{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZOBFK5UVZFF4RCOW3TRAXVXLAM","short_pith_number":"pith:ZOBFK5UV","canonical_record":{"source":{"id":"1804.08756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-23T21:56:11Z","cross_cats_sorted":[],"title_canon_sha256":"d88ad948dbc3c6e0bd8b79da8e41767dafc58d6d97a1e71db4710a46e5419cda","abstract_canon_sha256":"3837b607733a8fe6093fd3b53c09e5d027b616e344c247b8cf812a7a9ebb2b98"},"schema_version":"1.0"},"canonical_sha256":"cb82557695c94bc889d6dce20bd6eb0300edf93a241207ea312663f148e67000","source":{"kind":"arxiv","id":"1804.08756","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.08756","created_at":"2026-05-18T00:17:37Z"},{"alias_kind":"arxiv_version","alias_value":"1804.08756v1","created_at":"2026-05-18T00:17:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08756","created_at":"2026-05-18T00:17:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZOBFK5UVZFF4","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZOBFK5UVZFF4RCOW","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZOBFK5UV","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZOBFK5UVZFF4RCOW3TRAXVXLAM","target":"record","payload":{"canonical_record":{"source":{"id":"1804.08756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-23T21:56:11Z","cross_cats_sorted":[],"title_canon_sha256":"d88ad948dbc3c6e0bd8b79da8e41767dafc58d6d97a1e71db4710a46e5419cda","abstract_canon_sha256":"3837b607733a8fe6093fd3b53c09e5d027b616e344c247b8cf812a7a9ebb2b98"},"schema_version":"1.0"},"canonical_sha256":"cb82557695c94bc889d6dce20bd6eb0300edf93a241207ea312663f148e67000","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:37.445052Z","signature_b64":"pJkOBvpiXNbxEspU/zhY6OD2/77LqEiELeUahs9hoq8ZJT6otGMYRynzcihzMKweA8OK03bMd5d3nKFKiosfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb82557695c94bc889d6dce20bd6eb0300edf93a241207ea312663f148e67000","last_reissued_at":"2026-05-18T00:17:37.444208Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:37.444208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.08756","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":"2026-05-18T00:17:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xKfjAUgCQj7vP/pN379RRhCmyJwy043rjgaUvGT2xOI60kw7r4QDy9D+A35eXs+6mb2dv5okBp0ZS1bHNg/ABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:15:18.262424Z"},"content_sha256":"2bdd312a6ffb4b48f075661cdccbb910d3f112f1503501f5e615c9bbc7690440","schema_version":"1.0","event_id":"sha256:2bdd312a6ffb4b48f075661cdccbb910d3f112f1503501f5e615c9bbc7690440"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZOBFK5UVZFF4RCOW3TRAXVXLAM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Detecting Syntactic Features of Translated Chinese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Hu, Sandra K\\\"ubler, Wen Li","submitted_at":"2018-04-23T21:56:11Z","abstract_excerpt":"We present a machine learning approach to distinguish texts translated to Chinese (by humans) from texts originally written in Chinese, with a focus on a wide range of syntactic features. Using Support Vector Machines (SVMs) as classifier on a genre-balanced corpus in translation studies of Chinese, we find that constituent parse trees and dependency triples as features without lexical information perform very well on the task, with an F-measure above 90%, close to the results of lexical n-gram features, without the risk of learning topic information rather than translation features. Thus, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08756","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":"2026-05-18T00:17:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MvLObwYWTLbt3XxUT9uI1038fnfta8bczb+Eb14FUEFeM6GQWOs+ofxeVX9STDtw5bG6c4pFznnlFoJ44DlVDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:15:18.262779Z"},"content_sha256":"601efbbbba3f331d7569f1ffa3a7c6f85c421ad9fe05cc6000a3b850e5609c7c","schema_version":"1.0","event_id":"sha256:601efbbbba3f331d7569f1ffa3a7c6f85c421ad9fe05cc6000a3b850e5609c7c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZOBFK5UVZFF4RCOW3TRAXVXLAM/bundle.json","state_url":"https://pith.science/pith/ZOBFK5UVZFF4RCOW3TRAXVXLAM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZOBFK5UVZFF4RCOW3TRAXVXLAM/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":"2026-05-30T11:15:18Z","links":{"resolver":"https://pith.science/pith/ZOBFK5UVZFF4RCOW3TRAXVXLAM","bundle":"https://pith.science/pith/ZOBFK5UVZFF4RCOW3TRAXVXLAM/bundle.json","state":"https://pith.science/pith/ZOBFK5UVZFF4RCOW3TRAXVXLAM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZOBFK5UVZFF4RCOW3TRAXVXLAM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZOBFK5UVZFF4RCOW3TRAXVXLAM","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":"3837b607733a8fe6093fd3b53c09e5d027b616e344c247b8cf812a7a9ebb2b98","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-23T21:56:11Z","title_canon_sha256":"d88ad948dbc3c6e0bd8b79da8e41767dafc58d6d97a1e71db4710a46e5419cda"},"schema_version":"1.0","source":{"id":"1804.08756","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.08756","created_at":"2026-05-18T00:17:37Z"},{"alias_kind":"arxiv_version","alias_value":"1804.08756v1","created_at":"2026-05-18T00:17:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08756","created_at":"2026-05-18T00:17:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZOBFK5UVZFF4","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZOBFK5UVZFF4RCOW","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZOBFK5UV","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:601efbbbba3f331d7569f1ffa3a7c6f85c421ad9fe05cc6000a3b850e5609c7c","target":"graph","created_at":"2026-05-18T00:17:37Z","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":"We present a machine learning approach to distinguish texts translated to Chinese (by humans) from texts originally written in Chinese, with a focus on a wide range of syntactic features. Using Support Vector Machines (SVMs) as classifier on a genre-balanced corpus in translation studies of Chinese, we find that constituent parse trees and dependency triples as features without lexical information perform very well on the task, with an F-measure above 90%, close to the results of lexical n-gram features, without the risk of learning topic information rather than translation features. Thus, we ","authors_text":"Hai Hu, Sandra K\\\"ubler, Wen Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-23T21:56:11Z","title":"Detecting Syntactic Features of Translated Chinese"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08756","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":"sha256:2bdd312a6ffb4b48f075661cdccbb910d3f112f1503501f5e615c9bbc7690440","target":"record","created_at":"2026-05-18T00:17:37Z","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":"3837b607733a8fe6093fd3b53c09e5d027b616e344c247b8cf812a7a9ebb2b98","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-23T21:56:11Z","title_canon_sha256":"d88ad948dbc3c6e0bd8b79da8e41767dafc58d6d97a1e71db4710a46e5419cda"},"schema_version":"1.0","source":{"id":"1804.08756","kind":"arxiv","version":1}},"canonical_sha256":"cb82557695c94bc889d6dce20bd6eb0300edf93a241207ea312663f148e67000","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb82557695c94bc889d6dce20bd6eb0300edf93a241207ea312663f148e67000","first_computed_at":"2026-05-18T00:17:37.444208Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:37.444208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pJkOBvpiXNbxEspU/zhY6OD2/77LqEiELeUahs9hoq8ZJT6otGMYRynzcihzMKweA8OK03bMd5d3nKFKiosfDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:37.445052Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.08756","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bdd312a6ffb4b48f075661cdccbb910d3f112f1503501f5e615c9bbc7690440","sha256:601efbbbba3f331d7569f1ffa3a7c6f85c421ad9fe05cc6000a3b850e5609c7c"],"state_sha256":"5d5e140ef55278c49ccc54184f1e92a9d289059d6e54e4c691279f48b0e0dacf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lu6j5MniGiT5Hi85buBflHpOpJsni1iw4QpRHjKmrr7Mo+YsViy5aSCKIjh31FWq61pvxALh2bK9F0d5ZG0pDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T11:15:18.266509Z","bundle_sha256":"b58c6830e8b7e317450f75a06281b6c4152a70bc439106992683f332c4d6db37"}}