{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:L776KHPT772PJ2UFJJVNFQJDJD","short_pith_number":"pith:L776KHPT","canonical_record":{"source":{"id":"2406.05707","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-09T09:51:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c05dd8038dbe1417b8e95bc99269f99f2b0624e0ea862d046ec9e886e4fa1ac","abstract_canon_sha256":"6f29dad8ab6dac2018f247cb7618791f3b956a2e2ed7aca1e791ea53844e37c3"},"schema_version":"1.0"},"canonical_sha256":"5fffe51df3fff4f4ea854a6ad2c12348db33d76ed67bdff868d731959d3c8e4b","source":{"kind":"arxiv","id":"2406.05707","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05707","created_at":"2026-07-05T09:18:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05707v2","created_at":"2026-07-05T09:18:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05707","created_at":"2026-07-05T09:18:26Z"},{"alias_kind":"pith_short_12","alias_value":"L776KHPT772P","created_at":"2026-07-05T09:18:26Z"},{"alias_kind":"pith_short_16","alias_value":"L776KHPT772PJ2UF","created_at":"2026-07-05T09:18:26Z"},{"alias_kind":"pith_short_8","alias_value":"L776KHPT","created_at":"2026-07-05T09:18:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:L776KHPT772PJ2UFJJVNFQJDJD","target":"record","payload":{"canonical_record":{"source":{"id":"2406.05707","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-09T09:51:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c05dd8038dbe1417b8e95bc99269f99f2b0624e0ea862d046ec9e886e4fa1ac","abstract_canon_sha256":"6f29dad8ab6dac2018f247cb7618791f3b956a2e2ed7aca1e791ea53844e37c3"},"schema_version":"1.0"},"canonical_sha256":"5fffe51df3fff4f4ea854a6ad2c12348db33d76ed67bdff868d731959d3c8e4b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:26.848481Z","signature_b64":"gW2MVX6KODaMOhooPS/SsJluhkH6TwDXTOQM+Xwm1HcNSKsP4b0DA1SNiEo3CDrGF/s5YEspZ+M1vR2WYvZ+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fffe51df3fff4f4ea854a6ad2c12348db33d76ed67bdff868d731959d3c8e4b","last_reissued_at":"2026-07-05T09:18:26.848008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:26.848008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.05707","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:18:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vjKiSMCfhHEEo+BcxalimlOUgbl4qguXa9Mxz27KPDCCfqrpiydy4K7s4jtJsbhXyHu8Tw6RmLhgnZp/GeEMCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:31:05.784507Z"},"content_sha256":"a048d0b0c11f835575c4e8eb8d0421fd8f412acf20dbbe23c5c3a91fc5755fb8","schema_version":"1.0","event_id":"sha256:a048d0b0c11f835575c4e8eb8d0421fd8f412acf20dbbe23c5c3a91fc5755fb8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:L776KHPT772PJ2UFJJVNFQJDJD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"QGEval: Benchmarking Multi-dimensional Evaluation for Question Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bifan Wei, Jianxiang Hu, Jun Liu, Weiping Fu, Zhongmin Cai","submitted_at":"2024-06-09T09:51:55Z","abstract_excerpt":"Automatically generated questions often suffer from problems such as unclear expression or factual inaccuracies, requiring a reliable and comprehensive evaluation of their quality. Human evaluation is widely used in the field of question generation (QG) and serves as the gold standard for automatic metrics. However, there is a lack of unified human evaluation criteria, which hampers consistent and reliable evaluations of both QG models and automatic metrics. To address this, we propose QGEval, a multi-dimensional Evaluation benchmark for Question Generation, which evaluates both generated ques"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05707","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/2406.05707/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":"2026-07-05T09:18:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YOWhyD1CZRbLec5feISxmsepYgRNCSf17lpb9vIrMqbkoGcR5oGGFEer+uJjlpT1z8u8aE/LIq2/fju2XTmoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:31:05.785129Z"},"content_sha256":"d31743880b71d1a03f9dafd543bbdbd84442102aeca61331d84e4309d124d524","schema_version":"1.0","event_id":"sha256:d31743880b71d1a03f9dafd543bbdbd84442102aeca61331d84e4309d124d524"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L776KHPT772PJ2UFJJVNFQJDJD/bundle.json","state_url":"https://pith.science/pith/