{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZDXMQY6RUJIW3M5G7AE2PAGJ2D","short_pith_number":"pith:ZDXMQY6R","schema_version":"1.0","canonical_sha256":"c8eec863d1a2516db3a6f809a780c9d0c0c3f5124d21e6228d12d6256742d8d2","source":{"kind":"arxiv","id":"2607.04581","version":1},"attestation_state":"computed","paper":{"title":"MTEB-PT: A Text Embedding Benchmark for Brazilian Portuguese","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Tardelli Ronan Coelho Stekel","submitted_at":"2026-07-06T01:19:30Z","abstract_excerpt":"Text embeddings for Portuguese have no dedicated benchmark: evaluation rests on translated corpora such as English MS MARCO or on thin multilingual coverage, with native tasks scattered and unconsolidated. We introduce MTEB-PT, a benchmark of 22 native Brazilian-Portuguese tasks across seven categories (classification, multilabel classification, pair classification, semantic textual similarity, clustering, retrieval, and reranking), admitting only data created or found in Portuguese and excluding translations by construction. We evaluate 93 models spanning 23M to 27B parameters: 73 open-weight"},"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":"2607.04581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T01:19:30Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"176592b75e16931ad35b4b236d6cf51b81a2663e74b7c9896c8bf5d8e7cb3126","abstract_canon_sha256":"50fb97e82f26203e896b13ad36259ef63e7eac9aa997f362df8acd18f4c68455"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:25.749025Z","signature_b64":"yJCFoG1ZhnhP8nZonYaOQg0F4O0BMbATjikqKF7Ijar6hYbGczvZDPUmEtBqp+C4wNdd5vqFpwU5VvX5qBm2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8eec863d1a2516db3a6f809a780c9d0c0c3f5124d21e6228d12d6256742d8d2","last_reissued_at":"2026-07-07T02:19:25.748460Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:25.748460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MTEB-PT: A Text Embedding Benchmark for Brazilian Portuguese","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Tardelli Ronan Coelho Stekel","submitted_at":"2026-07-06T01:19:30Z","abstract_excerpt":"Text embeddings for Portuguese have no dedicated benchmark: evaluation rests on translated corpora such as English MS MARCO or on thin multilingual coverage, with native tasks scattered and unconsolidated. We introduce MTEB-PT, a benchmark of 22 native Brazilian-Portuguese tasks across seven categories (classification, multilabel classification, pair classification, semantic textual similarity, clustering, retrieval, and reranking), admitting only data created or found in Portuguese and excluding translations by construction. We evaluate 93 models spanning 23M to 27B parameters: 73 open-weight"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04581","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/2607.04581/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":"2607.04581","created_at":"2026-07-07T02:19:25.748552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04581v1","created_at":"2026-07-07T02:19:25.748552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04581","created_at":"2026-07-07T02:19:25.748552+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDXMQY6RUJIW","created_at":"2026-07-07T02:19:25.748552+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDXMQY6RUJIW3M5G","created_at":"2026-07-07T02:19:25.748552+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDXMQY6R","created_at":"2026-07-07T02:19:25.748552+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/ZDXMQY6RUJIW3M5G7AE2PAGJ2D","json":"https://pith.science/pith/ZDXMQY6RUJIW3M5G7AE2PAGJ2D.json","graph_json":"https://pith.science/api/pith-number/ZDXMQY6RUJIW3M5G7AE2PAGJ2D/graph.json","events_json":"https://pith.science/api/pith-number/ZDXMQY6RUJIW3M5G7AE2PAGJ2D/events.json","paper":"https://pith.science/paper/ZDXMQY6R"},"agent_actions":{"view_html":"https://pith.science/pith/ZDXMQY6RUJIW3M5G7AE2PAGJ2D","download_json":"https://pith.science/pith/ZDXMQY6RUJIW3M5G7AE2PAGJ2D.json","view_paper":"https://pith.science/paper/ZDXMQY6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04581&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDXMQY6RUJIW3M5G7AE2PAGJ2D/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDXMQY6RUJIW3M5G7AE2PAGJ2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDXMQY6RUJIW3M5G7AE2PAGJ2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDXMQY6RUJIW3M5G7AE2PAGJ2D/action/storage_attestation","attest_author":"https://pith.science/pith/ZDXMQY6RUJIW3M5G7AE2PAGJ2D/action/author_attestation","sign_citation":"https://pith.science/pith/ZDXMQY6RUJIW3M5G7AE2PAGJ2D/action/citation_signature","submit_replication":"https://pith.science/pith/ZDXMQY6RUJIW3M5G7AE2PAGJ2D/action/replication_record"}},"created_at":"2026-07-07T02:19:25.748552+00:00","updated_at":"2026-07-07T02:19:25.748552+00:00"}