{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:7NFCALNNQGYGUIV4ZO4R25O7T6","short_pith_number":"pith:7NFCALNN","canonical_record":{"source":{"id":"2202.09509","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-19T03:16:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e377dad5813b54254abdf650dfd6a836399382c81b96569c13184be6d12beeff","abstract_canon_sha256":"b82668c1eb0217feb07d31caf17ab5236a8e028475dede0521a466fe6d41970e"},"schema_version":"1.0"},"canonical_sha256":"fb4a202dad81b06a22bccbb91d75df9fa2b0b6aced661004ed42761414de2b47","source":{"kind":"arxiv","id":"2202.09509","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.09509","created_at":"2026-07-05T03:58:23Z"},{"alias_kind":"arxiv_version","alias_value":"2202.09509v1","created_at":"2026-07-05T03:58:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09509","created_at":"2026-07-05T03:58:23Z"},{"alias_kind":"pith_short_12","alias_value":"7NFCALNNQGYG","created_at":"2026-07-05T03:58:23Z"},{"alias_kind":"pith_short_16","alias_value":"7NFCALNNQGYGUIV4","created_at":"2026-07-05T03:58:23Z"},{"alias_kind":"pith_short_8","alias_value":"7NFCALNN","created_at":"2026-07-05T03:58:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:7NFCALNNQGYGUIV4ZO4R25O7T6","target":"record","payload":{"canonical_record":{"source":{"id":"2202.09509","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-19T03:16:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e377dad5813b54254abdf650dfd6a836399382c81b96569c13184be6d12beeff","abstract_canon_sha256":"b82668c1eb0217feb07d31caf17ab5236a8e028475dede0521a466fe6d41970e"},"schema_version":"1.0"},"canonical_sha256":"fb4a202dad81b06a22bccbb91d75df9fa2b0b6aced661004ed42761414de2b47","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:23.236969Z","signature_b64":"QkgXOxaS2+3NMtDOy1MVvsxC7mmlAgjViTPCd8AEHvsqo/7hbKJZ3UMm/EqFN7pJ+YSLbPlNyzXEzzhQtAOFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb4a202dad81b06a22bccbb91d75df9fa2b0b6aced661004ed42761414de2b47","last_reissued_at":"2026-07-05T03:58:23.236500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:23.236500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.09509","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":"2026-07-05T03:58:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pstpXxCnChmC4JeTZQRI1c1wQNOV2anrMEWP0atN5A9wkRIFu/cU+FdRIkN2Kaxhj6whbK5VjoBNfItX8W4wAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:05:37.273823Z"},"content_sha256":"10e5022ba30b99ebc05b96fd2e4026281aac53d768ee140a5481549b6398fa5d","schema_version":"1.0","event_id":"sha256:10e5022ba30b99ebc05b96fd2e4026281aac53d768ee140a5481549b6398fa5d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:7NFCALNNQGYGUIV4ZO4R25O7T6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PETCI: A Parallel English Translation Dataset of Chinese Idioms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Kenan Tang (The University of Chicago)","submitted_at":"2022-02-19T03:16:20Z","abstract_excerpt":"Idioms are an important language phenomenon in Chinese, but idiom translation is notoriously hard. Current machine translation models perform poorly on idiom translation, while idioms are sparse in many translation datasets. We present PETCI, a parallel English translation dataset of Chinese idioms, aiming to improve idiom translation by both human and machine. The dataset is built by leveraging human and machine effort. Baseline generation models show unsatisfactory abilities to improve translation, but structure-aware classification models show good performance on distinguishing good transla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09509","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2202.09509/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T03:58:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jg0IlftpRFLL05o8FnG8xDmLWIM+HwR0PvfYeRrqBIxGnC0KiDbExxJLcO1RHxE6XtU+jls5Cr8En5r4hRGAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:05:37.274322Z"},"content_sha256":"cc54436ca1ca215262f9bed6b024fc53ab21e1bfabe1cfb4ae6dc7d9e058b6bb","schema_version":"1.0","event_id":"sha256:cc54436ca1ca215262f9bed6b024fc53ab21e1bfabe1cfb4ae6dc7d9e058b6bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7NFCALNNQGYGUIV4ZO4R25O7T6/bundle.json","state_url":"https://pith.science