L776KHPT772PJ2UFJJVNFQJDJD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L776KHPT772PJ2UFJJVNFQJDJD/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":"2026-08-06T13:31:05Z","links":{"resolver":"https://pith.science/pith/L776KHPT772PJ2UFJJVNFQJDJD","bundle":"https://pith.science/pith/L776KHPT772PJ2UFJJVNFQJDJD/bundle.json","state":"https://pith.science/pith/L776KHPT772PJ2UFJJVNFQJDJD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L776KHPT772PJ2UFJJVNFQJDJD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L776KHPT772PJ2UFJJVNFQJDJD","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":"6f29dad8ab6dac2018f247cb7618791f3b956a2e2ed7aca1e791ea53844e37c3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-09T09:51:55Z","title_canon_sha256":"5c05dd8038dbe1417b8e95bc99269f99f2b0624e0ea862d046ec9e886e4fa1ac"},"schema_version":"1.0","source":{"id":"2406.05707","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05707","created_at":"2026-07-05T09:18:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05707v2","created_at":"2026-07-05T09:18:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05707","created_at":"2026-07-05T09:18:26Z"},{"alias_kind":"pith_short_12","alias_value":"L776KHPT772P","created_at":"2026-07-05T09:18:26Z"},{"alias_kind":"pith_short_16","alias_value":"L776KHPT772PJ2UF","created_at":"2026-07-05T09:18:26Z"},{"alias_kind":"pith_short_8","alias_value":"L776KHPT","created_at":"2026-07-05T09:18:26Z"}],"graph_snapshots":[{"event_id":"sha256:d31743880b71d1a03f9dafd543bbdbd84442102aeca61331d84e4309d124d524","target":"graph","created_at":"2026-07-05T09:18:26Z","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/2406.05707/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatically generated questions often suffer from problems such as unclear expression or factual inaccuracies, requiring a reliable and comprehensive evaluation of their quality. Human evaluation is widely used in the field of question generation (QG) and serves as the gold standard for automatic metrics. However, there is a lack of unified human evaluation criteria, which hampers consistent and reliable evaluations of both QG models and automatic metrics. To address this, we propose QGEval, a multi-dimensional Evaluation benchmark for Question Generation, which evaluates both generated ques","authors_text":"Bifan Wei, Jianxiang Hu, Jun Liu, Weiping Fu, Zhongmin Cai","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-09T09:51:55Z","title":"QGEval: Benchmarking Multi-dimensional Evaluation for Question Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05707","kind":"arxiv","version":2},"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:a048d0b0c11f835575c4e8eb8d0421fd8f412acf20dbbe23c5c3a91fc5755fb8","target":"record","created_at":"2026-07-05T09:18:26Z","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":"6f29dad8ab6dac2018f247cb7618791f3b956a2e2ed7aca1e791ea53844e37c3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-09T09:51:55Z","title_canon_sha256":"5c05dd8038dbe1417b8e95bc99269f99f2b0624e0ea862d046ec9e886e4fa1ac"},"schema_version":"1.0","source":{"id":"2406.05707","kind":"arxiv","version":2}},"canonical_sha256":"5fffe51df3fff4f4ea854a6ad2c12348db33d76ed67bdff868d731959d3c8e4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fffe51df3fff4f4ea854a6ad2c12348db33d76ed67bdff868d731959d3c8e4b","first_computed_at":"2026-07-05T09:18:26.848008Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:26.848008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gW2MVX6KODaMOhooPS/SsJluhkH6TwDXTOQM+Xwm1HcNSKsP4b0DA1SNiEo3CDrGF/s5YEspZ+M1vR2WYvZ+Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:26.848481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.05707","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a048d0b0c11f835575c4e8eb8d0421fd8f412acf20dbbe23c5c3a91fc5755fb8","sha256:d31743880b71d1a03f9dafd543bbdbd84442102aeca61331d84e4309d124d524"],"state_sha256":"d0a1211556beb516e4ac493f1f10c670e6b8e99cce0cf5a1173defd627daecaa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WsnHtkbz2ix+24cSW2fFlDSRhgJJKuhxrqbY5vcXIqxyEsYrcraBZLsNfqp0Mo9XqENj09bndoJSTqJbxwyPDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T13:31:05.796302Z","bundle_sha256":"b8d2a1cb58b1ead89f87d594cd70f4b9624c56f8d201c68c774946a0aff88a32"}}