{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:JIFMNQJPF6HX3XLI2AF34RIX7L","short_pith_number":"pith:JIFMNQJP","canonical_record":{"source":{"id":"1710.00803","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-02T17:18:37Z","cross_cats_sorted":[],"title_canon_sha256":"ab088c9685988a76c161ec5cad215456aab956ed8684732e8a8bd539cc3ddc4e","abstract_canon_sha256":"e5e4b44a97b99790ee253185ef79ae2812d54ba0575a0a8bf61a0ef1b3ab651f"},"schema_version":"1.0"},"canonical_sha256":"4a0ac6c12f2f8f7ddd68d00bbe4517facd14c4af92a0d6f4545069cbf5ad8b46","source":{"kind":"arxiv","id":"1710.00803","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.00803","created_at":"2026-05-18T00:33:53Z"},{"alias_kind":"arxiv_version","alias_value":"1710.00803v1","created_at":"2026-05-18T00:33:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.00803","created_at":"2026-05-18T00:33:53Z"},{"alias_kind":"pith_short_12","alias_value":"JIFMNQJPF6HX","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"JIFMNQJPF6HX3XLI","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"JIFMNQJP","created_at":"2026-05-18T12:31:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:JIFMNQJPF6HX3XLI2AF34RIX7L","target":"record","payload":{"canonical_record":{"source":{"id":"1710.00803","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-02T17:18:37Z","cross_cats_sorted":[],"title_canon_sha256":"ab088c9685988a76c161ec5cad215456aab956ed8684732e8a8bd539cc3ddc4e","abstract_canon_sha256":"e5e4b44a97b99790ee253185ef79ae2812d54ba0575a0a8bf61a0ef1b3ab651f"},"schema_version":"1.0"},"canonical_sha256":"4a0ac6c12f2f8f7ddd68d00bbe4517facd14c4af92a0d6f4545069cbf5ad8b46","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:53.738069Z","signature_b64":"rW3m626oHNEbpNhgnl/CXib7OPSmDSgLYfLZEtXi+1u7H4V8gKr98SMr1FXw5TCe1KKawAVXFCk41wKwdlFyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a0ac6c12f2f8f7ddd68d00bbe4517facd14c4af92a0d6f4545069cbf5ad8b46","last_reissued_at":"2026-05-18T00:33:53.737446Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:53.737446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.00803","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":"2026-05-18T00:33:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q8A3j5LOV7ctfIJw36LVgBfoimlkjC/waVsmn45BVMOPyN/276RYJB/rCTeLNw7ywGS/bLQfnjPkNCPExpFKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:13:45.588498Z"},"content_sha256":"437d4180402e9d51349d77c0a23d6e5737b2b056be73b51f587c05fb7a7c093c","schema_version":"1.0","event_id":"sha256:437d4180402e9d51349d77c0a23d6e5737b2b056be73b51f587c05fb7a7c093c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:JIFMNQJPF6HX3XLI2AF34RIX7L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compiling and Processing Historical and Contemporary Portuguese Corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Marcos Zampieri","submitted_at":"2017-10-02T17:18:37Z","abstract_excerpt":"This technical report describes the framework used for processing three large Portuguese corpora. Two corpora contain texts from newspapers, one published in Brazil and the other published in Portugal. The third corpus is Colonia, a historical Portuguese collection containing texts written between the 16th and the early 20th century. The report presents pre-processing methods, segmentation, and annotation of the corpora as well as indexing and querying methods. Finally, it presents published research papers using the corpora."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.00803","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":""},"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":"2026-05-18T00:33:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fpDnDeDnwKUOR4gVmcYpFCJuYlC0tnp+GhAZui1TvBgs4eHKHhAgZ6LQNkaNlctSasFO6r75hjEn2SHrfWV7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:13:45.589168Z"},"content_sha256":"13fb7ccc3fb1de0f82ba1927f9e265f763369d6751df18f011888968ecd6157b","schema_version":"1.0","event_id":"sha256:13fb7ccc3fb1de0f82ba1927f9e265f763369d6751df18f011888968ecd6157b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JIFMNQJPF6HX3XLI2AF34RIX7L/bundle.json","state_url":"https