{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CS4TPT2Q6CF7S6SGXFHCRX4FPT","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":"fe80113390f1e22ee9bdda1a37d5f6a2103b67b3481c9629e08f2efae0cb07c4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-05T01:06:29Z","title_canon_sha256":"0ad219675e928c021770d3a3f9b7914b6ebf2d3d22a83b409ef9b7c3eacea4bf"},"schema_version":"1.0","source":{"id":"2607.04071","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04071","created_at":"2026-07-07T02:18:55Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04071v1","created_at":"2026-07-07T02:18:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04071","created_at":"2026-07-07T02:18:55Z"},{"alias_kind":"pith_short_12","alias_value":"CS4TPT2Q6CF7","created_at":"2026-07-07T02:18:55Z"},{"alias_kind":"pith_short_16","alias_value":"CS4TPT2Q6CF7S6SG","created_at":"2026-07-07T02:18:55Z"},{"alias_kind":"pith_short_8","alias_value":"CS4TPT2Q","created_at":"2026-07-07T02:18:55Z"}],"graph_snapshots":[{"event_id":"sha256:8ac212ee3a4a37a35b6d5b02e1f9f7db15ff0d3f61cb6728bbbea2276d6cdd26","target":"graph","created_at":"2026-07-07T02:18:55Z","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/2607.04071/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Portuguese remains underrepresented in text embedding evaluation, despite being one of the most widely spoken languages in the world. As a result, embedding models are often selected based on English or multilingual metrics, while their effectiveness in Portuguese remains unclear. We present MTEB-PT, a Portuguese benchmark constructed from a subset of MMTEB, comprising 14 existing datasets across Semantic Textual Similarity (STS), classification, retrieval, and reranking. We use this benchmark to evaluate 17 open- and closed-source embedding models under a unified protocol. Our results show th","authors_text":"Alexandre Alcoforado, Anna Helena Reali Costa, Lucas Hideki Takeuchi Okamura","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-05T01:06:29Z","title":"Beyond Multilingual Averages: MTEB-PT, a Benchmark for Portuguese Sentence Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04071","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":"sha256:5a2aa73e37d246fd008e3b476b87d5f46c0712b1fc8b82492fdd356fc5c37726","target":"record","created_at":"2026-07-07T02:18:55Z","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":"fe80113390f1e22ee9bdda1a37d5f6a2103b67b3481c9629e08f2efae0cb07c4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-05T01:06:29Z","title_canon_sha256":"0ad219675e928c021770d3a3f9b7914b6ebf2d3d22a83b409ef9b7c3eacea4bf"},"schema_version":"1.0","source":{"id":"2607.04071","kind":"arxiv","version":1}},"canonical_sha256":"14b937cf50f08bf97a46b94e28df857cc80382bacbc43443a8a8c9468908c12f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14b937cf50f08bf97a46b94e28df857cc80382bacbc43443a8a8c9468908c12f","first_computed_at":"2026-07-07T02:18:55.958531Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:18:55.958531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tG+eRdjDFJ7LAidtVTQbVCoMiAEGU5V+kVZHAfY9DZb2MKtM/wSEABAwvkspkHC4YJbXW2l/+2FPV/nEL7PzBA==","signature_status":"signed_v1","signed_at":"2026-07-07T02:18:55.959220Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04071","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a2aa73e37d246fd008e3b476b87d5f46c0712b1fc8b82492fdd356fc5c37726","sha256:8ac212ee3a4a37a35b6d5b02e1f9f7db15ff0d3f61cb6728bbbea2276d6cdd26"],"state_sha256":"60af9202f6de611fa3fb9cbc5e6f676859097189deee5101d15dd1dd77f23fd7"}