{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VVRFA3TGT6ET2BSW2WBD6MSDFX","short_pith_number":"pith:VVRFA3TG","schema_version":"1.0","canonical_sha256":"ad62506e669f893d0656d5823f32432dd3e3f8f03801aade7e90ceeacadb377a","source":{"kind":"arxiv","id":"2503.02948","version":1},"attestation_state":"computed","paper":{"title":"ExpertGenQA: Open-ended QA generation in Specialized Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Chansong Lim, Evangelos E. Papalexakis, Haz Sameen Shahgir, Jia Chen, Yue Dong","submitted_at":"2025-03-04T19:09:48Z","abstract_excerpt":"Generating high-quality question-answer pairs for specialized technical domains remains challenging, with existing approaches facing a tradeoff between leveraging expert examples and achieving topical diversity. We present ExpertGenQA, a protocol that combines few-shot learning with structured topic and style categorization to generate comprehensive domain-specific QA pairs. Using U.S. Federal Railroad Administration documents as a test bed, we demonstrate that ExpertGenQA achieves twice the efficiency of baseline few-shot approaches while maintaining $94.4\\%$ topic coverage. Through systemati"},"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":"2503.02948","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-04T19:09:48Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"8eae71a9ec5b6940880dca05a0c275101c0a40450124dc9281e24e833c9801bb","abstract_canon_sha256":"b6dea3a1eaad47aad7a5f7a39f1b1e9d750d75b61686f9416bee9ea5b419f506"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:35.601689Z","signature_b64":"tGkBBdqfBR2YuaJF19b670s3o0tX7LEeDfdbqIKV7o9uIzgdeGnNDZMs9ErDIJnK3EoZoYDbeLlyH5TDhyYGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad62506e669f893d0656d5823f32432dd3e3f8f03801aade7e90ceeacadb377a","last_reissued_at":"2026-07-05T10:24:35.601151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:35.601151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ExpertGenQA: Open-ended QA generation in Specialized Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Chansong Lim, Evangelos E. Papalexakis, Haz Sameen Shahgir, Jia Chen, Yue Dong","submitted_at":"2025-03-04T19:09:48Z","abstract_excerpt":"Generating high-quality question-answer pairs for specialized technical domains remains challenging, with existing approaches facing a tradeoff between leveraging expert examples and achieving topical diversity. We present ExpertGenQA, a protocol that combines few-shot learning with structured topic and style categorization to generate comprehensive domain-specific QA pairs. Using U.S. Federal Railroad Administration documents as a test bed, we demonstrate that ExpertGenQA achieves twice the efficiency of baseline few-shot approaches while maintaining $94.4\\%$ topic coverage. Through systemati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02948","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/2503.02948/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":"2503.02948","created_at":"2026-07-05T10:24:35.601214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02948v1","created_at":"2026-07-05T10:24:35.601214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02948","created_at":"2026-07-05T10:24:35.601214+00:00"},{"alias_kind":"pith_short_12","alias_value":"VVRFA3TGT6ET","created_at":"2026-07-05T10:24:35.601214+00:00"},{"alias_kind":"pith_short_16","alias_value":"VVRFA3TGT6ET2BSW","created_at":"2026-07-05T10:24:35.601214+00:00"},{"alias_kind":"pith_short_8","alias_value":"VVRFA3TG","created_at":"2026-07-05T10:24:35.601214+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VVRFA3TGT6ET2BSW2WBD6MSDFX","json":"https://pith.science/pith/VVRFA3TGT6ET2BSW2WBD6MSDFX.json","graph_json":"https://pith.science/api/pith-number/VVRFA3TGT6ET2BSW2WBD6MSDFX/graph.json","events_json":"https://pith.science/api/pith-number/VVRFA3TGT6ET2BSW2WBD6MSDFX/events.json","paper":"https://pith.science/paper/VVRFA3TG"},"agent_actions":{"view_html":"https://pith.science/pith/VVRFA3TGT6ET2BSW2WBD6MSDFX","download_json":"https://pith.science/pith/VVRFA3TGT6ET2BSW2WBD6MSDFX.json","view_paper":"https://pith.science/paper/VVRFA3TG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02948&json=true","fetch_graph":"https://pith.science/api/pith-number/VVRFA3TGT6ET2BSW2WBD6MSDFX/graph.json","fetch_events":"https://pith.science/api/pith-number/VVRFA3TGT6ET2BSW2WBD6MSDFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VVRFA3TGT6ET2BSW2WBD6MSDFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VVRFA3TGT6ET2BSW2WBD6MSDFX/action/storage_attestation","attest_author":"https://pith.science/pith/VVRFA3TGT6ET2BSW2WBD6MSDFX/action/author_attestation","sign_citation":"https://pith.science/pith/VVRFA3TGT6ET2BSW2WBD6MSDFX/action/citation_signature","submit_replication":"https://pith.science/pith/VVRFA3TGT6ET2BSW2WBD6MSDFX/action/replication_record"}},"created_at":"2026-07-05T10:24:35.601214+00:00","updated_at":"2026-07-05T10:24:35.601214+00:00"}