{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:27DXUASEBPEH5KKJ5UUXZX35IS","short_pith_number":"pith:27DXUASE","schema_version":"1.0","canonical_sha256":"d7c77a02440bc87ea949ed297cdf7d449720e9ffc40a20b7c55671d4d95ea34c","source":{"kind":"arxiv","id":"2407.16931","version":1},"attestation_state":"computed","paper":{"title":"ScholarChemQA: Unveiling the Power of Language Models in Chemical Research Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoyang Li, Juexiao Zhou, J\\\"urgen Schmidhuber, Kehan Guo, Mingchen Zhuge, Taicheng Guo, Tairan Wang, Xiangliang Zhang, Xin Gao, Xiuying Chen","submitted_at":"2024-07-24T01:46:55Z","abstract_excerpt":"Question Answering (QA) effectively evaluates language models' reasoning and knowledge depth. While QA datasets are plentiful in areas like general domain and biomedicine, academic chemistry is less explored. Chemical QA plays a crucial role in both education and research by effectively translating complex chemical information into readily understandable format. Addressing this gap, we introduce ScholarChemQA, a large-scale QA dataset constructed from chemical papers. This dataset reflects typical real-world challenges, including an imbalanced data distribution and a substantial amount of unla"},"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":"2407.16931","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-24T01:46:55Z","cross_cats_sorted":[],"title_canon_sha256":"db8b9f23423787a8e68632d5523bec7e14d7b9a007e99e56d56854f4781eb039","abstract_canon_sha256":"92958b0acac46fc25c31b625343ef992827815dc9c5a3f20d363da1e39c8d648"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:59.357069Z","signature_b64":"LglBKPm+rmLfDFVnb/ksjkZgqmiQjp/cfUYSNUw3B2IS9BxoN8Y2vlX5vLQLwmT7b9QHs/C/iSEA8XMFiXcMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7c77a02440bc87ea949ed297cdf7d449720e9ffc40a20b7c55671d4d95ea34c","last_reissued_at":"2026-07-05T08:47:59.356554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:59.356554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScholarChemQA: Unveiling the Power of Language Models in Chemical Research Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoyang Li, Juexiao Zhou, J\\\"urgen Schmidhuber, Kehan Guo, Mingchen Zhuge, Taicheng Guo, Tairan Wang, Xiangliang Zhang, Xin Gao, Xiuying Chen","submitted_at":"2024-07-24T01:46:55Z","abstract_excerpt":"Question Answering (QA) effectively evaluates language models' reasoning and knowledge depth. While QA datasets are plentiful in areas like general domain and biomedicine, academic chemistry is less explored. Chemical QA plays a crucial role in both education and research by effectively translating complex chemical information into readily understandable format. Addressing this gap, we introduce ScholarChemQA, a large-scale QA dataset constructed from chemical papers. This dataset reflects typical real-world challenges, including an imbalanced data distribution and a substantial amount of unla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16931","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/2407.16931/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":"2407.16931","created_at":"2026-07-05T08:47:59.356623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16931v1","created_at":"2026-07-05T08:47:59.356623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16931","created_at":"2026-07-05T08:47:59.356623+00:00"},{"alias_kind":"pith_short_12","alias_value":"27DXUASEBPEH","created_at":"2026-07-05T08:47:59.356623+00:00"},{"alias_kind":"pith_short_16","alias_value":"27DXUASEBPEH5KKJ","created_at":"2026-07-05T08:47:59.356623+00:00"},{"alias_kind":"pith_short_8","alias_value":"27DXUASE","created_at":"2026-07-05T08:47:59.356623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.11336","citing_title":"XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/27DXUASEBPEH5KKJ5UUXZX35IS","json":"https://pith.science/pith/27DXUASEBPEH5KKJ5UUXZX35IS.json","graph_json":"https://pith.science/api/pith-number/27DXUASEBPEH5KKJ5UUXZX35IS/graph.json","events_json":"https://pith.science/api/pith-number/27DXUASEBPEH5KKJ5UUXZX35IS/events.json","paper":"https://pith.science/paper/27DXUASE"},"agent_actions":{"view_html":"https://pith.science/pith/27DXUASEBPEH5KKJ5UUXZX35IS","download_json":"https://pith.science/pith/27DXUASEBPEH5KKJ5UUXZX35IS.json","view_paper":"https://pith.science/paper/27DXUASE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16931&json=true","fetch_graph":"https://pith.science/api/pith-number/27DXUASEBPEH5KKJ5UUXZX35IS/graph.json","fetch_events":"https://pith.science/api/pith-number/27DXUASEBPEH5KKJ5UUXZX35IS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/27DXUASEBPEH5KKJ5UUXZX35IS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/27DXUASEBPEH5KKJ5UUXZX35IS/action/storage_attestation","attest_author":"https://pith.science/pith/27DXUASEBPEH5KKJ5UUXZX35IS/action/author_attestation","sign_citation":"https://pith.science/pith/27DXUASEBPEH5KKJ5UUXZX35IS/action/citation_signature","submit_replication":"https://pith.science/pith/27DXUASEBPEH5KKJ5UUXZX35IS/action/replication_record"}},"created_at":"2026-07-05T08:47:59.356623+00:00","updated_at":"2026-07-05T08:47:59.356623+00:00"}