{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GEWBFHGSU3FTMH6TCNJ76W7RUH","short_pith_number":"pith:GEWBFHGS","canonical_record":{"source":{"id":"2506.23051","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-29T01:23:57Z","cross_cats_sorted":[],"title_canon_sha256":"fb68737cf0d09af3a30238835a5893cab19a8ae6b311df710f87256f7cdd6eb8","abstract_canon_sha256":"b2dc7b3bbf0d8451fbcebef99412778f3c390d8549dbd82c2df7e74b99a43b11"},"schema_version":"1.0"},"canonical_sha256":"312c129cd2a6cb361fd31353ff5bf1a1d769cb2f8e0ffb82a6eabca5c65ebd08","source":{"kind":"arxiv","id":"2506.23051","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23051","created_at":"2026-07-05T11:28:49Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23051v1","created_at":"2026-07-05T11:28:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23051","created_at":"2026-07-05T11:28:49Z"},{"alias_kind":"pith_short_12","alias_value":"GEWBFHGSU3FT","created_at":"2026-07-05T11:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"GEWBFHGSU3FTMH6T","created_at":"2026-07-05T11:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"GEWBFHGS","created_at":"2026-07-05T11:28:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GEWBFHGSU3FTMH6TCNJ76W7RUH","target":"record","payload":{"canonical_record":{"source":{"id":"2506.23051","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-29T01:23:57Z","cross_cats_sorted":[],"title_canon_sha256":"fb68737cf0d09af3a30238835a5893cab19a8ae6b311df710f87256f7cdd6eb8","abstract_canon_sha256":"b2dc7b3bbf0d8451fbcebef99412778f3c390d8549dbd82c2df7e74b99a43b11"},"schema_version":"1.0"},"canonical_sha256":"312c129cd2a6cb361fd31353ff5bf1a1d769cb2f8e0ffb82a6eabca5c65ebd08","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:49.779978Z","signature_b64":"wWIEJpX9T0MmTfd43X1O1rvRAs51YYDNYjHQgP0T7H4sv1ExVbIiVdAXxSQ4FZORKw+CQ/GaHUC1lsbn4VSiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"312c129cd2a6cb361fd31353ff5bf1a1d769cb2f8e0ffb82a6eabca5c65ebd08","last_reissued_at":"2026-07-05T11:28:49.779497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:49.779497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.23051","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":"2026-07-05T11:28:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZL7cXxaKaU0yAmeeNNUTjYbZOdWqunhqtPBPV1jiLwprsmX5+3u+jYewvJaBRAo9a0ozyIi1AW3WZPDhq3w1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:39:46.151155Z"},"content_sha256":"3c3bdd108304e8070682d4816806a85330a3216680b8000b7b1016d565976c62","schema_version":"1.0","event_id":"sha256:3c3bdd108304e8070682d4816806a85330a3216680b8000b7b1016d565976c62"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GEWBFHGSU3FTMH6TCNJ76W7RUH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MariNER: A Dataset for Historical Brazilian Portuguese Named Entity Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Diego Furtado Silva, Jade Bortot de Paiva, Jo\\~ao Lucas Luz Lima Sarcinelli, Marina Lages Gon\\c{c}alves Teixeira","submitted_at":"2025-06-29T01:23:57Z","abstract_excerpt":"Named Entity Recognition (NER) is a fundamental Natural Language Processing (NLP) task that aims to identify and classify entity mentions in texts across different categories. While languages such as English possess a large number of high-quality resources for this task, Brazilian Portuguese still lacks in quantity of gold-standard NER datasets, especially when considering specific domains. Particularly, this paper considers the importance of NER for analyzing historical texts in the context of digital humanities. To address this gap, this work outlines the construction of MariNER: \\textit{Map"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23051","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/2506.23051/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":"2026-07-05T11:28:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C/kmuwWIHc7VDraIZ/toRZTwvJVCbk903SFsO0CUZ3Ox26cD54AWl+aQ2sZ1bRNVV6HI0DwlDdLY8TFiaQ8gAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:39:46.151649Z"},"content_sha256":"6f061d55856284fff919ae25324bf1b9c96c85a8013fe1881663ff1ecdf6776b","schema_version":"1.0","event_id":"sha256:6f061d55856284fff919ae25324bf1b9c96c85a8013fe1881663ff1ecdf6776b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GEWBFHGSU3FTMH6TCNJ76W7RUH/bundle.json","state_url":"https://pith.science