{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:N2YLC6JSXI2BY5YD3W63UZ6CAY","short_pith_number":"pith:N2YLC6JS","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"},"canonical_sha256":"6eb0b17932ba341c7703ddbdba67c20629ca93f89959517c41102d5d1e7c7a0e","source":{"kind":"arxiv","id":"2601.10406","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.10406","created_at":"2026-07-02T08:42:25Z"},{"alias_kind":"arxiv_version","alias_value":"2601.10406v1","created_at":"2026-07-02T08:42:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.10406","created_at":"2026-07-02T08:42:25Z"},{"alias_kind":"pith_short_12","alias_value":"N2YLC6JSXI2B","created_at":"2026-07-02T08:42:25Z"},{"alias_kind":"pith_short_16","alias_value":"N2YLC6JSXI2BY5YD","created_at":"2026-07-02T08:42:25Z"},{"alias_kind":"pith_short_8","alias_value":"N2YLC6JS","created_at":"2026-07-02T08:42:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:N2YLC6JSXI2BY5YD3W63UZ6CAY","target":"record","payload":{"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"},"canonical_sha256":"6eb0b17932ba341c7703ddbdba67c20629ca93f89959517c41102d5d1e7c7a0e","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"},"source_kind":"arxiv","source_id":"2601.10406","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-02T08:42:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7WaC21R3WyRBSdGadSCoaFSz6I6XDz2x3VwNdpoVyAYq2fkt4UQhFyEwQiqsgku3TszUqe0vNwEe/phLpMhSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:59:01.726401Z"},"content_sha256":"56984843c02d7ccd6cc0d122d6ed0f51cc7713bcb9e79837248d694e504b71e6","schema_version":"1.0","event_id":"sha256:56984843c02d7ccd6cc0d122d6ed0f51cc7713bcb9e79837248d694e504b71e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:N2YLC6JSXI2BY5YD3W63UZ6CAY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-02T08:42:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tteJEZbffNynTxECkpAyKRuTM40mmBqwGFOEepKFSWb8vzguAGy4XJwYZNkeQSEzijuQ1kIV7Gew9HfJwBXsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:59:01.726792Z"},"content_sha256":"a3989bda21ff0b31d431febcc3846b60382a7f7930052b590f553d3ed19814a9","schema_version":"1.0","event_id":"sha256:a3989bda21ff0b31d431febcc3846b60382a7f7930052b590f553d3ed19814a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N2YLC6JSXI2BY5YD3W63UZ6CAY/bundle.json","state_url":"https://pith.science/pith/N2YLC6JSXI2BY5YD3W63UZ6CAY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N2YLC6JSXI2BY5YD3W63UZ6CAY/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":"2026-08-04T03:59:01Z","links":{"resolver":"https://pith.science/pith/N2YLC6JSXI2BY5YD3W63UZ6CAY","bundle":"https://pith.science/pith/N2YLC6JSXI2BY5YD3W63UZ6CAY/bundle.json","state":"https://pith.science/pith/N2YLC6JSXI2BY5YD3W63UZ6CAY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N2YLC6JSXI2BY5YD3W63UZ6CAY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:N2YLC6JSXI2BY5YD3W63UZ6CAY","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":"9e1c6edb0e8790cf97439650bfa97194ed075c561b4edb781642f417851dfdf8","cross_cats_sorted":[],"license":"","primary_cat":"cs.AI","submitted_at":"2026-01-15T13:57:15Z","title_canon_sha256":"0b4657da9185a9b447ed16c3ce220d81423e41f660b3ebb3868a2778186d6913"},"schema_version":"1.0","source":{"id":"2601.10406","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.10406","created_at":"2026-07-02T08:42:25Z"},{"alias_kind":"arxiv_version","alias_value":"2601.10406v1","created_at":"2026-07-02T08:42:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.10406","created_at":"2026-07-02T08:42:25Z"},{"alias_kind":"pith_short_12","alias_value":"N2YLC6JSXI2B","created_at":"2026-07-02T08:42:25Z"},{"alias_kind":"pith_short_16","alias_value":"N2YLC6JSXI2BY5YD","created_at":"2026-07-02T08:42:25Z"},{"alias_kind":"pith_short_8","alias_value":"N2YLC6JS","created_at":"2026-07-02T08:42:25Z"}],"graph_snapshots":[{"event_id":"sha256:a3989bda21ff0b31d431febcc3846b60382a7f7930052b590f553d3ed19814a9","target":"graph","created_at":"2026-07-02T08:42:25Z","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/2601.10406/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bifan Wei, Bo Li, Jian Zhang, Jiaxin Wang, Jingyi Hao, Jun Liu, Lingling Zhang, Weiping Fu, Yu He, Yushun Zhang","cross_cats":[],"headline":"","license":"","primary_cat":"cs.AI","submitted_at":"2026-01-15T13:57:15Z","title":"ErrEval: Error-Aware Evaluation for Question Generation through Explicit Diagnostics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.10406","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":"sha256:56984843c02d7ccd6cc0d122d6ed0f51cc7713bcb9e79837248d694e504b71e6","target":"record","created_at":"2026-07-02T08:42:25Z","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":"9e1c6edb0e8790cf97439650bfa97194ed075c561b4edb781642f417851dfdf8","cross_cats_sorted":[],"license":"","primary_cat":"cs.AI","submitted_at":"2026-01-15T13:57:15Z","title_canon_sha256":"0b4657da9185a9b447ed16c3ce220d81423e41f660b3ebb3868a2778186d6913"},"schema_version":"1.0","source":{"id":"2601.10406","kind":"arxiv","version":1}},"canonical_sha256":"6eb0b17932ba341c7703ddbdba67c20629ca93f89959517c41102d5d1e7c7a0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6eb0b17932ba341c7703ddbdba67c20629ca93f89959517c41102d5d1e7c7a0e","first_computed_at":"2026-07-02T08:42:25.386154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T08:42:25.386154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U5UIrG2+F2B81I8OppiZ+Qr4ewbvTNZq+TYoh28Q6MacGcq9Pyu1n+BGt4JmZHj6pYFzVXsIF0AXIeNVjbt7Cg==","signature_status":"signed_v1","signed_at":"2026-07-02T08:42:25.386694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.10406","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56984843c02d7ccd6cc0d122d6ed0f51cc7713bcb9e79837248d694e504b71e6","sha256:a3989bda21ff0b31d431febcc3846b60382a7f7930052b590f553d3ed19814a9"],"state_sha256":"d8ba2662d94b2d6f160d3fa6103bf981c8cdf80ab52e596bccd9558d685251ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7rU7N4iCoZkeXkP8jWNEHp/DnOtCGFBdCHmM2/J5d9OpxsjjA/qhXO/aTXTeTAXcdv+DLRimHhxxReuOt/hPDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:59:01.729102Z","bundle_sha256":"d42af286fa201a15336133771a13afb8e90f18347ab64060cfc84a9219c74a0a"}}