{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NFQKXUSIGAMOILOOPPXQ2WTPEM","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":"8870bd6606819ba6ce0c129dc85c48dbfe1d6af677e0f8bb2f86825afb72a160","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-01T12:48:12Z","title_canon_sha256":"a41629f9a88b3f72b4ec5ae09987cf73b0e3a669618c075eebe8f1ace331477a"},"schema_version":"1.0","source":{"id":"2301.00395","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.00395","created_at":"2026-07-05T05:29:45Z"},{"alias_kind":"arxiv_version","alias_value":"2301.00395v1","created_at":"2026-07-05T05:29:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.00395","created_at":"2026-07-05T05:29:45Z"},{"alias_kind":"pith_short_12","alias_value":"NFQKXUSIGAMO","created_at":"2026-07-05T05:29:45Z"},{"alias_kind":"pith_short_16","alias_value":"NFQKXUSIGAMOILOO","created_at":"2026-07-05T05:29:45Z"},{"alias_kind":"pith_short_8","alias_value":"NFQKXUSI","created_at":"2026-07-05T05:29:45Z"}],"graph_snapshots":[{"event_id":"sha256:8ff19cefd8aafc25c3fbd288ff3916f40815e3d4e8acd136f9742e9b239f53eb","target":"graph","created_at":"2026-07-05T05:29:45Z","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/2301.00395/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As natural language processing (NLP) for gender bias becomes a significant interdisciplinary topic, the prevalent data-driven techniques such as large-scale language models suffer from data inadequacy and biased corpus, especially for languages with insufficient resources such as Chinese. To this end, we propose a Chinese cOrpus foR Gender bIas Probing and Mitigation CORGI-PM, which contains 32.9k sentences with high-quality labels derived by following an annotation scheme specifically developed for gender bias in the Chinese context. Moreover, we address three challenges for automatic textual","authors_text":"Chenghua Lin, Ge Zhang, Jiayi Geng, Jie Fu, Linyuan Zhang, Shi Wang, Yaoyao Wu, Yizhi Li","cross_cats":["cs.AI","cs.CY","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-01T12:48:12Z","title":"CORGI-PM: A Chinese Corpus For Gender Bias Probing and Mitigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.00395","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":"sha256:5bfea1882d7547ab16590e576a3c6892f75b0b09dc7727e9d5bd955f1473c94b","target":"record","created_at":"2026-07-05T05:29:45Z","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":"8870bd6606819ba6ce0c129dc85c48dbfe1d6af677e0f8bb2f86825afb72a160","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-01T12:48:12Z","title_canon_sha256":"a41629f9a88b3f72b4ec5ae09987cf73b0e3a669618c075eebe8f1ace331477a"},"schema_version":"1.0","source":{"id":"2301.00395","kind":"arxiv","version":1}},"canonical_sha256":"6960abd2483018e42dce7bef0d5a6f230943659338aaa466abe34237165dea11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6960abd2483018e42dce7bef0d5a6f230943659338aaa466abe34237165dea11","first_computed_at":"2026-07-05T05:29:45.700398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:29:45.700398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z/VoWC4T+O2KpLZRfJ7+U2JpX8x2hMnWOHjLlh2p8Pt29AAJVOsi5r0FBMBihD5ZU8hQgj4luan1SU8Y/UW0AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:29:45.700892Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.00395","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bfea1882d7547ab16590e576a3c6892f75b0b09dc7727e9d5bd955f1473c94b","sha256:8ff19cefd8aafc25c3fbd288ff3916f40815e3d4e8acd136f9742e9b239f53eb"],"state_sha256":"88f0f2e32d16ab7bb81d72af20cb9983dec1368284e88f06ad3fd9ce14caeec4"}