{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N2YLC6JSXI2BY5YD3W63UZ6CAY","short_pith_number":"pith:N2YLC6JS","schema_version":"1.0","canonical_sha256":"6eb0b17932ba341c7703ddbdba67c20629ca93f89959517c41102d5d1e7c7a0e","source":{"kind":"arxiv","id":"2601.10406","version":1},"attestation_state":"computed","paper":{"title":"ErrEval: Error-Aware Evaluation for Question Generation through Explicit Diagnostics","license":"","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bifan Wei, Bo Li, Jian Zhang, Jiaxin Wang, Jingyi Hao, Jun Liu, Lingling Zhang, Weiping Fu, Yu He, Yushun Zhang","submitted_at":"2026-01-15T13:57:15Z","abstract_excerpt":"Automatic Question Generation (QG) often produces outputs with critical defects, such as factual hallucinations and answer mismatches. However, existing evaluation methods, including LLM-based evaluators, mainly adopt a black-box and holistic paradigm without explicit error modeling, leading to the neglect of such defects and overestimation of question quality. To address this issue, we propose ErrEval, a flexible and Error-aware Evaluation framework that enhances QG evaluation through explicit error diagnostics. Specifically, ErrEval reformulates evaluation as a two-stage process of error dia"},"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":"2601.10406","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.AI","submitted_at":"2026-01-15T13:57:15Z","cross_cats_sorted":[],"title_canon_sha256":"0b4657da9185a9b447ed16c3ce220d81423e41f660b3ebb3868a2778186d6913","abstract_canon_sha256":"9e1c6edb0e8790cf97439650bfa97194ed075c561b4edb781642f417851dfdf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T08:42:25.386694Z","signature_b64":"U5UIrG2+F2B81I8OppiZ+Qr4ewbvTNZq+TYoh28Q6MacGcq9Pyu1n+BGt4JmZHj6pYFzVXsIF0AXIeNVjbt7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6eb0b17932ba341c7703ddbdba67c20629ca93f89959517c41102d5d1e7c7a0e","last_reissued_at":"2026-07-02T08:42:25.386154Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T08:42:25.386154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ErrEval: Error-Aware Evaluation for Question Generation through Explicit Diagnostics","license":"","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bifan Wei, Bo Li, Jian Zhang, Jiaxin Wang, Jingyi Hao, Jun Liu, Lingling Zhang, Weiping Fu, Yu He, Yushun Zhang","submitted_at":"2026-01-15T13:57:15Z","abstract_excerpt":"Automatic Question Generation (QG) often produces outputs with critical defects, such as factual hallucinations and answer mismatches. However, existing evaluation methods, including LLM-based evaluators, mainly adopt a black-box and holistic paradigm without explicit error modeling, leading to the neglect of such defects and overestimation of question quality. To address this issue, we propose ErrEval, a flexible and Error-aware Evaluation framework that enhances QG evaluation through explicit error diagnostics. Specifically, ErrEval reformulates evaluation as a two-stage process of error dia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.10406","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/2601.10406/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":"2601.10406","created_at":"2026-07-02T08:42:25.386233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.10406v1","created_at":"2026-07-02T08:42:25.386233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.10406","created_at":"2026-07-02T08:42:25.386233+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2YLC6JSXI2B","created_at":"2026-07-02T08:42:25.386233+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2YLC6JSXI2BY5YD","created_at":"2026-07-02T08:42:25.386233+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2YLC6JS","created_at":"2026-07-02T08:42:25.386233+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/N2YLC6JSXI2BY5YD3W63UZ6CAY","json":"https://pith.science/pith/N2YLC6JSXI2BY5YD3W63UZ6CAY.json","graph_json":"https://pith.science/api/pith-number/N2YLC6JSXI2BY5YD3W63UZ6CAY/graph.json","events_json":"https://pith.science/api/pith-number/N2YLC6JSXI2BY5YD3W63UZ6CAY/events.json","paper":"https://pith.science/paper/N2YLC6JS"},"agent_actions":{"view_html":"https://pith.science/pith/N2YLC6JSXI2BY5YD3W63UZ6CAY","download_json":"https://pith.science/pith/N2YLC6JSXI2BY5YD3W63UZ6CAY.json","view_paper":"https://pith.science/paper/N2YLC6JS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.10406&json=true","fetch_graph":"https://pith.science/api/pith-number/N2YLC6JSXI2BY5YD3W63UZ6CAY/graph.json","fetch_events":"https://pith.science/api/pith-number/N2YLC6JSXI2BY5YD3W63UZ6CAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2YLC6JSXI2BY5YD3W63UZ6CAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2YLC6JSXI2BY5YD3W63UZ6CAY/action/storage_attestation","attest_author":"https://pith.science/pith/N2YLC6JSXI2BY5YD3W63UZ6CAY/action/author_attestation","sign_citation":"https://pith.science/pith/N2YLC6JSXI2BY5YD3W63UZ6CAY/action/citation_signature","submit_replication":"https://pith.science/pith/N2YLC6JSXI2BY5YD3W63UZ6CAY/action/replication_record"}},"created_at":"2026-07-02T08:42:25.386233+00:00","updated_at":"2026-07-02T08:42:25.386233+00:00"}