{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VLEISICQQ5RH2CTLYZTTTL6SYN","short_pith_number":"pith:VLEISICQ","schema_version":"1.0","canonical_sha256":"aac889205087627d0a6bc66739afd2c34a9695cefa222ba0474be49dff4be549","source":{"kind":"arxiv","id":"2112.08609","version":2},"attestation_state":"computed","paper":{"title":"DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"HaiFeng Wang, Hongyu Zhu, Hua Wu, Jing Liu, Jing Yan, Yan Chen, Ying Chen, Yu Hong","submitted_at":"2021-12-16T04:16:39Z","abstract_excerpt":"In this paper, we focus on studying robustness evaluation of Chinese question matching. Most of the previous work on analyzing robustness issue focus on just one or a few types of artificial adversarial examples. Instead, we argue that it is necessary to formulate a comprehensive evaluation about the linguistic capabilities of models on natural texts. For this purpose, we create a Chinese dataset namely DuQM which contains natural questions with linguistic perturbations to evaluate the robustness of question matching models. DuQM contains 3 categories and 13 subcategories with 32 linguistic pe"},"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":"2112.08609","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T04:16:39Z","cross_cats_sorted":[],"title_canon_sha256":"143b751b225abe93399fd562c49b745a5d7020153c67016ff7168a7b43f2b115","abstract_canon_sha256":"f60f1ce4ece200803fcd56776c1178b8a6183207b639ab248eb39bb30301187d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:21.540727Z","signature_b64":"B3ObqA3O+DNQV/G3M5nMghluWC3Zewv/7Tx4pOQQ95ZU2fdbbXcekj9ddemfEOrVlMr4zTx/RIiV5+BO3QLFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aac889205087627d0a6bc66739afd2c34a9695cefa222ba0474be49dff4be549","last_reissued_at":"2026-07-05T04:26:21.540179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:21.540179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"HaiFeng Wang, Hongyu Zhu, Hua Wu, Jing Liu, Jing Yan, Yan Chen, Ying Chen, Yu Hong","submitted_at":"2021-12-16T04:16:39Z","abstract_excerpt":"In this paper, we focus on studying robustness evaluation of Chinese question matching. Most of the previous work on analyzing robustness issue focus on just one or a few types of artificial adversarial examples. Instead, we argue that it is necessary to formulate a comprehensive evaluation about the linguistic capabilities of models on natural texts. For this purpose, we create a Chinese dataset namely DuQM which contains natural questions with linguistic perturbations to evaluate the robustness of question matching models. DuQM contains 3 categories and 13 subcategories with 32 linguistic pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08609","kind":"arxiv","version":2},"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/2112.08609/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":"2112.08609","created_at":"2026-07-05T04:26:21.540244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08609v2","created_at":"2026-07-05T04:26:21.540244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08609","created_at":"2026-07-05T04:26:21.540244+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLEISICQQ5RH","created_at":"2026-07-05T04:26:21.540244+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLEISICQQ5RH2CTL","created_at":"2026-07-05T04:26:21.540244+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLEISICQ","created_at":"2026-07-05T04:26:21.540244+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/VLEISICQQ5RH2CTLYZTTTL6SYN","json":"https://pith.science/pith/VLEISICQQ5RH2CTLYZTTTL6SYN.json","graph_json":"https://pith.science/api/pith-number/VLEISICQQ5RH2CTLYZTTTL6SYN/graph.json","events_json":"https://pith.science/api/pith-number/VLEISICQQ5RH2CTLYZTTTL6SYN/events.json","paper":"https://pith.science/paper/VLEISICQ"},"agent_actions":{"view_html":"https://pith.science/pith/VLEISICQQ5RH2CTLYZTTTL6SYN","download_json":"https://pith.science/pith/VLEISICQQ5RH2CTLYZTTTL6SYN.json","view_paper":"https://pith.science/paper/VLEISICQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08609&json=true","fetch_graph":"https://pith.science/api/pith-number/VLEISICQQ5RH2CTLYZTTTL6SYN/graph.json","fetch_events":"https://pith.science/api/pith-number/VLEISICQQ5RH2CTLYZTTTL6SYN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLEISICQQ5RH2CTLYZTTTL6SYN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLEISICQQ5RH2CTLYZTTTL6SYN/action/storage_attestation","attest_author":"https://pith.science/pith/VLEISICQQ5RH2CTLYZTTTL6SYN/action/author_attestation","sign_citation":"https://pith.science/pith/VLEISICQQ5RH2CTLYZTTTL6SYN/action/citation_signature","submit_replication":"https://pith.science/pith/VLEISICQQ5RH2CTLYZTTTL6SYN/action/replication_record"}},"created_at":"2026-07-05T04:26:21.540244+00:00","updated_at":"2026-07-05T04:26:21.540244+00:00"}