{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JO7WHLPLGRDCZ3YTM3WUOE5XIH","short_pith_number":"pith:JO7WHLPL","schema_version":"1.0","canonical_sha256":"4bbf63adeb34462cef1366ed4713b741c6154e006a8770abc89e76c3151733a7","source":{"kind":"arxiv","id":"2510.08986","version":3},"attestation_state":"computed","paper":{"title":"CAPC-CG: A Large-Scale, Expert-Directed LLM-Annotated Corpus of Adaptive Policy Communication in China","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"CAPC-CG supplies the first large open corpus of Chinese central-government policy directives labeled with a five-color taxonomy of clear and ambiguous language.","cross_cats":["cs.CE","cs.CY"],"primary_cat":"cs.CL","authors_text":"Bolun Sun, Charles Chang, Pingxu Hao, Ruotong Mu, Yuchen Xu, Yuen Yuen Ang, Zhengxin Zhang","submitted_at":"2025-10-10T04:11:57Z","abstract_excerpt":"We introduce CAPC-CG, the Chinese Adaptive Policy Communication (Central Government) Corpus, the first open dataset of Chinese policy directives annotated with a five-color taxonomy of clear and ambiguous language categories, building on Ang's theory of adaptive policy communication. Spanning 1949-2023, this corpus includes national laws, administrative regulations, and ministerial rules issued by China's top authorities. Each document is segmented into paragraphs, producing a total of 3.3 million units. Alongside the corpus, we release comprehensive metadata, a two-round labeling framework, a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2510.08986","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-10T04:11:57Z","cross_cats_sorted":["cs.CE","cs.CY"],"title_canon_sha256":"8b075b2c8412c713cd5e6d7bb84d8b324111d1782c40d2d9fe192331217655b0","abstract_canon_sha256":"cf6aef52f02bb882fac9f5e6c8c19a515ee2dfbd64e4ddcc5f6b9bb75a55ef02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:04:59.752395Z","signature_b64":"/0I8lREyiRHsMIHem/q5GP+SI49G7igcf6bKFGHV+S4rwv8b5i7yI8hq6l1demj5kelSznpJ/GjesT5V0xqUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bbf63adeb34462cef1366ed4713b741c6154e006a8770abc89e76c3151733a7","last_reissued_at":"2026-05-20T01:04:59.751457Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:04:59.751457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAPC-CG: A Large-Scale, Expert-Directed LLM-Annotated Corpus of Adaptive Policy Communication in China","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"CAPC-CG supplies the first large open corpus of Chinese central-government policy directives labeled with a five-color taxonomy of clear and ambiguous language.","cross_cats":["cs.CE","cs.CY"],"primary_cat":"cs.CL","authors_text":"Bolun Sun, Charles Chang, Pingxu Hao, Ruotong Mu, Yuchen Xu, Yuen Yuen Ang, Zhengxin Zhang","submitted_at":"2025-10-10T04:11:57Z","abstract_excerpt":"We introduce CAPC-CG, the Chinese Adaptive Policy Communication (Central Government) Corpus, the first open dataset of Chinese policy directives annotated with a five-color taxonomy of clear and ambiguous language categories, building on Ang's theory of adaptive policy communication. Spanning 1949-2023, this corpus includes national laws, administrative regulations, and ministerial rules issued by China's top authorities. Each document is segmented into paragraphs, producing a total of 3.3 million units. Alongside the corpus, we release comprehensive metadata, a two-round labeling framework, a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We introduce CAPC-CG, the Chinese Adaptive Policy Communication (Central Government) Corpus, the first open dataset of Chinese policy directives annotated with a five-color taxonomy of clear and ambiguous language categories, building on Ang's theory of adaptive policy communication.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The five-color taxonomy derived from Ang's theory accurately and reliably distinguishes adaptive policy communication patterns in the selected documents, and that paragraph-level segmentation plus expert annotation produces labels suitable for supervised modeling without significant loss of context.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The first open annotated corpus of Chinese central government policy directives with expert-directed five-color labels for adaptive policy communication.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CAPC-CG supplies the first large open corpus of Chinese central-government policy directives labeled with a five-color taxonomy of clear and ambiguous language.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b0559a830645347b28928015e0d53bca3317f67e0a8e63e9f1e03102cc86cbd2"},"source":{"id":"2510.08986","kind":"arxiv","version":3},"verdict":{"id":"ceb7e306-1f2b-46e8-86fd-1e2dcf89576a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T08:32:29.560522Z","strongest_claim":"We introduce CAPC-CG, the Chinese Adaptive Policy Communication (Central Government) Corpus, the first open dataset of Chinese policy directives annotated with a five-color taxonomy of clear and ambiguous language categories, building on Ang's theory of adaptive policy communication.","one_line_summary":"The first open annotated corpus of Chinese central government policy directives with expert-directed five-color labels for adaptive policy communication.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The five-color taxonomy derived from Ang's theory accurately and reliably distinguishes adaptive policy communication patterns in the selected documents, and that paragraph-level segmentation plus expert annotation produces labels suitable for supervised modeling without significant loss of context.","pith_extraction_headline":"CAPC-CG supplies the first large open corpus of Chinese central-government policy directives labeled with a five-color taxonomy of clear and ambiguous language."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.08986/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2510.08986","created_at":"2026-05-20T01:04:59.751614+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.08986v3","created_at":"2026-05-20T01:04:59.751614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.08986","created_at":"2026-05-20T01:04:59.751614+00:00"},{"alias_kind":"pith_short_12","alias_value":"JO7WHLPLGRDC","created_at":"2026-05-20T01:04:59.751614+00:00"},{"alias_kind":"pith_short_16","alias_value":"JO7WHLPLGRDCZ3YT","created_at":"2026-05-20T01:04:59.751614+00:00"},{"alias_kind":"pith_short_8","alias_value":"JO7WHLPL","created_at":"2026-05-20T01:04:59.751614+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JO7WHLPLGRDCZ3YTM3WUOE5XIH","json":"https://pith.science/pith/JO7WHLPLGRDCZ3YTM3WUOE5XIH.json","graph_json":"https://pith.science/api/pith-number/JO7WHLPLGRDCZ3YTM3WUOE5XIH/graph.json","events_json":"https://pith.science/api/pith-number/JO7WHLPLGRDCZ3YTM3WUOE5XIH/events.json","paper":"https://pith.science/paper/JO7WHLPL"},"agent_actions":{"view_html":"https://pith.science/pith/JO7WHLPLGRDCZ3YTM3WUOE5XIH","download_json":"https://pith.science/pith/JO7WHLPLGRDCZ3YTM3WUOE5XIH.json","view_paper":"https://pith.science/paper/JO7WHLPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.08986&json=true","fetch_graph":"https://pith.science/api/pith-number/JO7WHLPLGRDCZ3YTM3WUOE5XIH/graph.json","fetch_events":"https://pith.science/api/pith-number/JO7WHLPLGRDCZ3YTM3WUOE5XIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JO7WHLPLGRDCZ3YTM3WUOE5XIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JO7WHLPLGRDCZ3YTM3WUOE5XIH/action/storage_attestation","attest_author":"https://pith.science/pith/JO7WHLPLGRDCZ3YTM3WUOE5XIH/action/author_attestation","sign_citation":"https://pith.science/pith/JO7WHLPLGRDCZ3YTM3WUOE5XIH/action/citation_signature","submit_replication":"https://pith.science/pith/JO7WHLPLGRDCZ3YTM3WUOE5XIH/action/replication_record"}},"created_at":"2026-05-20T01:04:59.751614+00:00","updated_at":"2026-05-20T01:04:59.751614+00:00"}