{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CS4TPT2Q6CF7S6SGXFHCRX4FPT","short_pith_number":"pith:CS4TPT2Q","schema_version":"1.0","canonical_sha256":"14b937cf50f08bf97a46b94e28df857cc80382bacbc43443a8a8c9468908c12f","source":{"kind":"arxiv","id":"2607.04071","version":1},"attestation_state":"computed","paper":{"title":"Beyond Multilingual Averages: MTEB-PT, a Benchmark for Portuguese Sentence Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexandre Alcoforado, Anna Helena Reali Costa, Lucas Hideki Takeuchi Okamura","submitted_at":"2026-07-05T01:06:29Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.04071","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-05T01:06:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0ad219675e928c021770d3a3f9b7914b6ebf2d3d22a83b409ef9b7c3eacea4bf","abstract_canon_sha256":"fe80113390f1e22ee9bdda1a37d5f6a2103b67b3481c9629e08f2efae0cb07c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:55.959220Z","signature_b64":"tG+eRdjDFJ7LAidtVTQbVCoMiAEGU5V+kVZHAfY9DZb2MKtM/wSEABAwvkspkHC4YJbXW2l/+2FPV/nEL7PzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14b937cf50f08bf97a46b94e28df857cc80382bacbc43443a8a8c9468908c12f","last_reissued_at":"2026-07-07T02:18:55.958531Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:55.958531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Multilingual Averages: MTEB-PT, a Benchmark for Portuguese Sentence Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexandre Alcoforado, Anna Helena Reali Costa, Lucas Hideki Takeuchi Okamura","submitted_at":"2026-07-05T01:06:29Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04071","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/2607.04071/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.04071","created_at":"2026-07-07T02:18:55.958634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04071v1","created_at":"2026-07-07T02:18:55.958634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04071","created_at":"2026-07-07T02:18:55.958634+00:00"},{"alias_kind":"pith_short_12","alias_value":"CS4TPT2Q6CF7","created_at":"2026-07-07T02:18:55.958634+00:00"},{"alias_kind":"pith_short_16","alias_value":"CS4TPT2Q6CF7S6SG","created_at":"2026-07-07T02:18:55.958634+00:00"},{"alias_kind":"pith_short_8","alias_value":"CS4TPT2Q","created_at":"2026-07-07T02:18:55.958634+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CS4TPT2Q6CF7S6SGXFHCRX4FPT","json":"https://pith.science/pith/CS4TPT2Q6CF7S6SGXFHCRX4FPT.json","graph_json":"https://pith.science/api/pith-number/CS4TPT2Q6CF7S6SGXFHCRX4FPT/graph.json","events_json":"https://pith.science/api/pith-number/CS4TPT2Q6CF7S6SGXFHCRX4FPT/events.json","paper":"https://pith.science/paper/CS4TPT2Q"},"agent_actions":{"view_html":"https://pith.science/pith/CS4TPT2Q6CF7S6SGXFHCRX4FPT","download_json":"https://pith.science/pith/CS4TPT2Q6CF7S6SGXFHCRX4FPT.json","view_paper":"https://pith.science/paper/CS4TPT2Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04071&json=true","fetch_graph":"https://pith.science/api/pith-number/CS4TPT2Q6CF7S6SGXFHCRX4FPT/graph.json","fetch_events":"https://pith.science/api/pith-number/CS4TPT2Q6CF7S6SGXFHCRX4FPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CS4TPT2Q6CF7S6SGXFHCRX4FPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CS4TPT2Q6CF7S6SGXFHCRX4FPT/action/storage_attestation","attest_author":"https://pith.science/pith/CS4TPT2Q6CF7S6SGXFHCRX4FPT/action/author_attestation","sign_citation":"https://pith.science/pith/CS4TPT2Q6CF7S6SGXFHCRX4FPT/action/citation_signature","submit_replication":"https://pith.science/pith/CS4TPT2Q6CF7S6SGXFHCRX4FPT/action/replication_record"}},"created_at":"2026-07-07T02:18:55.958634+00:00","updated_at":"2026-07-07T02:18:55.958634+00:00"}