{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NIZXN6QA4I3B4VSE6QYORBWKNT","short_pith_number":"pith:NIZXN6QA","schema_version":"1.0","canonical_sha256":"6a3376fa00e2361e5644f430e886ca6ce2217d8bc8a2b4eab8a69b1c161eff7a","source":{"kind":"arxiv","id":"2606.00902","version":1},"attestation_state":"computed","paper":{"title":"Ryze: Evidence-Enriched Data Synthesis from Biomedical Papers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guanhao Su, Luo Mai, Yanwei Ye, Yeqi Huang, Yue Chen","submitted_at":"2026-05-30T21:54:02Z","abstract_excerpt":"General-purpose VLMs remain unreliable for biomedical research because valid answers in scientific papers depend on evidence split across figures, tables, charts, captions, and referring text. Existing post-training pipelines are bottlenecked by costly expert annotation and by synthetic data that drops this evidence structure. We present Ryze, a fully automated system that converts raw biomedical papers into an evidence-enriched training set and a domain-specialized VLM. Ryze synthesizes QA pairs with complete supporting evidence (visual element, caption, extracted structure, and referring par"},"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":"2606.00902","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-30T21:54:02Z","cross_cats_sorted":[],"title_canon_sha256":"7194904214d9fe4b0349759d81d361c89e8a51a65a2b2a364673ead6c28a61b9","abstract_canon_sha256":"369208c8fb3c582e2172883f0123837784fe73e116fcc402ceaec926c09281ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:09.149589Z","signature_b64":"X5UUBh7qcPCJjkc0MNSeQT0uhF8p9ZEY2vK3P75OspVofiE68ECFYhn81yyqygij2FxMzpb/QYg1zDThhxGZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a3376fa00e2361e5644f430e886ca6ce2217d8bc8a2b4eab8a69b1c161eff7a","last_reissued_at":"2026-06-02T01:04:09.149150Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:09.149150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ryze: Evidence-Enriched Data Synthesis from Biomedical Papers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guanhao Su, Luo Mai, Yanwei Ye, Yeqi Huang, Yue Chen","submitted_at":"2026-05-30T21:54:02Z","abstract_excerpt":"General-purpose VLMs remain unreliable for biomedical research because valid answers in scientific papers depend on evidence split across figures, tables, charts, captions, and referring text. Existing post-training pipelines are bottlenecked by costly expert annotation and by synthetic data that drops this evidence structure. We present Ryze, a fully automated system that converts raw biomedical papers into an evidence-enriched training set and a domain-specialized VLM. Ryze synthesizes QA pairs with complete supporting evidence (visual element, caption, extracted structure, and referring par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00902","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/2606.00902/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":"2606.00902","created_at":"2026-06-02T01:04:09.149207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00902v1","created_at":"2026-06-02T01:04:09.149207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00902","created_at":"2026-06-02T01:04:09.149207+00:00"},{"alias_kind":"pith_short_12","alias_value":"NIZXN6QA4I3B","created_at":"2026-06-02T01:04:09.149207+00:00"},{"alias_kind":"pith_short_16","alias_value":"NIZXN6QA4I3B4VSE","created_at":"2026-06-02T01:04:09.149207+00:00"},{"alias_kind":"pith_short_8","alias_value":"NIZXN6QA","created_at":"2026-06-02T01:04:09.149207+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/NIZXN6QA4I3B4VSE6QYORBWKNT","json":"https://pith.science/pith/NIZXN6QA4I3B4VSE6QYORBWKNT.json","graph_json":"https://pith.science/api/pith-number/NIZXN6QA4I3B4VSE6QYORBWKNT/graph.json","events_json":"https://pith.science/api/pith-number/NIZXN6QA4I3B4VSE6QYORBWKNT/events.json","paper":"https://pith.science/paper/NIZXN6QA"},"agent_actions":{"view_html":"https://pith.science/pith/NIZXN6QA4I3B4VSE6QYORBWKNT","download_json":"https://pith.science/pith/NIZXN6QA4I3B4VSE6QYORBWKNT.json","view_paper":"https://pith.science/paper/NIZXN6QA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00902&json=true","fetch_graph":"https://pith.science/api/pith-number/NIZXN6QA4I3B4VSE6QYORBWKNT/graph.json","fetch_events":"https://pith.science/api/pith-number/NIZXN6QA4I3B4VSE6QYORBWKNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NIZXN6QA4I3B4VSE6QYORBWKNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NIZXN6QA4I3B4VSE6QYORBWKNT/action/storage_attestation","attest_author":"https://pith.science/pith/NIZXN6QA4I3B4VSE6QYORBWKNT/action/author_attestation","sign_citation":"https://pith.science/pith/NIZXN6QA4I3B4VSE6QYORBWKNT/action/citation_signature","submit_replication":"https://pith.science/pith/NIZXN6QA4I3B4VSE6QYORBWKNT/action/replication_record"}},"created_at":"2026-06-02T01:04:09.149207+00:00","updated_at":"2026-06-02T01:04:09.149207+00:00"}