{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:WKXA3I2OJ57SD4Y6ZI3OMU5OC2","short_pith_number":"pith:WKXA3I2O","canonical_record":{"source":{"id":"2008.09144","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-20T18:10:13Z","cross_cats_sorted":[],"title_canon_sha256":"86f2acadc76220d0453b7ebe5c5aaac9f9f5269a0f02ffcccc8acae538c818d9","abstract_canon_sha256":"4b10cd67f09e940ce3a4d2bac365b5b8f99ac3d0b938989988b1ba628b975e53"},"schema_version":"1.0"},"canonical_sha256":"b2ae0da34e4f7f21f31eca36e653ae16853a51b88d2121821d4524699550dbe1","source":{"kind":"arxiv","id":"2008.09144","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.09144","created_at":"2026-07-05T01:41:33Z"},{"alias_kind":"arxiv_version","alias_value":"2008.09144v2","created_at":"2026-07-05T01:41:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.09144","created_at":"2026-07-05T01:41:33Z"},{"alias_kind":"pith_short_12","alias_value":"WKXA3I2OJ57S","created_at":"2026-07-05T01:41:33Z"},{"alias_kind":"pith_short_16","alias_value":"WKXA3I2OJ57SD4Y6","created_at":"2026-07-05T01:41:33Z"},{"alias_kind":"pith_short_8","alias_value":"WKXA3I2O","created_at":"2026-07-05T01:41:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:WKXA3I2OJ57SD4Y6ZI3OMU5OC2","target":"record","payload":{"canonical_record":{"source":{"id":"2008.09144","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-20T18:10:13Z","cross_cats_sorted":[],"title_canon_sha256":"86f2acadc76220d0453b7ebe5c5aaac9f9f5269a0f02ffcccc8acae538c818d9","abstract_canon_sha256":"4b10cd67f09e940ce3a4d2bac365b5b8f99ac3d0b938989988b1ba628b975e53"},"schema_version":"1.0"},"canonical_sha256":"b2ae0da34e4f7f21f31eca36e653ae16853a51b88d2121821d4524699550dbe1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:33.262166Z","signature_b64":"BUN7GSvU5uNdU5GRPb8fLRswsCGyRM3nMNWsn8P7CB5uSuotWU860mY4VYnRhub42o+dFovpoKIeBh5+QsOEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2ae0da34e4f7f21f31eca36e653ae16853a51b88d2121821d4524699550dbe1","last_reissued_at":"2026-07-05T01:41:33.261542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:33.261542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.09144","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:41:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Un+6B2JpwsyvmN91cDTpAzWf3rkY+osmhz5IjntOpdfz4d1rAd8HcHhplvfPScWIaLH0NGanpKpyVSWWNCYeBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T08:17:43.823477Z"},"content_sha256":"ee5eff4caf81cf4219317c448b717bad4a4d112c57718eb4dbaf9eb98e0755e0","schema_version":"1.0","event_id":"sha256:ee5eff4caf81cf4219317c448b717bad4a4d112c57718eb4dbaf9eb98e0755e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:WKXA3I2OJ57SD4Y6ZI3OMU5OC2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PTT5: Pretraining and validating the T5 model on Brazilian Portuguese data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Diedre Carmo, Israel Campiotti, Marcos Piau, Roberto Lotufo, Rodrigo Nogueira","submitted_at":"2020-08-20T18:10:13Z","abstract_excerpt":"In natural language processing (NLP), there is a need for more resources in Portuguese, since much of the data used in the state-of-the-art research is in other languages. In this paper, we pretrain a T5 model on the BrWac corpus, an extensive collection of web pages in Portuguese, and evaluate its performance against other Portuguese pretrained models and multilingual models on three different tasks. We show that our Portuguese pretrained models have significantly better performance over the original T5 models. Moreover, we demonstrate the positive impact of using a Portuguese vocabulary. Our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.09144","kind":"arxiv","version":2},"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/2008.09144/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":"2026-07-05T01:41:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sZVkGGVkT+yaL9GO2N+TsYC4TnsuYxdXe1eIVbStieFIeeudLIMg28Il3q69GbvIP4UR5Inb4naHuvtCOaSkDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T08:17:43.824373Z"},"content_sha256":"bc7f09ab319f37fed1a09ee514d2e1157e3b4cc8a10689e6c9beecd44d2e32c3","schema_version":"1.0","event_id":"sha256:bc7f09ab319f37fed1a09ee514d2e1157e3b4cc8a10689e6c9beecd44d2e32c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WKXA3I2OJ57SD4Y6ZI3OMU5OC2/bundle.json","state_url":"https://pith.science/pith