{"kind":"arxiv","id":"2501.07020","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07020","created_at":"2026-07-05T10:00:13Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07020v1","created_at":"2026-07-05T10:00:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07020","created_at":"2026-07-05T10:00:13Z"},{"alias_kind":"pith_short_12","alias_value":"G7KSMVWWDXUV","created_at":"2026-07-05T10:00:13Z"},{"alias_kind":"pith_short_16","alias_value":"G7KSMVWWDXUVNBYZ","created_at":"2026-07-05T10:00:13Z"},{"alias_kind":"pith_short_8","alias_value":"G7KSMVWW","created_at":"2026-07-05T10:00:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:G7KSMVWWDXUVNBYZEYEWWUYIAC","target":"record","payload":{"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"},"canonical_sha256":"37d52656d61de956871926096b5308008f6b92457d6026c1e859bb5282e9703e","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"},"source_kind":"arxiv","source_id":"2501.07020","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":"2026-07-05T10:00:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YvDp9yPo9jzHMzNni1nDTTf4NazqyhbHAKGeNw0ovZ2vRgr7BYS+G72FAi+6NvjMlbJbzOQz0FZxuQhPQurQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:31:36.228275Z"},"content_sha256":"a3a490095830c3d65fb0aac751f875e4fd600f78e0964ddf4501fc40fc0296e1","schema_version":"1.0","event_id":"sha256:a3a490095830c3d65fb0aac751f875e4fd600f78e0964ddf4501fc40fc0296e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:G7KSMVWWDXUVNBYZEYEWWUYIAC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:00:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R4gh3hJpalcU3wx9jo3ub8m63TXvYddCjZ7VYc/fIcyInUkPTs2pxzUh1rEpaR2Cd9ofnCSmifWo4fWz5kW5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:31:36.229136Z"},"content_sha256":"58d028ec85420b6e4a18ab4ef6b1ee493fc94883a58c46950cd6194b49b5063c","schema_version":"1.0","event_id":"sha256:58d028ec85420b6e4a18ab4ef6b1ee493fc94883a58c46950cd6194b49b5063c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G7KSMVWWDXUVNBYZEYEWWUYIAC/bundle.json","state_url":"https://pith.science/pith/G7KSMVWWDXUVNBYZEYEWWUYIAC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G7KSMVWWDXUVNBYZEYEWWUYIAC/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":"2026-08-13T13:31:36Z","links":{"resolver":"https://pith.science/pith/G7KSMVWWDXUVNBYZEYEWWUYIAC","bundle":"https://pith.science/pith/G7KSMVWWDXUVNBYZEYEWWUYIAC/bundle.json","state":"https://pith.science/pith/G7KSMVWWDXUVNBYZEYEWWUYIAC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G7KSMVWWDXUVNBYZEYEWWUYIAC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G7KSMVWWDXUVNBYZEYEWWUYIAC","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":"c851e8e0b04b4becbbcffd138cf20b02093b316005a245f254f3ebeec39f2690","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-13T02:47:13Z","title_canon_sha256":"69ec178bf1dc9376b25628b147f7744ff76a03e2277208cb5c9091a95fdfa424"},"schema_version":"1.0","source":{"id":"2501.07020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07020","created_at":"2026-07-05T10:00:13Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07020v1","created_at":"2026-07-05T10:00:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07020","created_at":"2026-07-05T10:00:13Z"},{"alias_kind":"pith_short_12","alias_value":"G7KSMVWWDXUV","created_at":"2026-07-05T10:00:13Z"},{"alias_kind":"pith_short_16","alias_value":"G7KSMVWWDXUVNBYZ","created_at":"2026-07-05T10:00:13Z"},{"alias_kind":"pith_short_8","alias_value":"G7KSMVWW","created_at":"2026-07-05T10:00:13Z"}],"graph_snapshots":[{"event_id":"sha256:58d028ec85420b6e4a18ab4ef6b1ee493fc94883a58c46950cd6194b49b5063c","target":"graph","created_at":"2026-07-05T10:00:13Z","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/2501.07020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","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":"2025-01-13T02:47:13Z","title":"ViSoLex: An Open-Source Repository for Vietnamese Social Media Lexical Normalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07020","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:a3a490095830c3d65fb0aac751f875e4fd600f78e0964ddf4501fc40fc0296e1","target":"record","created_at":"2026-07-05T10:00:13Z","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":"c851e8e0b04b4becbbcffd138cf20b02093b316005a245f254f3ebeec39f2690","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-13T02:47:13Z","title_canon_sha256":"69ec178bf1dc9376b25628b147f7744ff76a03e2277208cb5c9091a95fdfa424"},"schema_version":"1.0","source":{"id":"2501.07020","kind":"arxiv","version":1}},"canonical_sha256":"37d52656d61de956871926096b5308008f6b92457d6026c1e859bb5282e9703e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37d52656d61de956871926096b5308008f6b92457d6026c1e859bb5282e9703e","first_computed_at":"2026-07-05T10:00:13.827233Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:13.827233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gCCUKZoWpKuqZoiosf7xfdzLehn95452gWGwWtKTZtRwgbgQs1eBUmA4E+TwwYBuur7TgffW5p4/E9hNrp+sBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:13.827740Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.07020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3a490095830c3d65fb0aac751f875e4fd600f78e0964ddf4501fc40fc0296e1","sha256:58d028ec85420b6e4a18ab4ef6b1ee493fc94883a58c46950cd6194b49b5063c"],"state_sha256":"8e3e2a12a578326b8aec0de6548adcd250f81e3ece755c1fd2a9cff95d91b24d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"duGdezyPOh9DOgYwLNYlzo5cwEBl52AhGH/xs/DHxVF3+HDdWOjJ1kQmH/kPEqtIlLBqVaEqsW72TxHuZ/N8DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T13:31:36.236845Z","bundle_sha256":"97d1fc4ce7c2bd2af8348309aa53229d93af7e4c1318d3c1b3f2b701d720bfc2"}}