{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LSNYZ647IKLXPRUWGYZTL5B3JR","short_pith_number":"pith:LSNYZ647","canonical_record":{"source":{"id":"1804.11346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-30T17:52:28Z","cross_cats_sorted":[],"title_canon_sha256":"92ea1803d0dd2b00069e1461372564f012e2b626f42e6860990dd9f1ebe21baf","abstract_canon_sha256":"c6860813b37cac754e85a506d61c8daef8a05815d18b20a1151cee35f3716be5"},"schema_version":"1.0"},"canonical_sha256":"5c9b8cfb9f429777c696363335f43b4c4a56c05f61cc4b7466dc077a6781225c","source":{"kind":"arxiv","id":"1804.11346","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.11346","created_at":"2026-05-18T00:17:13Z"},{"alias_kind":"arxiv_version","alias_value":"1804.11346v1","created_at":"2026-05-18T00:17:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.11346","created_at":"2026-05-18T00:17:13Z"},{"alias_kind":"pith_short_12","alias_value":"LSNYZ647IKLX","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LSNYZ647IKLXPRUW","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LSNYZ647","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LSNYZ647IKLXPRUWGYZTL5B3JR","target":"record","payload":{"canonical_record":{"source":{"id":"1804.11346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-30T17:52:28Z","cross_cats_sorted":[],"title_canon_sha256":"92ea1803d0dd2b00069e1461372564f012e2b626f42e6860990dd9f1ebe21baf","abstract_canon_sha256":"c6860813b37cac754e85a506d61c8daef8a05815d18b20a1151cee35f3716be5"},"schema_version":"1.0"},"canonical_sha256":"5c9b8cfb9f429777c696363335f43b4c4a56c05f61cc4b7466dc077a6781225c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:13.949078Z","signature_b64":"ch3hc0qaAtEb8KO83caGoQUWBObgvi5PeKCwQj2y63IROB5SOAeBaF1slIhWukygM9hD3qKYHMAfJBYXcw3hCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c9b8cfb9f429777c696363335f43b4c4a56c05f61cc4b7466dc077a6781225c","last_reissued_at":"2026-05-18T00:17:13.948436Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:13.948436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.11346","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":"2026-05-18T00:17:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oxMdflP0zp0W2ovxp0S2rngnVc4x/nbBi2IMWTdFGwmWxVvpFg5H/4ecSDif8ZpV7ZcMhxWFKHC5J07ODFMQDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T23:58:17.146154Z"},"content_sha256":"18b216c41b5760f70906a0e514ed169723d6221b871798f6e081afb725c239a8","schema_version":"1.0","event_id":"sha256:18b216c41b5760f70906a0e514ed169723d6221b871798f6e081afb725c239a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LSNYZ647IKLXPRUWGYZTL5B3JR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Portuguese Native Language Identification Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iria del R\\'io, Marcos Zampieri, Shervin Malmasi","submitted_at":"2018-04-30T17:52:28Z","abstract_excerpt":"In this paper we present NLI-PT, the first Portuguese dataset compiled for Native Language Identification (NLI), the task of identifying an author's first language based on their second language writing. The dataset includes 1,868 student essays written by learners of European Portuguese, native speakers of the following L1s: Chinese, English, Spanish, German, Russian, French, Japanese, Italian, Dutch, Tetum, Arabic, Polish, Korean, Romanian, and Swedish. NLI-PT includes the original student text and four different types of annotation: POS, fine-grained POS, constituency parses, and dependency"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.11346","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":"2026-05-18T00:17:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WHjlv06tGjk8BwIQV93lHLVPh2rvofpG0OZ6FbZXn8zYZ9pczrXLeI8D8Px+Zu24dqf7S2kzSeVFW4l+MFB9Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T23:58:17.146652Z"},"content_sha256":"fbb551663576acdff8c34546f7609bfb202fcfff08c268c5a0a653eabea88c54","schema_version":"1.0","event_id":"sha256:fbb551663576acdff8c34546f7609bfb202fcfff08c268c5a0a653eabea88c54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LSNYZ647IKLXPRUWGYZTL5B3JR/bundle.json","state_url":"https://pith.science/pith/LSNYZ647IKLXPRUWGYZTL5B3JR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LSNYZ647IKLXPRUWGYZTL5B3JR/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":"2026-06-07T23:58:17Z","links":{"resolver":"https://pith.science/pith/LSNYZ647IKLXPRUWGYZTL5B3JR","bundle":"https://pith.science/pith/LSNYZ647IKLXPRUWGYZTL5B3JR/bundle.json","state":"https://pith.science/pith/LSNYZ647IKLXPRUWGYZTL5B3JR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LSNYZ647IKLXPRUWGYZTL5B3JR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LSNYZ647IKLXPRUWGYZTL5B3JR","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":"c6860813b37cac754e85a506d61c8daef8a05815d18b20a1151cee35f3716be5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-30T17:52:28Z","title_canon_sha256":"92ea1803d0dd2b00069e1461372564f012e2b626f42e6860990dd9f1ebe21baf"},"schema_version":"1.0","source":{"id":"1804.11346","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.11346","created_at":"2026-05-18T00:17:13Z"},{"alias_kind":"arxiv_version","alias_value":"1804.11346v1","created_at":"2026-05-18T00:17:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.11346","created_at":"2026-05-18T00:17:13Z"},{"alias_kind":"pith_short_12","alias_value":"LSNYZ647IKLX","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LSNYZ647IKLXPRUW","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LSNYZ647","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:fbb551663576acdff8c34546f7609bfb202fcfff08c268c5a0a653eabea88c54","target":"graph","created_at":"2026-05-18T00:17:13Z","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":"In this paper we present NLI-PT, the first Portuguese dataset compiled for Native Language Identification (NLI), the task of identifying an author's first language based on their second language writing. The dataset includes 1,868 student essays written by learners of European Portuguese, native speakers of the following L1s: Chinese, English, Spanish, German, Russian, French, Japanese, Italian, Dutch, Tetum, Arabic, Polish, Korean, Romanian, and Swedish. NLI-PT includes the original student text and four different types of annotation: POS, fine-grained POS, constituency parses, and dependency","authors_text":"Iria del R\\'io, Marcos Zampieri, Shervin Malmasi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-30T17:52:28Z","title":"A Portuguese Native Language Identification Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.11346","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":"sha256:18b216c41b5760f70906a0e514ed169723d6221b871798f6e081afb725c239a8","target":"record","created_at":"2026-05-18T00:17:13Z","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":"c6860813b37cac754e85a506d61c8daef8a05815d18b20a1151cee35f3716be5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-30T17:52:28Z","title_canon_sha256":"92ea1803d0dd2b00069e1461372564f012e2b626f42e6860990dd9f1ebe21baf"},"schema_version":"1.0","source":{"id":"1804.11346","kind":"arxiv","version":1}},"canonical_sha256":"5c9b8cfb9f429777c696363335f43b4c4a56c05f61cc4b7466dc077a6781225c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c9b8cfb9f429777c696363335f43b4c4a56c05f61cc4b7466dc077a6781225c","first_computed_at":"2026-05-18T00:17:13.948436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:13.948436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ch3hc0qaAtEb8KO83caGoQUWBObgvi5PeKCwQj2y63IROB5SOAeBaF1slIhWukygM9hD3qKYHMAfJBYXcw3hCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:13.949078Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.11346","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18b216c41b5760f70906a0e514ed169723d6221b871798f6e081afb725c239a8","sha256:fbb551663576acdff8c34546f7609bfb202fcfff08c268c5a0a653eabea88c54"],"state_sha256":"6099c279ce17d1143cc8d51173c817b3b214fe841c6e96de61b842d2bbfa861e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5SEddR+uIPJhz1TJrTulsXe7gb9TEWlBPk+RnushCtcyzt2QvBnV7ZCDb6Kwn495+10QTIYPq/lcrlaBox+rBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T23:58:17.149985Z","bundle_sha256":"5a9953396b387bf08f4258a26a3a9348e1caf6667c9c4ab146619cb08ace57c0"}}