{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L2RY3QMM37HDNHAM3CWYXKVK7Y","short_pith_number":"pith:L2RY3QMM","schema_version":"1.0","canonical_sha256":"5ea38dc18cdfce369c0cd8ad8baaaafe33ad08ca274c4f6f770399da9bb8a814","source":{"kind":"arxiv","id":"2405.09939","version":2},"attestation_state":"computed","paper":{"title":"SciQAG: A Framework for Auto-Generated Science Question Answering Dataset with Fine-grained Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aswathy Ajith, Bram Hoex, Chunyu Kit, Clara Grazian, Ian Foster, Tong Xie, Wenjie Zhang, Yixuan Liu, Yuwei Wan","submitted_at":"2024-05-16T09:42:37Z","abstract_excerpt":"We introduce SciQAG, a novel framework for automatically generating high-quality science question-answer pairs from a large corpus of scientific literature based on large language models (LLMs). SciQAG consists of a QA generator and a QA evaluator, which work together to extract diverse and research-level questions and answers from scientific papers. Utilizing this framework, we construct a large-scale, high-quality, open-ended science QA dataset containing 188,042 QA pairs extracted from 22,743 scientific papers across 24 scientific domains. We also introduce SciQAG-24D, a new benchmark task "},"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":"2405.09939","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-16T09:42:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6c49ee9094007a2787e61611e12ffc99597630797432d7ebaa1a0380a757f824","abstract_canon_sha256":"7f76f73c446961978d17fc42c6180fc941ab6d6eda0b2237acc6208336340736"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:04.374900Z","signature_b64":"EcgBW1t6y8+SHWonsjU+tyv/BoluGzsMSr8fHjtzH2lQsfi2xx5KwEKqfJ9/m6Vey90ObIeMWa8e0n3DlmNVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ea38dc18cdfce369c0cd8ad8baaaafe33ad08ca274c4f6f770399da9bb8a814","last_reissued_at":"2026-07-05T08:42:04.374404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:04.374404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciQAG: A Framework for Auto-Generated Science Question Answering Dataset with Fine-grained Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aswathy Ajith, Bram Hoex, Chunyu Kit, Clara Grazian, Ian Foster, Tong Xie, Wenjie Zhang, Yixuan Liu, Yuwei Wan","submitted_at":"2024-05-16T09:42:37Z","abstract_excerpt":"We introduce SciQAG, a novel framework for automatically generating high-quality science question-answer pairs from a large corpus of scientific literature based on large language models (LLMs). SciQAG consists of a QA generator and a QA evaluator, which work together to extract diverse and research-level questions and answers from scientific papers. Utilizing this framework, we construct a large-scale, high-quality, open-ended science QA dataset containing 188,042 QA pairs extracted from 22,743 scientific papers across 24 scientific domains. We also introduce SciQAG-24D, a new benchmark task "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.09939","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/2405.09939/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":"2405.09939","created_at":"2026-07-05T08:42:04.374462+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.09939v2","created_at":"2026-07-05T08:42:04.374462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.09939","created_at":"2026-07-05T08:42:04.374462+00:00"},{"alias_kind":"pith_short_12","alias_value":"L2RY3QMM37HD","created_at":"2026-07-05T08:42:04.374462+00:00"},{"alias_kind":"pith_short_16","alias_value":"L2RY3QMM37HDNHAM","created_at":"2026-07-05T08:42:04.374462+00:00"},{"alias_kind":"pith_short_8","alias_value":"L2RY3QMM","created_at":"2026-07-05T08:42:04.374462+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00644","citing_title":"ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2506.17585","citing_title":"Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21990","citing_title":"ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L2RY3QMM37HDNHAM3CWYXKVK7Y","json":"https://pith.science/pith/L2RY3QMM37HDNHAM3CWYXKVK7Y.json","graph_json":"https://pith.science/api/pith-number/L2RY3QMM37HDNHAM3CWYXKVK7Y/graph.json","events_json":"https://pith.science/api/pith-number/L2RY3QMM37HDNHAM3CWYXKVK7Y/events.json","paper":"https://pith.science/paper/L2RY3QMM"},"agent_actions":{"view_html":"https://pith.science/pith/L2RY3QMM37HDNHAM3CWYXKVK7Y","download_json":"https://pith.science/pith/L2RY3QMM37HDNHAM3CWYXKVK7Y.json","view_paper":"https://pith.science/paper/L2RY3QMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.09939&json=true","fetch_graph":"https://pith.science/api/pith-number/L2RY3QMM37HDNHAM3CWYXKVK7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/L2RY3QMM37HDNHAM3CWYXKVK7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L2RY3QMM37HDNHAM3CWYXKVK7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L2RY3QMM37HDNHAM3CWYXKVK7Y/action/storage_attestation","attest_author":"https://pith.science/pith/L2RY3QMM37HDNHAM3CWYXKVK7Y/action/author_attestation","sign_citation":"https://pith.science/pith/L2RY3QMM37HDNHAM3CWYXKVK7Y/action/citation_signature","submit_replication":"https://pith.science/pith/L2RY3QMM37HDNHAM3CWYXKVK7Y/action/replication_record"}},"created_at":"2026-07-05T08:42:04.374462+00:00","updated_at":"2026-07-05T08:42:04.374462+00:00"}