{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ARG7UBA63VCWMOOVZYVEPOB4YE","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":"895f55ef6d2c6b8686fa4e1920002b6af528d92cf1135e7f76091e3b4061cc9c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-29T04:48:55Z","title_canon_sha256":"16caacbd610410e3663272763f6fa39a48a4aa6332771d2d21195caa8d4f8676"},"schema_version":"1.0","source":{"id":"2507.21500","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21500","created_at":"2026-07-05T11:45:01Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21500v1","created_at":"2026-07-05T11:45:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21500","created_at":"2026-07-05T11:45:01Z"},{"alias_kind":"pith_short_12","alias_value":"ARG7UBA63VCW","created_at":"2026-07-05T11:45:01Z"},{"alias_kind":"pith_short_16","alias_value":"ARG7UBA63VCWMOOV","created_at":"2026-07-05T11:45:01Z"},{"alias_kind":"pith_short_8","alias_value":"ARG7UBA6","created_at":"2026-07-05T11:45:01Z"}],"graph_snapshots":[{"event_id":"sha256:5ee3add95597ee4a1b51e68ed9837a6267beb65881b787b4862b1b878acd056a","target":"graph","created_at":"2026-07-05T11:45:01Z","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/2507.21500/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vietnam ranks among the top countries in terms of both internet traffic and online toxicity. As a result, implementing embedding models for recommendation and content control duties in applications is crucial. However, a lack of large-scale test datasets, both in volume and task diversity, makes it tricky for scientists to effectively evaluate AI models before deploying them in real-world, large-scale projects. To solve this important problem, we introduce a Vietnamese benchmark, VN-MTEB for embedding models, which we created by translating a large number of English samples from the Massive Te","authors_text":"Loc Pham, Minh Nguyen, Thu Vo, Tung Luu, Viet Hoang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-29T04:48:55Z","title":"VN-MTEB: Vietnamese Massive Text Embedding Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21500","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:e307c28efd9b32add2d8b88fb004cc14a4b9904196bce73a2382553137e8551f","target":"record","created_at":"2026-07-05T11:45:01Z","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":"895f55ef6d2c6b8686fa4e1920002b6af528d92cf1135e7f76091e3b4061cc9c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-29T04:48:55Z","title_canon_sha256":"16caacbd610410e3663272763f6fa39a48a4aa6332771d2d21195caa8d4f8676"},"schema_version":"1.0","source":{"id":"2507.21500","kind":"arxiv","version":1}},"canonical_sha256":"044dfa041edd456639d5ce2a47b83cc106a313202fdca3b4f5158d601011a9e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"044dfa041edd456639d5ce2a47b83cc106a313202fdca3b4f5158d601011a9e0","first_computed_at":"2026-07-05T11:45:01.265779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:01.265779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e1+Qqws4m4o7XbDZYlzDvvKldsIX9fau2/qXrZsfTZ3zrqXzDROxFs1atx/PGVb/NpF22GINSeasiss2IsIVCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:01.266336Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.21500","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e307c28efd9b32add2d8b88fb004cc14a4b9904196bce73a2382553137e8551f","sha256:5ee3add95597ee4a1b51e68ed9837a6267beb65881b787b4862b1b878acd056a"],"state_sha256":"06b23955ad03c3625c934f068f0b2bab1053893604c90ab3d471f445c25e52dc"}