{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:VGSD73PVEQTHRM4OXGAO4WVUIH","short_pith_number":"pith:VGSD73PV","canonical_record":{"source":{"id":"1906.01265","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-04T08:29:00Z","cross_cats_sorted":[],"title_canon_sha256":"a90cb1a36f0158d4aa6b3771665f4ac369793ee3ba1df777886538bf27b69df3","abstract_canon_sha256":"26e1b239feb4e47113d381800ac52863cd829a83abce47ceb6d9c4d514253fd6"},"schema_version":"1.0"},"canonical_sha256":"a9a43fedf5242678b38eb980ee5ab441c9e2a447b7c6d3ac4a2a479e4c424300","source":{"kind":"arxiv","id":"1906.01265","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.01265","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"arxiv_version","alias_value":"1906.01265v3","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01265","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"pith_short_12","alias_value":"VGSD73PVEQTH","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"pith_short_16","alias_value":"VGSD73PVEQTHRM4O","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"pith_short_8","alias_value":"VGSD73PV","created_at":"2026-07-05T00:35:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:VGSD73PVEQTHRM4OXGAO4WVUIH","target":"record","payload":{"canonical_record":{"source":{"id":"1906.01265","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-04T08:29:00Z","cross_cats_sorted":[],"title_canon_sha256":"a90cb1a36f0158d4aa6b3771665f4ac369793ee3ba1df777886538bf27b69df3","abstract_canon_sha256":"26e1b239feb4e47113d381800ac52863cd829a83abce47ceb6d9c4d514253fd6"},"schema_version":"1.0"},"canonical_sha256":"a9a43fedf5242678b38eb980ee5ab441c9e2a447b7c6d3ac4a2a479e4c424300","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:44.173276Z","signature_b64":"MgpeW5cAPqyL6J9dSUkKf07QCn1XLX8m6o6RL8tE7tRcie3P/d3eehqlfzcyyuQFJV5DBm1p6msGiP1j7bk8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9a43fedf5242678b38eb980ee5ab441c9e2a447b7c6d3ac4a2a479e4c424300","last_reissued_at":"2026-07-05T00:35:44.172855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:44.172855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.01265","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:35:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eHlgAKB3PiXoCrx09eHX6/6htwyRabyxhLlnFSYCG9EOC4bXd8MVEUl7a2U5ZQ0KtswnM5keSa44kyK/MbO/CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:52:16.035914Z"},"content_sha256":"5c734e06a3529c3800f71c514211bb769462fbc6b90069a06c481b4295b3c338","schema_version":"1.0","event_id":"sha256:5c734e06a3529c3800f71c514211bb769462fbc6b90069a06c481b4295b3c338"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:VGSD73PVEQTHRM4OXGAO4WVUIH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ChID: A Large-scale Chinese IDiom Dataset for Cloze Test","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aixin Sun, Chujie Zheng, Minlie Huang","submitted_at":"2019-06-04T08:29:00Z","abstract_excerpt":"Cloze-style reading comprehension in Chinese is still limited due to the lack of various corpora. In this paper we propose a large-scale Chinese cloze test dataset ChID, which studies the comprehension of idiom, a unique language phenomenon in Chinese. In this corpus, the idioms in a passage are replaced by blank symbols and the correct answer needs to be chosen from well-designed candidate idioms. We carefully study how the design of candidate idioms and the representation of idioms affect the performance of state-of-the-art models. Results show that the machine accuracy is substantially wors"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01265","kind":"arxiv","version":3},"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/1906.01265/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":"2026-07-05T00:35:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KtHDp6ak12MhHt46HqvC3n2OelcXd6nMCEZD0gfCCWGa93EPz5KFFzpdCTwJ7GLl3rycUqDRHXw1b8HJaziZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:52:16.036439Z"},"content_sha256":"577e3ffc965e2c4942287eb87e2616d7747b15e4d47bafe6032e8893a17a2c26","schema_version":"1.0","event_id":"sha256:577e3ffc965e2c4942287eb87e2616d7747b15e4d47bafe6032e8893a17a2c26"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VGSD73PVEQTHRM4OXGAO4WVUIH/bundle.json","state_url":"https://pith.science