{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WC5MQ4BIEQ5GFFOZVQWA4AMTD4","short_pith_number":"pith:WC5MQ4BI","canonical_record":{"source":{"id":"1805.07697","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-20T03:42:50Z","cross_cats_sorted":[],"title_canon_sha256":"bd0b0b1ae8a21aa180d1ad5008691fd4d608969f94c5164f6e29c9c8b729eb1a","abstract_canon_sha256":"3a0f5adb823d31fffc71aed8deab43f3e72a23608ac514403a41b008b0f303c9"},"schema_version":"1.0"},"canonical_sha256":"b0bac87028243a6295d9ac2c0e01931f17a349a31a2332570ec2b0a5960fe002","source":{"kind":"arxiv","id":"1805.07697","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07697","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07697v1","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07697","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"pith_short_12","alias_value":"WC5MQ4BIEQ5G","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WC5MQ4BIEQ5GFFOZ","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WC5MQ4BI","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WC5MQ4BIEQ5GFFOZVQWA4AMTD4","target":"record","payload":{"canonical_record":{"source":{"id":"1805.07697","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-20T03:42:50Z","cross_cats_sorted":[],"title_canon_sha256":"bd0b0b1ae8a21aa180d1ad5008691fd4d608969f94c5164f6e29c9c8b729eb1a","abstract_canon_sha256":"3a0f5adb823d31fffc71aed8deab43f3e72a23608ac514403a41b008b0f303c9"},"schema_version":"1.0"},"canonical_sha256":"b0bac87028243a6295d9ac2c0e01931f17a349a31a2332570ec2b0a5960fe002","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:32.802812Z","signature_b64":"amaE3Yj02wHED+/kBeNjYnjWF2wconRf63YkSAbjRYaW5dwS+lurE7J0r0zCI0YV4fS5Y8RKWkpbn/VzlkkgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0bac87028243a6295d9ac2c0e01931f17a349a31a2332570ec2b0a5960fe002","last_reissued_at":"2026-05-18T00:15:32.802263Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:32.802263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.07697","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":"2026-05-18T00:15:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dlt6dC/S6pXABWzNMderFepL0GkYdj0lDeu0akAoBFyPFa1bkHZN+BqOZlxDFngfDUfPMljpc4uNi1kpYitbDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T13:40:46.515084Z"},"content_sha256":"f736530084d14451c813312868871058bd378a9f1770ef35db97e238e1fe867a","schema_version":"1.0","event_id":"sha256:f736530084d14451c813312868871058bd378a9f1770ef35db97e238e1fe867a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WC5MQ4BIEQ5GFFOZVQWA4AMTD4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The UN Parallel Corpus Annotated for Translation Direction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Elad Tolochinsky, Ella Rabinovich, Ohad Mosafi, Shuly Wintner","submitted_at":"2018-05-20T03:42:50Z","abstract_excerpt":"This work distinguishes between translated and original text in the UN protocol corpus. By modeling the problem as classification problem, we can achieve up to 95% classification accuracy. We begin by deriving a parallel corpus for different language-pairs annotated for translation direction, and then classify the data by using various feature extraction methods. We compare the different methods as well as the ability to distinguish between translated and original texts in the different languages. The annotated corpus is publicly available."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07697","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":"2026-05-18T00:15:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZuNJosOMoBJJ9M8V14z4mDOmuMiO+H+iW2s2ArKROuFG9yzp/nLQUWSPrSI5FegWbBtzXvBwl94m0Q1HwstcAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T13:40:46.515441Z"},"content_sha256":"c2be68466140bf451c53c2665cbed92f6a8df7d4600e24342a94613fd34ab873","schema_version":"1.0","event_id":"sha256:c2be68466140bf451c53c2665cbed92f6a8df7d4600e24342a94613fd34ab873"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WC5MQ4BIEQ5GFFOZVQWA4AMTD4/bundle.json","state_url":"https://pith.science/pith/WC5MQ4BIEQ5GFFOZVQWA4AMTD4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WC5MQ4BIEQ5GFFOZVQWA4AMTD4/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":"2026-07-04T13:40:46Z","links":{"resolver":"https://pith.science/pith/WC5MQ4BIEQ5GFFOZVQWA4AMTD4","bundle":"https://pith.science/pith/WC5MQ4BIEQ5GFFOZVQWA4AMTD4/bundle.json","state":"https://pith.science/pith/WC5MQ4BIEQ5GFFOZVQWA4AMTD4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WC5MQ4BIEQ5GFFOZVQWA4AMTD4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WC5MQ4BIEQ5GFFOZVQWA4AMTD4","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":"3a0f5adb823d31fffc71aed8deab43f3e72a23608ac514403a41b008b0f303c9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-20T03:42:50Z","title_canon_sha256":"bd0b0b1ae8a21aa180d1ad5008691fd4d608969f94c5164f6e29c9c8b729eb1a"},"schema_version":"1.0","source":{"id":"1805.07697","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07697","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07697v1","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07697","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"pith_short_12","alias_value":"WC5MQ4BIEQ5G","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WC5MQ4BIEQ5GFFOZ","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WC5MQ4BI","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:c2be68466140bf451c53c2665cbed92f6a8df7d4600e24342a94613fd34ab873","target":"graph","created_at":"2026-05-18T00:15:32Z","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 work distinguishes between translated and original text in the UN protocol corpus. By modeling the problem as classification problem, we can achieve up to 95% classification accuracy. We begin by deriving a parallel corpus for different language-pairs annotated for translation direction, and then classify the data by using various feature extraction methods. We compare the different methods as well as the ability to distinguish between translated and original texts in the different languages. The annotated corpus is publicly available.","authors_text":"Elad Tolochinsky, Ella Rabinovich, Ohad Mosafi, Shuly Wintner","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-20T03:42:50Z","title":"The UN Parallel Corpus Annotated for Translation Direction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07697","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:f736530084d14451c813312868871058bd378a9f1770ef35db97e238e1fe867a","target":"record","created_at":"2026-05-18T00:15:32Z","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":"3a0f5adb823d31fffc71aed8deab43f3e72a23608ac514403a41b008b0f303c9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-20T03:42:50Z","title_canon_sha256":"bd0b0b1ae8a21aa180d1ad5008691fd4d608969f94c5164f6e29c9c8b729eb1a"},"schema_version":"1.0","source":{"id":"1805.07697","kind":"arxiv","version":1}},"canonical_sha256":"b0bac87028243a6295d9ac2c0e01931f17a349a31a2332570ec2b0a5960fe002","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0bac87028243a6295d9ac2c0e01931f17a349a31a2332570ec2b0a5960fe002","first_computed_at":"2026-05-18T00:15:32.802263Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:32.802263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"amaE3Yj02wHED+/kBeNjYnjWF2wconRf63YkSAbjRYaW5dwS+lurE7J0r0zCI0YV4fS5Y8RKWkpbn/VzlkkgDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:32.802812Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.07697","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f736530084d14451c813312868871058bd378a9f1770ef35db97e238e1fe867a","sha256:c2be68466140bf451c53c2665cbed92f6a8df7d4600e24342a94613fd34ab873"],"state_sha256":"e38f9db4b65ce062881ae6c3a6450bc28fb480950291fcf038d8d6fe43fb79f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0lXFUYzogVOYxzMcXx6HVbQoCEqOJiIZ09foBU2reFg80Hf26PYotJDpcP1nFzO1lOg528vBLsZhJqduO0lXAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T13:40:46.517359Z","bundle_sha256":"9c437d6c8bfcd678f42510377d60efa5b6821cc7e47180e6314c57785c2bca20"}}