{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BJZ4MSW72WH53LTSQOMK7P7CAN","short_pith_number":"pith:BJZ4MSW7","schema_version":"1.0","canonical_sha256":"0a73c64adfd58fddae728398afbfe203546a58509c3e6a81d87112f1bda4f897","source":{"kind":"arxiv","id":"2502.13668","version":1},"attestation_state":"computed","paper":{"title":"PeerQA: A Scientific Question Answering Dataset from Peer Reviews","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Iryna Gurevych, Ted Briscoe, Tim Baumg\\\"artner","submitted_at":"2025-02-19T12:24:46Z","abstract_excerpt":"We present PeerQA, a real-world, scientific, document-level Question Answering (QA) dataset. PeerQA questions have been sourced from peer reviews, which contain questions that reviewers raised while thoroughly examining the scientific article. Answers have been annotated by the original authors of each paper. The dataset contains 579 QA pairs from 208 academic articles, with a majority from ML and NLP, as well as a subset of other scientific communities like Geoscience and Public Health. PeerQA supports three critical tasks for developing practical QA systems: Evidence retrieval, unanswerable "},"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":"2502.13668","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T12:24:46Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"103038b39ff31f23ff23b59c6e957fe6d20a8f9007885f9f656b73bfaffc3700","abstract_canon_sha256":"dae6389ac468a800d862c50ea158290fbd819877acbcf865c74d8a7a3605998b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:51.196061Z","signature_b64":"9BZFqkWGUFwz86wCNbYuQcR66Vp41J16pBwiVsLio5IijKHeW30c3wH2Upm637IhLBOcSsjCJUU5g1dEvqmUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a73c64adfd58fddae728398afbfe203546a58509c3e6a81d87112f1bda4f897","last_reissued_at":"2026-07-05T10:16:51.195584Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:51.195584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PeerQA: A Scientific Question Answering Dataset from Peer Reviews","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Iryna Gurevych, Ted Briscoe, Tim Baumg\\\"artner","submitted_at":"2025-02-19T12:24:46Z","abstract_excerpt":"We present PeerQA, a real-world, scientific, document-level Question Answering (QA) dataset. PeerQA questions have been sourced from peer reviews, which contain questions that reviewers raised while thoroughly examining the scientific article. Answers have been annotated by the original authors of each paper. The dataset contains 579 QA pairs from 208 academic articles, with a majority from ML and NLP, as well as a subset of other scientific communities like Geoscience and Public Health. PeerQA supports three critical tasks for developing practical QA systems: Evidence retrieval, unanswerable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13668","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/2502.13668/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":"2502.13668","created_at":"2026-07-05T10:16:51.195645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.13668v1","created_at":"2026-07-05T10:16:51.195645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13668","created_at":"2026-07-05T10:16:51.195645+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJZ4MSW72WH5","created_at":"2026-07-05T10:16:51.195645+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJZ4MSW72WH53LTS","created_at":"2026-07-05T10:16:51.195645+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJZ4MSW7","created_at":"2026-07-05T10:16:51.195645+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06650","citing_title":"LinkNav: Surfacing Interconnected Information in Scientific Articles","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2601.14289","citing_title":"RPC-Bench: A Fine-grained Benchmark for Research Paper Comprehension","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23321","citing_title":"MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21304","citing_title":"PaperMind: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJZ4MSW72WH53LTSQOMK7P7CAN","json":"https://pith.science/pith/BJZ4MSW72WH53LTSQOMK7P7CAN.json","graph_json":"https://pith.science/api/pith-number/BJZ4MSW72WH53LTSQOMK7P7CAN/graph.json","events_json":"https://pith.science/api/pith-number/BJZ4MSW72WH53LTSQOMK7P7CAN/events.json","paper":"https://pith.science/paper/BJZ4MSW7"},"agent_actions":{"view_html":"https://pith.science/pith/BJZ4MSW72WH53LTSQOMK7P7CAN","download_json":"https://pith.science/pith/BJZ4MSW72WH53LTSQOMK7P7CAN.json","view_paper":"https://pith.science/paper/BJZ4MSW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.13668&json=true","fetch_graph":"https://pith.science/api/pith-number/BJZ4MSW72WH53LTSQOMK7P7CAN/graph.json","fetch_events":"https://pith.science/api/pith-number/BJZ4MSW72WH53LTSQOMK7P7CAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJZ4MSW72WH53LTSQOMK7P7CAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJZ4MSW72WH53LTSQOMK7P7CAN/action/storage_attestation","attest_author":"https://pith.science/pith/BJZ4MSW72WH53LTSQOMK7P7CAN/action/author_attestation","sign_citation":"https://pith.science/pith/BJZ4MSW72WH53LTSQOMK7P7CAN/action/citation_signature","submit_replication":"https://pith.science/pith/BJZ4MSW72WH53LTSQOMK7P7CAN/action/replication_record"}},"created_at":"2026-07-05T10:16:51.195645+00:00","updated_at":"2026-07-05T10:16:51.195645+00:00"}