{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XKPRBHEAWLFQHOZTC7EZHSNSNR","short_pith_number":"pith:XKPRBHEA","canonical_record":{"source":{"id":"1801.07779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-01-23T21:40:53Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d1482c9166ce0cbaec55a6c1e88ec499700e620826dab697320f306a84df6c02","abstract_canon_sha256":"5487e607f9f5bbdffb79823a0d044db84b2a59ff36f42b9882def6f7a04907cb"},"schema_version":"1.0"},"canonical_sha256":"ba9f109c80b2cb03bb3317c993c9b26c66debfaff94d36d3e944d3efbf7afb04","source":{"kind":"arxiv","id":"1801.07779","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.07779","created_at":"2026-05-18T00:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"1801.07779v1","created_at":"2026-05-18T00:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07779","created_at":"2026-05-18T00:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"XKPRBHEAWLFQ","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XKPRBHEAWLFQHOZT","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XKPRBHEA","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XKPRBHEAWLFQHOZTC7EZHSNSNR","target":"record","payload":{"canonical_record":{"source":{"id":"1801.07779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-01-23T21:40:53Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d1482c9166ce0cbaec55a6c1e88ec499700e620826dab697320f306a84df6c02","abstract_canon_sha256":"5487e607f9f5bbdffb79823a0d044db84b2a59ff36f42b9882def6f7a04907cb"},"schema_version":"1.0"},"canonical_sha256":"ba9f109c80b2cb03bb3317c993c9b26c66debfaff94d36d3e944d3efbf7afb04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:10.882669Z","signature_b64":"HIClHtzNlo6fSFS76F7U57Gs+OB9dhorNAQ4h8gBx3WRneaMXHOqsLz7lT+sUVH6WFNiVTgF74zTJ/gtrpfXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba9f109c80b2cb03bb3317c993c9b26c66debfaff94d36d3e944d3efbf7afb04","last_reissued_at":"2026-05-18T00:25:10.881992Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:10.881992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.07779","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":"2026-05-18T00:25:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QF9tqLWToZem5nH2mebL0LF+D4p0S2TqygnarO8v+ejBzk819Nu+wWJ68wlFQT3VNNX1mObimxLWErWqFqrvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:51:27.405585Z"},"content_sha256":"f230c87d3dec60dc76fee29f0b12188f43b8fdbea09509b991f3853ff9da7b08","schema_version":"1.0","event_id":"sha256:f230c87d3dec60dc76fee29f0b12188f43b8fdbea09509b991f3853ff9da7b08"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XKPRBHEAWLFQHOZTC7EZHSNSNR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The WiLI benchmark dataset for written language identification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Martin Thoma","submitted_at":"2018-01-23T21:40:53Z","abstract_excerpt":"This paper describes the WiLI-2018 benchmark dataset for monolingual written natural language identification. WiLI-2018 is a publicly available, free of charge dataset of short text extracts from Wikipedia. It contains 1000 paragraphs of 235 languages, totaling in 23500 paragraphs. WiLI is a classification dataset: Given an unknown paragraph written in one dominant language, it has to be decided which language it is."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07779","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":"2026-05-18T00:25:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f82pmIEsm3O8lm0lAc3cbs9w86HNVHPX2MckY8zNGCTeIbqz+V0RSQ2nYHpQR1WYta6BJUCp5EZZZiWfqdVgDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:51:27.406183Z"},"content_sha256":"95d151beea9565ed2a1bd8a9affcba875819fa81642e53c26f41d4550d2de6c2","schema_version":"1.0","event_id":"sha256:95d151beea9565ed2a1bd8a9affcba875819fa81642e53c26f41d4550d2de6c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XKPRBHEAWLFQHOZTC7EZHSNSNR/bundle.json","state_url":"https://pith.science/pith/XKPRBHEAWLFQHOZTC7EZHSNSNR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XKPRBHEAWLFQHOZTC7EZHSNSNR/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":"2026-05-27T07:51:27Z","links":{"resolver":"https://pith.science/pith/XKPRBHEAWLFQHOZTC7EZHSNSNR","bundle":"https://pith.science/pith/XKPRBHEAWLFQHOZTC7EZHSNSNR/bundle.json","state":"https://pith.science/pith/XKPRBHEAWLFQHOZTC7EZHSNSNR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XKPRBHEAWLFQHOZTC7EZHSNSNR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XKPRBHEAWLFQHOZTC7EZHSNSNR","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":"5487e607f9f5bbdffb79823a0d044db84b2a59ff36f42b9882def6f7a04907cb","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-01-23T21:40:53Z","title_canon_sha256":"d1482c9166ce0cbaec55a6c1e88ec499700e620826dab697320f306a84df6c02"},"schema_version":"1.0","source":{"id":"1801.07779","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.07779","created_at":"2026-05-18T00:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"1801.07779v1","created_at":"2026-05-18T00:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07779","created_at":"2026-05-18T00:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"XKPRBHEAWLFQ","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XKPRBHEAWLFQHOZT","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XKPRBHEA","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:95d151beea9565ed2a1bd8a9affcba875819fa81642e53c26f41d4550d2de6c2","target":"graph","created_at":"2026-05-18T00:25:10Z","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 paper describes the WiLI-2018 benchmark dataset for monolingual written natural language identification. WiLI-2018 is a publicly available, free of charge dataset of short text extracts from Wikipedia. It contains 1000 paragraphs of 235 languages, totaling in 23500 paragraphs. WiLI is a classification dataset: Given an unknown paragraph written in one dominant language, it has to be decided which language it is.","authors_text":"Martin Thoma","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-01-23T21:40:53Z","title":"The WiLI benchmark dataset for written language identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07779","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:f230c87d3dec60dc76fee29f0b12188f43b8fdbea09509b991f3853ff9da7b08","target":"record","created_at":"2026-05-18T00:25:10Z","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":"5487e607f9f5bbdffb79823a0d044db84b2a59ff36f42b9882def6f7a04907cb","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-01-23T21:40:53Z","title_canon_sha256":"d1482c9166ce0cbaec55a6c1e88ec499700e620826dab697320f306a84df6c02"},"schema_version":"1.0","source":{"id":"1801.07779","kind":"arxiv","version":1}},"canonical_sha256":"ba9f109c80b2cb03bb3317c993c9b26c66debfaff94d36d3e944d3efbf7afb04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba9f109c80b2cb03bb3317c993c9b26c66debfaff94d36d3e944d3efbf7afb04","first_computed_at":"2026-05-18T00:25:10.881992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:25:10.881992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HIClHtzNlo6fSFS76F7U57Gs+OB9dhorNAQ4h8gBx3WRneaMXHOqsLz7lT+sUVH6WFNiVTgF74zTJ/gtrpfXAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:25:10.882669Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.07779","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f230c87d3dec60dc76fee29f0b12188f43b8fdbea09509b991f3853ff9da7b08","sha256:95d151beea9565ed2a1bd8a9affcba875819fa81642e53c26f41d4550d2de6c2"],"state_sha256":"75ebf738c14920118c94c3b49bcfcbfe8aadc5361e2940458798706bbb4b4ec4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3Gs2iCjxbYUcEsznPv+QuHdYmXCM+t9e+yl2q0kLyBCoewIU2MbAMSDqQxUOWFHGl2U5TVBLDOndg3M9iy+PBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T07:51:27.409892Z","bundle_sha256":"93efab9a94bc926ec309aeabc0290378aa3af5adaab1e370573d5dba9baf41dc"}}