{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MUTIEFSHXQ76ZJXZ3XZPSLSGSH","short_pith_number":"pith:MUTIEFSH","schema_version":"1.0","canonical_sha256":"6526821647bc3feca6f9ddf2f92e4691cc5efa410ef4313e329aacd1765a24b3","source":{"kind":"arxiv","id":"1909.06146","version":1},"attestation_state":"computed","paper":{"title":"PubMedQA: A Dataset for Biomedical Research Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Bhuwan Dhingra, Qiao Jin, William W. Cohen, Xinghua Lu, Zhengping Liu","submitted_at":"2019-09-13T11:18:20Z","abstract_excerpt":"We introduce PubMedQA, a novel biomedical question answering (QA) dataset collected from PubMed abstracts. The task of PubMedQA is to answer research questions with yes/no/maybe (e.g.: Do preoperative statins reduce atrial fibrillation after coronary artery bypass grafting?) using the corresponding abstracts. PubMedQA has 1k expert-annotated, 61.2k unlabeled and 211.3k artificially generated QA instances. Each PubMedQA instance is composed of (1) a question which is either an existing research article title or derived from one, (2) a context which is the corresponding abstract without its conc"},"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":"1909.06146","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-13T11:18:20Z","cross_cats_sorted":["cs.LG","q-bio.QM"],"title_canon_sha256":"0a166d8073dacf0c70c257efdc89612264c463d71713c7da698d5d3ab364bdbf","abstract_canon_sha256":"0ed3df6b33953d68f1cae4f4d2e0b0042ff52a04648ffeb0bc1093c49f18fd5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-23T18:38:47.377624Z","signature_b64":"09py/K3JgXYnTJmpr2IY5WAHS8xoGunddYYdkMWeDx/RM8Uh2IZknIWKG1SthcGv5OzxgDplXXnWYRFCqPGLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6526821647bc3feca6f9ddf2f92e4691cc5efa410ef4313e329aacd1765a24b3","last_reissued_at":"2026-05-23T18:38:47.374057Z","signature_status":"signed_v1","first_computed_at":"2026-05-23T18:38:47.374057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PubMedQA: A Dataset for Biomedical Research Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Bhuwan Dhingra, Qiao Jin, William W. Cohen, Xinghua Lu, Zhengping Liu","submitted_at":"2019-09-13T11:18:20Z","abstract_excerpt":"We introduce PubMedQA, a novel biomedical question answering (QA) dataset collected from PubMed abstracts. The task of PubMedQA is to answer research questions with yes/no/maybe (e.g.: Do preoperative statins reduce atrial fibrillation after coronary artery bypass grafting?) using the corresponding abstracts. PubMedQA has 1k expert-annotated, 61.2k unlabeled and 211.3k artificially generated QA instances. Each PubMedQA instance is composed of (1) a question which is either an existing research article title or derived from one, (2) a context which is the corresponding abstract without its conc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.06146","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/1909.06146/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":"1909.06146","created_at":"2026-05-23T18:38:47.374257+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.06146v1","created_at":"2026-05-23T18:38:47.374257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.06146","created_at":"2026-05-23T18:38:47.374257+00:00"},{"alias_kind":"pith_short_12","alias_value":"MUTIEFSHXQ76","created_at":"2026-05-23T18:38:47.374257+00:00"},{"alias_kind":"pith_short_16","alias_value":"MUTIEFSHXQ76ZJXZ","created_at":"2026-05-23T18:38:47.374257+00:00"},{"alias_kind":"pith_short_8","alias_value":"MUTIEFSH","created_at":"2026-05-23T18:38:47.374257+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":26,"sample":[{"citing_arxiv_id":"2401.02458","citing_title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","ref_index":130,"is_internal_anchor":true},{"citing_arxiv_id":"2410.13903","citing_title":"CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2501.05465","citing_title":"Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2502.00270","citing_title":"DUET: Optimizing Training Data Mixtures via Feedback from Unseen Evaluation Tasks","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21949","citing_title":"Claim-Selective Certification for High-Risk Medical Retrieval-Augmented Generation","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22047","citing_title":"Active Evidence-Seeking and Diagnostic Reasoning in Large Language Models for Clinical Decision Support","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2405.07960","citing_title":"AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05974","citing_title":"PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16679","citing_title":"CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2406.07887","citing_title":"An Empirical Study of Mamba-based Language Models","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2510.17210","citing_title":"Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2601.03054","citing_title":"IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08549","citing_title":"VerifAI: A Verifiable Open-Source Search Engine for Biomedical Question Answering","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09554","citing_title":"LABBench2: An Improved Benchmark for AI Systems Performing Biology Research","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2303.13375","citing_title":"Capabilities of GPT-4 on Medical Challenge Problems","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2412.18925","citing_title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04759","citing_title":"Gyan: An Explainable Neuro-Symbolic Language Model","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2211.09085","citing_title":"Galactica: A Large Language Model for Science","ref_index":183,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10025","citing_title":"Medical Incident Causal Factors and Preventive Measures Generation Using Tag-based Example Selection in Few-shot Learning","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2402.03216","citing_title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","ref_index":73,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05974","citing_title":"PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04759","citing_title":"Gyan: An Explainable Neuro-Symbolic Language Model","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10316","citing_title":"Comparative Analysis of Large Language Models in Healthcare","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12384","citing_title":"Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06846","citing_title":"MedDialBench: Benchmarking LLM Diagnostic Robustness under Parametric Adversarial Patient Behaviors","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MUTIEFSHXQ76ZJXZ3XZPSLSGSH","json":"https://pith.science/pith/MUTIEFSHXQ76ZJXZ3XZPSLSGSH.json","graph_json":"https://pith.science/api/pith-number/MUTIEFSHXQ76ZJXZ3XZPSLSGSH/graph.json","events_json":"https://pith.science/api/pith-number/MUTIEFSHXQ76ZJXZ3XZPSLSGSH/events.json","paper":"https://pith.science/paper/MUTIEFSH"},"agent_actions":{"view_html":"https://pith.science/pith/MUTIEFSHXQ76ZJXZ3XZPSLSGSH","download_json":"https://pith.science/pith/MUTIEFSHXQ76ZJXZ3XZPSLSGSH.json","view_paper":"https://pith.science/paper/MUTIEFSH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.06146&json=true","fetch_graph":"https://pith.science/api/pith-number/MUTIEFSHXQ76ZJXZ3XZPSLSGSH/graph.json","fetch_events":"https://pith.science/api/pith-number/MUTIEFSHXQ76ZJXZ3XZPSLSGSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MUTIEFSHXQ76ZJXZ3XZPSLSGSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MUTIEFSHXQ76ZJXZ3XZPSLSGSH/action/storage_attestation","attest_author":"https://pith.science/pith/MUTIEFSHXQ76ZJXZ3XZPSLSGSH/action/author_attestation","sign_citation":"https://pith.science/pith/MUTIEFSHXQ76ZJXZ3XZPSLSGSH/action/citation_signature","submit_replication":"https://pith.science/pith/MUTIEFSHXQ76ZJXZ3XZPSLSGSH/action/replication_record"}},"created_at":"2026-05-23T18:38:47.374257+00:00","updated_at":"2026-05-23T18:38:47.374257+00:00"}