/pith/VGSD73PVEQTHRM4OXGAO4WVUIH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VGSD73PVEQTHRM4OXGAO4WVUIH/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":"2026-08-07T23:52:16Z","links":{"resolver":"https://pith.science/pith/VGSD73PVEQTHRM4OXGAO4WVUIH","bundle":"https://pith.science/pith/VGSD73PVEQTHRM4OXGAO4WVUIH/bundle.json","state":"https://pith.science/pith/VGSD73PVEQTHRM4OXGAO4WVUIH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VGSD73PVEQTHRM4OXGAO4WVUIH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:VGSD73PVEQTHRM4OXGAO4WVUIH","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":"26e1b239feb4e47113d381800ac52863cd829a83abce47ceb6d9c4d514253fd6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-04T08:29:00Z","title_canon_sha256":"a90cb1a36f0158d4aa6b3771665f4ac369793ee3ba1df777886538bf27b69df3"},"schema_version":"1.0","source":{"id":"1906.01265","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.01265","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"arxiv_version","alias_value":"1906.01265v3","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01265","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"pith_short_12","alias_value":"VGSD73PVEQTH","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"pith_short_16","alias_value":"VGSD73PVEQTHRM4O","created_at":"2026-07-05T00:35:44Z"},{"alias_kind":"pith_short_8","alias_value":"VGSD73PV","created_at":"2026-07-05T00:35:44Z"}],"graph_snapshots":[{"event_id":"sha256:577e3ffc965e2c4942287eb87e2616d7747b15e4d47bafe6032e8893a17a2c26","target":"graph","created_at":"2026-07-05T00:35:44Z","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/1906.01265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cloze-style reading comprehension in Chinese is still limited due to the lack of various corpora. In this paper we propose a large-scale Chinese cloze test dataset ChID, which studies the comprehension of idiom, a unique language phenomenon in Chinese. In this corpus, the idioms in a passage are replaced by blank symbols and the correct answer needs to be chosen from well-designed candidate idioms. We carefully study how the design of candidate idioms and the representation of idioms affect the performance of state-of-the-art models. Results show that the machine accuracy is substantially wors","authors_text":"Aixin Sun, Chujie Zheng, Minlie Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-04T08:29:00Z","title":"ChID: A Large-scale Chinese IDiom Dataset for Cloze Test"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01265","kind":"arxiv","version":3},"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":"sha256:5c734e06a3529c3800f71c514211bb769462fbc6b90069a06c481b4295b3c338","target":"record","created_at":"2026-07-05T00:35:44Z","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":"26e1b239feb4e47113d381800ac52863cd829a83abce47ceb6d9c4d514253fd6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-04T08:29:00Z","title_canon_sha256":"a90cb1a36f0158d4aa6b3771665f4ac369793ee3ba1df777886538bf27b69df3"},"schema_version":"1.0","source":{"id":"1906.01265","kind":"arxiv","version":3}},"canonical_sha256":"a9a43fedf5242678b38eb980ee5ab441c9e2a447b7c6d3ac4a2a479e4c424300","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9a43fedf5242678b38eb980ee5ab441c9e2a447b7c6d3ac4a2a479e4c424300","first_computed_at":"2026-07-05T00:35:44.172855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:35:44.172855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MgpeW5cAPqyL6J9dSUkKf07QCn1XLX8m6o6RL8tE7tRcie3P/d3eehqlfzcyyuQFJV5DBm1p6msGiP1j7bk8AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:35:44.173276Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.01265","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c734e06a3529c3800f71c514211bb769462fbc6b90069a06c481b4295b3c338","sha256:577e3ffc965e2c4942287eb87e2616d7747b15e4d47bafe6032e8893a17a2c26"],"state_sha256":"120bed95e9d188ab43f388ed1bf4e04eca3851ddc58d72e6cda8f02312f4085f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YrknU8Hjg6Sb9ysFiJGoNut9BtUfCYAQv/IPnh/R2PlfhmH8OD1Z7i+6mcWNJVRoLx3NaUKnNQmxqOxz6NIaCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:52:16.040910Z","bundle_sha256":"0fc054ddc960dab1cd8803543880c7587d724cb50b52bbcba9fc68ce307e866a"}}