/pith/GEWBFHGSU3FTMH6TCNJ76W7RUH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GEWBFHGSU3FTMH6TCNJ76W7RUH/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":"2026-08-09T21:39:46Z","links":{"resolver":"https://pith.science/pith/GEWBFHGSU3FTMH6TCNJ76W7RUH","bundle":"https://pith.science/pith/GEWBFHGSU3FTMH6TCNJ76W7RUH/bundle.json","state":"https://pith.science/pith/GEWBFHGSU3FTMH6TCNJ76W7RUH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GEWBFHGSU3FTMH6TCNJ76W7RUH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GEWBFHGSU3FTMH6TCNJ76W7RUH","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":"b2dc7b3bbf0d8451fbcebef99412778f3c390d8549dbd82c2df7e74b99a43b11","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-29T01:23:57Z","title_canon_sha256":"fb68737cf0d09af3a30238835a5893cab19a8ae6b311df710f87256f7cdd6eb8"},"schema_version":"1.0","source":{"id":"2506.23051","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23051","created_at":"2026-07-05T11:28:49Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23051v1","created_at":"2026-07-05T11:28:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23051","created_at":"2026-07-05T11:28:49Z"},{"alias_kind":"pith_short_12","alias_value":"GEWBFHGSU3FT","created_at":"2026-07-05T11:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"GEWBFHGSU3FTMH6T","created_at":"2026-07-05T11:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"GEWBFHGS","created_at":"2026-07-05T11:28:49Z"}],"graph_snapshots":[{"event_id":"sha256:6f061d55856284fff919ae25324bf1b9c96c85a8013fe1881663ff1ecdf6776b","target":"graph","created_at":"2026-07-05T11:28:49Z","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/2506.23051/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Named Entity Recognition (NER) is a fundamental Natural Language Processing (NLP) task that aims to identify and classify entity mentions in texts across different categories. While languages such as English possess a large number of high-quality resources for this task, Brazilian Portuguese still lacks in quantity of gold-standard NER datasets, especially when considering specific domains. Particularly, this paper considers the importance of NER for analyzing historical texts in the context of digital humanities. To address this gap, this work outlines the construction of MariNER: \\textit{Map","authors_text":"Diego Furtado Silva, Jade Bortot de Paiva, Jo\\~ao Lucas Luz Lima Sarcinelli, Marina Lages Gon\\c{c}alves Teixeira","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-29T01:23:57Z","title":"MariNER: A Dataset for Historical Brazilian Portuguese Named Entity Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23051","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":"sha256:3c3bdd108304e8070682d4816806a85330a3216680b8000b7b1016d565976c62","target":"record","created_at":"2026-07-05T11:28:49Z","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":"b2dc7b3bbf0d8451fbcebef99412778f3c390d8549dbd82c2df7e74b99a43b11","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-29T01:23:57Z","title_canon_sha256":"fb68737cf0d09af3a30238835a5893cab19a8ae6b311df710f87256f7cdd6eb8"},"schema_version":"1.0","source":{"id":"2506.23051","kind":"arxiv","version":1}},"canonical_sha256":"312c129cd2a6cb361fd31353ff5bf1a1d769cb2f8e0ffb82a6eabca5c65ebd08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"312c129cd2a6cb361fd31353ff5bf1a1d769cb2f8e0ffb82a6eabca5c65ebd08","first_computed_at":"2026-07-05T11:28:49.779497Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:49.779497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wWIEJpX9T0MmTfd43X1O1rvRAs51YYDNYjHQgP0T7H4sv1ExVbIiVdAXxSQ4FZORKw+CQ/GaHUC1lsbn4VSiBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:49.779978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23051","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c3bdd108304e8070682d4816806a85330a3216680b8000b7b1016d565976c62","sha256:6f061d55856284fff919ae25324bf1b9c96c85a8013fe1881663ff1ecdf6776b"],"state_sha256":"a0d04a7b9fc42b1a1be016e0b0913aab450c03ce3992868f94c92ec04049655c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tS+FpYe0anAj00L+Kl2PtVy2IX3r5oEabIyNtXHO51pnpHVhgc5LUxTHxOz2t4YuzowzQ/Pmj0aepfs9kMrpBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T21:39:46.155673Z","bundle_sha256":"a68cf77890aea18014c869c7c2831fb351ffd4edaefda66626fa3767c488c981"}}