://pith.science/pith/JIFMNQJPF6HX3XLI2AF34RIX7L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JIFMNQJPF6HX3XLI2AF34RIX7L/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":"2026-06-07T14:13:45Z","links":{"resolver":"https://pith.science/pith/JIFMNQJPF6HX3XLI2AF34RIX7L","bundle":"https://pith.science/pith/JIFMNQJPF6HX3XLI2AF34RIX7L/bundle.json","state":"https://pith.science/pith/JIFMNQJPF6HX3XLI2AF34RIX7L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JIFMNQJPF6HX3XLI2AF34RIX7L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:JIFMNQJPF6HX3XLI2AF34RIX7L","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":"e5e4b44a97b99790ee253185ef79ae2812d54ba0575a0a8bf61a0ef1b3ab651f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-02T17:18:37Z","title_canon_sha256":"ab088c9685988a76c161ec5cad215456aab956ed8684732e8a8bd539cc3ddc4e"},"schema_version":"1.0","source":{"id":"1710.00803","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.00803","created_at":"2026-05-18T00:33:53Z"},{"alias_kind":"arxiv_version","alias_value":"1710.00803v1","created_at":"2026-05-18T00:33:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.00803","created_at":"2026-05-18T00:33:53Z"},{"alias_kind":"pith_short_12","alias_value":"JIFMNQJPF6HX","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"JIFMNQJPF6HX3XLI","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"JIFMNQJP","created_at":"2026-05-18T12:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:13fb7ccc3fb1de0f82ba1927f9e265f763369d6751df18f011888968ecd6157b","target":"graph","created_at":"2026-05-18T00:33:53Z","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"},"paper":{"abstract_excerpt":"This technical report describes the framework used for processing three large Portuguese corpora. Two corpora contain texts from newspapers, one published in Brazil and the other published in Portugal. The third corpus is Colonia, a historical Portuguese collection containing texts written between the 16th and the early 20th century. The report presents pre-processing methods, segmentation, and annotation of the corpora as well as indexing and querying methods. Finally, it presents published research papers using the corpora.","authors_text":"Marcos Zampieri","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-02T17:18:37Z","title":"Compiling and Processing Historical and Contemporary Portuguese Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.00803","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":"sha256:437d4180402e9d51349d77c0a23d6e5737b2b056be73b51f587c05fb7a7c093c","target":"record","created_at":"2026-05-18T00:33:53Z","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":"e5e4b44a97b99790ee253185ef79ae2812d54ba0575a0a8bf61a0ef1b3ab651f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-02T17:18:37Z","title_canon_sha256":"ab088c9685988a76c161ec5cad215456aab956ed8684732e8a8bd539cc3ddc4e"},"schema_version":"1.0","source":{"id":"1710.00803","kind":"arxiv","version":1}},"canonical_sha256":"4a0ac6c12f2f8f7ddd68d00bbe4517facd14c4af92a0d6f4545069cbf5ad8b46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a0ac6c12f2f8f7ddd68d00bbe4517facd14c4af92a0d6f4545069cbf5ad8b46","first_computed_at":"2026-05-18T00:33:53.737446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:33:53.737446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rW3m626oHNEbpNhgnl/CXib7OPSmDSgLYfLZEtXi+1u7H4V8gKr98SMr1FXw5TCe1KKawAVXFCk41wKwdlFyDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:33:53.738069Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.00803","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:437d4180402e9d51349d77c0a23d6e5737b2b056be73b51f587c05fb7a7c093c","sha256:13fb7ccc3fb1de0f82ba1927f9e265f763369d6751df18f011888968ecd6157b"],"state_sha256":"f6e474f4aae11d6795bb3d24771d414eff9ea05827ea4d44b7f4ebff0e4fd22f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tTVT7zWaQQHQaPE11ukVbQj/0jYZkpm6Iya0lIsCdwXRvgVViLihDKGz8Up1xKNlXfTo9RF2O85M+Pnn05DUCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T14:13:45.591680Z","bundle_sha256":"c647be160ef236a22e38701321893aa41439708d4da604e71323c884758bee27"}}