{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KTGEZH2FANLHKXFTR2HH4CDNUA","short_pith_number":"pith:KTGEZH2F","schema_version":"1.0","canonical_sha256":"54cc4c9f450356755cb38e8e7e086da02bcecc7733e6a3fa91cff34842e63f55","source":{"kind":"arxiv","id":"2606.21959","version":1},"attestation_state":"computed","paper":{"title":"OpenBioRQ: Unsolved Biomedical Research Questions for Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Minbyul Jeong","submitted_at":"2026-06-20T09:16:15Z","abstract_excerpt":"A working citation looks like proof -- but the fact that a link resolves does not mean the cited paper supports the claim. I find that current agentic models rarely fabricate citations (over $99\\%$ resolve), yet roughly $15.9\\%$ link to the wrong paper. Existing benchmarks miss this failure mode: when a question has a fixed answer key, a model can reproduce the expected source from that key rather than independently verifying that the source supports the claim. I introduce \\textbf{\\openbiorq{}}, a retrieval-grounded agentic benchmark of $12{,}553$ unsolved biomedical research questions across "},"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":"2606.21959","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-20T09:16:15Z","cross_cats_sorted":[],"title_canon_sha256":"d47ad2922bc346fabe6a190485ad10f4c2c6b8f1b46686b0d1cd868a93a89390","abstract_canon_sha256":"30c8f89f59c3f59bf5e1d57264387f23a9cb7aebaba02f4398052a70ff3976c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:04.255776Z","signature_b64":"hwh0ciDoKE65RiO4Ux4HdP4w64ul5q4Xn1CYBpisQQqMA50rjcGB2gEO0NfuAHGQMVuhtT/hQoAob6ALqvrVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54cc4c9f450356755cb38e8e7e086da02bcecc7733e6a3fa91cff34842e63f55","last_reissued_at":"2026-06-23T02:13:04.255434Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:04.255434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenBioRQ: Unsolved Biomedical Research Questions for Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Minbyul Jeong","submitted_at":"2026-06-20T09:16:15Z","abstract_excerpt":"A working citation looks like proof -- but the fact that a link resolves does not mean the cited paper supports the claim. I find that current agentic models rarely fabricate citations (over $99\\%$ resolve), yet roughly $15.9\\%$ link to the wrong paper. Existing benchmarks miss this failure mode: when a question has a fixed answer key, a model can reproduce the expected source from that key rather than independently verifying that the source supports the claim. I introduce \\textbf{\\openbiorq{}}, a retrieval-grounded agentic benchmark of $12{,}553$ unsolved biomedical research questions across "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21959","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/2606.21959/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":"2606.21959","created_at":"2026-06-23T02:13:04.255495+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21959v1","created_at":"2026-06-23T02:13:04.255495+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21959","created_at":"2026-06-23T02:13:04.255495+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTGEZH2FANLH","created_at":"2026-06-23T02:13:04.255495+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTGEZH2FANLHKXFT","created_at":"2026-06-23T02:13:04.255495+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTGEZH2F","created_at":"2026-06-23T02:13:04.255495+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/KTGEZH2FANLHKXFTR2HH4CDNUA","json":"https://pith.science/pith/KTGEZH2FANLHKXFTR2HH4CDNUA.json","graph_json":"https://pith.science/api/pith-number/KTGEZH2FANLHKXFTR2HH4CDNUA/graph.json","events_json":"https://pith.science/api/pith-number/KTGEZH2FANLHKXFTR2HH4CDNUA/events.json","paper":"https://pith.science/paper/KTGEZH2F"},"agent_actions":{"view_html":"https://pith.science/pith/KTGEZH2FANLHKXFTR2HH4CDNUA","download_json":"https://pith.science/pith/KTGEZH2FANLHKXFTR2HH4CDNUA.json","view_paper":"https://pith.science/paper/KTGEZH2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21959&json=true","fetch_graph":"https://pith.science/api/pith-number/KTGEZH2FANLHKXFTR2HH4CDNUA/graph.json","fetch_events":"https://pith.science/api/pith-number/KTGEZH2FANLHKXFTR2HH4CDNUA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTGEZH2FANLHKXFTR2HH4CDNUA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTGEZH2FANLHKXFTR2HH4CDNUA/action/storage_attestation","attest_author":"https://pith.science/pith/KTGEZH2FANLHKXFTR2HH4CDNUA/action/author_attestation","sign_citation":"https://pith.science/pith/KTGEZH2FANLHKXFTR2HH4CDNUA/action/citation_signature","submit_replication":"https://pith.science/pith/KTGEZH2FANLHKXFTR2HH4CDNUA/action/replication_record"}},"created_at":"2026-06-23T02:13:04.255495+00:00","updated_at":"2026-06-23T02:13:04.255495+00:00"}