/pith/7NFCALNNQGYGUIV4ZO4R25O7T6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7NFCALNNQGYGUIV4ZO4R25O7T6/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":"2026-08-09T09:05:37Z","links":{"resolver":"https://pith.science/pith/7NFCALNNQGYGUIV4ZO4R25O7T6","bundle":"https://pith.science/pith/7NFCALNNQGYGUIV4ZO4R25O7T6/bundle.json","state":"https://pith.science/pith/7NFCALNNQGYGUIV4ZO4R25O7T6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7NFCALNNQGYGUIV4ZO4R25O7T6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7NFCALNNQGYGUIV4ZO4R25O7T6","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":"b82668c1eb0217feb07d31caf17ab5236a8e028475dede0521a466fe6d41970e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-19T03:16:20Z","title_canon_sha256":"e377dad5813b54254abdf650dfd6a836399382c81b96569c13184be6d12beeff"},"schema_version":"1.0","source":{"id":"2202.09509","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.09509","created_at":"2026-07-05T03:58:23Z"},{"alias_kind":"arxiv_version","alias_value":"2202.09509v1","created_at":"2026-07-05T03:58:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09509","created_at":"2026-07-05T03:58:23Z"},{"alias_kind":"pith_short_12","alias_value":"7NFCALNNQGYG","created_at":"2026-07-05T03:58:23Z"},{"alias_kind":"pith_short_16","alias_value":"7NFCALNNQGYGUIV4","created_at":"2026-07-05T03:58:23Z"},{"alias_kind":"pith_short_8","alias_value":"7NFCALNN","created_at":"2026-07-05T03:58:23Z"}],"graph_snapshots":[{"event_id":"sha256:cc54436ca1ca215262f9bed6b024fc53ab21e1bfabe1cfb4ae6dc7d9e058b6bb","target":"graph","created_at":"2026-07-05T03:58:23Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2202.09509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Idioms are an important language phenomenon in Chinese, but idiom translation is notoriously hard. Current machine translation models perform poorly on idiom translation, while idioms are sparse in many translation datasets. We present PETCI, a parallel English translation dataset of Chinese idioms, aiming to improve idiom translation by both human and machine. The dataset is built by leveraging human and machine effort. Baseline generation models show unsatisfactory abilities to improve translation, but structure-aware classification models show good performance on distinguishing good transla","authors_text":"Kenan Tang (The University of Chicago)","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-19T03:16:20Z","title":"PETCI: A Parallel English Translation Dataset of Chinese Idioms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09509","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":"sha256:10e5022ba30b99ebc05b96fd2e4026281aac53d768ee140a5481549b6398fa5d","target":"record","created_at":"2026-07-05T03:58:23Z","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":"b82668c1eb0217feb07d31caf17ab5236a8e028475dede0521a466fe6d41970e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-19T03:16:20Z","title_canon_sha256":"e377dad5813b54254abdf650dfd6a836399382c81b96569c13184be6d12beeff"},"schema_version":"1.0","source":{"id":"2202.09509","kind":"arxiv","version":1}},"canonical_sha256":"fb4a202dad81b06a22bccbb91d75df9fa2b0b6aced661004ed42761414de2b47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb4a202dad81b06a22bccbb91d75df9fa2b0b6aced661004ed42761414de2b47","first_computed_at":"2026-07-05T03:58:23.236500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:58:23.236500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QkgXOxaS2+3NMtDOy1MVvsxC7mmlAgjViTPCd8AEHvsqo/7hbKJZ3UMm/EqFN7pJ+YSLbPlNyzXEzzhQtAOFDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:58:23.236969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.09509","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10e5022ba30b99ebc05b96fd2e4026281aac53d768ee140a5481549b6398fa5d","sha256:cc54436ca1ca215262f9bed6b024fc53ab21e1bfabe1cfb4ae6dc7d9e058b6bb"],"state_sha256":"5fb9d9a31c36a3d888eb5473b43757a3529dcd996bd59fb69501a28e489de585"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VwpCwirnJf1jfwFsLJh40H82smsXVpu+ZOEFvGUz3UXv8oML5Fdgi19U8G965qsn71SdVLbxH60syLbvxCmmAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T09:05:37.278150Z","bundle_sha256":"61c1bacb67d38a967e7142ad69c4a8e2c455b52b46c36123d13d575ceab2c9c4"}}