{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5GXB7JI52QFDUHCM3UJZUD252B","short_pith_number":"pith:5GXB7JI5","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"},"canonical_sha256":"e9ae1fa51dd40a3a1c4cdd139a0f5dd059482009a40f80b8c86b122087639e90","source":{"kind":"arxiv","id":"2407.19527","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.19527","created_at":"2026-07-05T08:49:41Z"},{"alias_kind":"arxiv_version","alias_value":"2407.19527v1","created_at":"2026-07-05T08:49:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19527","created_at":"2026-07-05T08:49:41Z"},{"alias_kind":"pith_short_12","alias_value":"5GXB7JI52QFD","created_at":"2026-07-05T08:49:41Z"},{"alias_kind":"pith_short_16","alias_value":"5GXB7JI52QFDUHCM","created_at":"2026-07-05T08:49:41Z"},{"alias_kind":"pith_short_8","alias_value":"5GXB7JI5","created_at":"2026-07-05T08:49:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5GXB7JI52QFDUHCM3UJZUD252B","target":"record","payload":{"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"},"canonical_sha256":"e9ae1fa51dd40a3a1c4cdd139a0f5dd059482009a40f80b8c86b122087639e90","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"},"source_kind":"arxiv","source_id":"2407.19527","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:49:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MA8NojEF6N1kcijo787E1FTp2mTMEPzteQMz7XADOoO6Ch5QDPSuwtsoXJTi7XouWc6AXQU94QYERvlTFLg4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:38:49.677884Z"},"content_sha256":"1cd42d763c270c6761c6e03110e6066ef991d74aef2910f8d0684dc66099e059","schema_version":"1.0","event_id":"sha256:1cd42d763c270c6761c6e03110e6066ef991d74aef2910f8d0684dc66099e059"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5GXB7JI52QFDUHCM3UJZUD252B","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:49:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oP/sRHpbZEK+n8tP8rCKdSySZGJBkDSgArQsrS7EDRIwG8orJDgPyOKwIVSjN8wX9dL8FDz3p/ESmuR1BI42Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:38:49.678856Z"},"content_sha256":"0b7e714ac6d84561629fdcf4f97117b9dd4b67372df855ff897eb566a82fd6a4","schema_version":"1.0","event_id":"sha256:0b7e714ac6d84561629fdcf4f97117b9dd4b67372df855ff897eb566a82fd6a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5GXB7JI52QFDUHCM3UJZUD252B/bundle.json","state_url":"https://pith.science/pith/5GXB7JI52QFDUHCM3UJZUD252B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5GXB7JI52QFDUHCM3UJZUD252B/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T19:38:49Z","links":{"resolver":"https://pith.science/pith/5GXB7JI52QFDUHCM3UJZUD252B","bundle":"https://pith.science/pith/5GXB7JI52QFDUHCM3UJZUD252B/bundle.json","state":"https://pith.science/pith/5GXB7JI52QFDUHCM3UJZUD252B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5GXB7JI52QFDUHCM3UJZUD252B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5GXB7JI52QFDUHCM3UJZUD252B","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":"b8ef80af9a052f0c0d999b4f480ee4f16adcac52aca7c265a66a49cadfd71238","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-28T16:34:25Z","title_canon_sha256":"5d01c96fa5b73307088a2c6fe0b02788b64f144c4ab1cadbdd33c9ce4d8f9b7f"},"schema_version":"1.0","source":{"id":"2407.19527","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.19527","created_at":"2026-07-05T08:49:41Z"},{"alias_kind":"arxiv_version","alias_value":"2407.19527v1","created_at":"2026-07-05T08:49:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19527","created_at":"2026-07-05T08:49:41Z"},{"alias_kind":"pith_short_12","alias_value":"5GXB7JI52QFD","created_at":"2026-07-05T08:49:41Z"},{"alias_kind":"pith_short_16","alias_value":"5GXB7JI52QFDUHCM","created_at":"2026-07-05T08:49:41Z"},{"alias_kind":"pith_short_8","alias_value":"5GXB7JI5","created_at":"2026-07-05T08:49:41Z"}],"graph_snapshots":[{"event_id":"sha256:0b7e714ac6d84561629fdcf4f97117b9dd4b67372df855ff897eb566a82fd6a4","target":"graph","created_at":"2026-07-05T08:49:41Z","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/2407.19527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ant\\'onio Branco, Jo\\~ao Rodrigues, Jo\\~ao Silva, Lu\\'is Gomes, Rodrigo Santos","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-28T16:34:25Z","title":"Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19527","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":"sha256:1cd42d763c270c6761c6e03110e6066ef991d74aef2910f8d0684dc66099e059","target":"record","created_at":"2026-07-05T08:49:41Z","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":"b8ef80af9a052f0c0d999b4f480ee4f16adcac52aca7c265a66a49cadfd71238","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-28T16:34:25Z","title_canon_sha256":"5d01c96fa5b73307088a2c6fe0b02788b64f144c4ab1cadbdd33c9ce4d8f9b7f"},"schema_version":"1.0","source":{"id":"2407.19527","kind":"arxiv","version":1}},"canonical_sha256":"e9ae1fa51dd40a3a1c4cdd139a0f5dd059482009a40f80b8c86b122087639e90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9ae1fa51dd40a3a1c4cdd139a0f5dd059482009a40f80b8c86b122087639e90","first_computed_at":"2026-07-05T08:49:41.121397Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:49:41.121397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TfujpfQKjHynfd+s1JFl6oaYv3VzIdjmbZ2pXYJdPQhB/Yycfzpr3gTdOdGG/Yj7cD63iHEhK9/hk6D7v406Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:49:41.121750Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.19527","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cd42d763c270c6761c6e03110e6066ef991d74aef2910f8d0684dc66099e059","sha256:0b7e714ac6d84561629fdcf4f97117b9dd4b67372df855ff897eb566a82fd6a4"],"state_sha256":"48d32585822df7334ac614222b5f2598d656e5ae910c3ba1ca8ce7c95ed041da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CFHoqz6dUMwoh7YoV31dQtiq4RGuwkNlBdKkScgFZrIXjllUq4V5bPMM2PBfz99FpXCd+Ok9DR6BN5Wa+LMlDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T19:38:49.685139Z","bundle_sha256":"bcbe8b0b95f1a928b53b3b0d1d1085c11529831c9dd11482b4350a527604bac0"}}