/WKXA3I2OJ57SD4Y6ZI3OMU5OC2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WKXA3I2OJ57SD4Y6ZI3OMU5OC2/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":"2026-08-01T08:17:43Z","links":{"resolver":"https://pith.science/pith/WKXA3I2OJ57SD4Y6ZI3OMU5OC2","bundle":"https://pith.science/pith/WKXA3I2OJ57SD4Y6ZI3OMU5OC2/bundle.json","state":"https://pith.science/pith/WKXA3I2OJ57SD4Y6ZI3OMU5OC2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WKXA3I2OJ57SD4Y6ZI3OMU5OC2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:WKXA3I2OJ57SD4Y6ZI3OMU5OC2","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":"4b10cd67f09e940ce3a4d2bac365b5b8f99ac3d0b938989988b1ba628b975e53","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-20T18:10:13Z","title_canon_sha256":"86f2acadc76220d0453b7ebe5c5aaac9f9f5269a0f02ffcccc8acae538c818d9"},"schema_version":"1.0","source":{"id":"2008.09144","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.09144","created_at":"2026-07-05T01:41:33Z"},{"alias_kind":"arxiv_version","alias_value":"2008.09144v2","created_at":"2026-07-05T01:41:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.09144","created_at":"2026-07-05T01:41:33Z"},{"alias_kind":"pith_short_12","alias_value":"WKXA3I2OJ57S","created_at":"2026-07-05T01:41:33Z"},{"alias_kind":"pith_short_16","alias_value":"WKXA3I2OJ57SD4Y6","created_at":"2026-07-05T01:41:33Z"},{"alias_kind":"pith_short_8","alias_value":"WKXA3I2O","created_at":"2026-07-05T01:41:33Z"}],"graph_snapshots":[{"event_id":"sha256:bc7f09ab319f37fed1a09ee514d2e1157e3b4cc8a10689e6c9beecd44d2e32c3","target":"graph","created_at":"2026-07-05T01:41:33Z","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/2008.09144/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In natural language processing (NLP), there is a need for more resources in Portuguese, since much of the data used in the state-of-the-art research is in other languages. In this paper, we pretrain a T5 model on the BrWac corpus, an extensive collection of web pages in Portuguese, and evaluate its performance against other Portuguese pretrained models and multilingual models on three different tasks. We show that our Portuguese pretrained models have significantly better performance over the original T5 models. Moreover, we demonstrate the positive impact of using a Portuguese vocabulary. Our","authors_text":"Diedre Carmo, Israel Campiotti, Marcos Piau, Roberto Lotufo, Rodrigo Nogueira","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-20T18:10:13Z","title":"PTT5: Pretraining and validating the T5 model on Brazilian Portuguese data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.09144","kind":"arxiv","version":2},"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:ee5eff4caf81cf4219317c448b717bad4a4d112c57718eb4dbaf9eb98e0755e0","target":"record","created_at":"2026-07-05T01:41:33Z","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":"4b10cd67f09e940ce3a4d2bac365b5b8f99ac3d0b938989988b1ba628b975e53","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-20T18:10:13Z","title_canon_sha256":"86f2acadc76220d0453b7ebe5c5aaac9f9f5269a0f02ffcccc8acae538c818d9"},"schema_version":"1.0","source":{"id":"2008.09144","kind":"arxiv","version":2}},"canonical_sha256":"b2ae0da34e4f7f21f31eca36e653ae16853a51b88d2121821d4524699550dbe1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2ae0da34e4f7f21f31eca36e653ae16853a51b88d2121821d4524699550dbe1","first_computed_at":"2026-07-05T01:41:33.261542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:41:33.261542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BUN7GSvU5uNdU5GRPb8fLRswsCGyRM3nMNWsn8P7CB5uSuotWU860mY4VYnRhub42o+dFovpoKIeBh5+QsOEBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:41:33.262166Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.09144","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee5eff4caf81cf4219317c448b717bad4a4d112c57718eb4dbaf9eb98e0755e0","sha256:bc7f09ab319f37fed1a09ee514d2e1157e3b4cc8a10689e6c9beecd44d2e32c3"],"state_sha256":"7883149206893cf76b1aa1e24ed1438cfa33fcc1e99649702ce98292d88273c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T7glnJXmJSdXriYbTwSJFaIoCp9czGYsizg3FxECMaCUjbdCXKzMskWCCTtTPbVYvICgyb3dPdDoICbwvriqAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T08:17:43.830383Z","bundle_sha256":"bbe913eaf3146083a6847fe21c999855347c111b2b4b4d78c1aec2490f713def"}}