{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5GXB7JI52QFDUHCM3UJZUD252B","short_pith_number":"pith:5GXB7JI5","schema_version":"1.0","canonical_sha256":"e9ae1fa51dd40a3a1c4cdd139a0f5dd059482009a40f80b8c86b122087639e90","source":{"kind":"arxiv","id":"2407.19527","version":1},"attestation_state":"computed","paper":{"title":"Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ant\\'onio Branco, Jo\\~ao Rodrigues, Jo\\~ao Silva, Lu\\'is Gomes, Rodrigo Santos","submitted_at":"2024-07-28T16:34:25Z","abstract_excerpt":"Sentence encoder encode the semantics of their input, enabling key downstream applications such as classification, clustering, or retrieval. In this paper, we present Serafim PT*, a family of open-source sentence encoders for Portuguese with various sizes, suited to different hardware/compute budgets. Each model exhibits state-of-the-art performance and is made openly available under a permissive license, allowing its use for both commercial and research purposes. Besides the sentence encoders, this paper contributes a systematic study and lessons learned concerning the selection criteria of l"},"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":"2407.19527","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-28T16:34:25Z","cross_cats_sorted":[],"title_canon_sha256":"5d01c96fa5b73307088a2c6fe0b02788b64f144c4ab1cadbdd33c9ce4d8f9b7f","abstract_canon_sha256":"b8ef80af9a052f0c0d999b4f480ee4f16adcac52aca7c265a66a49cadfd71238"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:41.121750Z","signature_b64":"TfujpfQKjHynfd+s1JFl6oaYv3VzIdjmbZ2pXYJdPQhB/Yycfzpr3gTdOdGG/Yj7cD63iHEhK9/hk6D7v406Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9ae1fa51dd40a3a1c4cdd139a0f5dd059482009a40f80b8c86b122087639e90","last_reissued_at":"2026-07-05T08:49:41.121397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:41.121397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ant\\'onio Branco, Jo\\~ao Rodrigues, Jo\\~ao Silva, Lu\\'is Gomes, Rodrigo Santos","submitted_at":"2024-07-28T16:34:25Z","abstract_excerpt":"Sentence encoder encode the semantics of their input, enabling key downstream applications such as classification, clustering, or retrieval. In this paper, we present Serafim PT*, a family of open-source sentence encoders for Portuguese with various sizes, suited to different hardware/compute budgets. Each model exhibits state-of-the-art performance and is made openly available under a permissive license, allowing its use for both commercial and research purposes. Besides the sentence encoders, this paper contributes a systematic study and lessons learned concerning the selection criteria of l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19527","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/2407.19527/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":"2407.19527","created_at":"2026-07-05T08:49:41.121456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.19527v1","created_at":"2026-07-05T08:49:41.121456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19527","created_at":"2026-07-05T08:49:41.121456+00:00"},{"alias_kind":"pith_short_12","alias_value":"5GXB7JI52QFD","created_at":"2026-07-05T08:49:41.121456+00:00"},{"alias_kind":"pith_short_16","alias_value":"5GXB7JI52QFDUHCM","created_at":"2026-07-05T08:49:41.121456+00:00"},{"alias_kind":"pith_short_8","alias_value":"5GXB7JI5","created_at":"2026-07-05T08:49:41.121456+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/5GXB7JI52QFDUHCM3UJZUD252B","json":"https://pith.science/pith/5GXB7JI52QFDUHCM3UJZUD252B.json","graph_json":"https://pith.science/api/pith-number/5GXB7JI52QFDUHCM3UJZUD252B/graph.json","events_json":"https://pith.science/api/pith-number/5GXB7JI52QFDUHCM3UJZUD252B/events.json","paper":"https://pith.science/paper/5GXB7JI5"},"agent_actions":{"view_html":"https://pith.science/pith/5GXB7JI52QFDUHCM3UJZUD252B","download_json":"https://pith.science/pith/5GXB7JI52QFDUHCM3UJZUD252B.json","view_paper":"https://pith.science/paper/5GXB7JI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.19527&json=true","fetch_graph":"https://pith.science/api/pith-number/5GXB7JI52QFDUHCM3UJZUD252B/graph.json","fetch_events":"https://pith.science/api/pith-number/5GXB7JI52QFDUHCM3UJZUD252B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5GXB7JI52QFDUHCM3UJZUD252B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5GXB7JI52QFDUHCM3UJZUD252B/action/storage_attestation","attest_author":"https://pith.science/pith/5GXB7JI52QFDUHCM3UJZUD252B/action/author_attestation","sign_citation":"https://pith.science/pith/5GXB7JI52QFDUHCM3UJZUD252B/action/citation_signature","submit_replication":"https://pith.science/pith/5GXB7JI52QFDUHCM3UJZUD252B/action/replication_record"}},"created_at":"2026-07-05T08:49:41.121456+00:00","updated_at":"2026-07-05T08:49:41.121456+00:00"}