{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TOWQDR35P2TF2DTDKEG7HLSRYY","short_pith_number":"pith:TOWQDR35","schema_version":"1.0","canonical_sha256":"9bad01c77d7ea65d0e63510df3ae51c60ed8dd10d09432abe30486cd0a167289","source":{"kind":"arxiv","id":"2506.07591","version":1},"attestation_state":"computed","paper":{"title":"Automating Exploratory Multiomics Research via Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.AI","authors_text":"Bowen Zhou, Dong Li, Ermo Hua, Fuchu He, Kaiyan Zhang, Linhai Xie, Ning Ding, Shang Qu, Xingtai Lv, Yang Li, Yibai Xiong, Yifei Li, Youbang Sun, Yuxin Zuo, Zaoqu Liu, Zhangren Chen","submitted_at":"2025-06-09T09:44:21Z","abstract_excerpt":"This paper introduces PROTEUS, a fully automated system that produces data-driven hypotheses from raw data files. We apply PROTEUS to clinical proteogenomics, a field where effective downstream data analysis and hypothesis proposal is crucial for producing novel discoveries. PROTEUS uses separate modules to simulate different stages of the scientific process, from open-ended data exploration to specific statistical analysis and hypothesis proposal. It formulates research directions, tools, and results in terms of relationships between biological entities, using unified graph structures to mana"},"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":"2506.07591","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-09T09:44:21Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"1634a1976175b18defa9cff1e2626d95a63cfa6c8f9cc5267cc5406283f6419b","abstract_canon_sha256":"0354339096f93c63112c6b36cbd8fd608b301629b95c47a0add7d6c93bdd5b3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:29.994864Z","signature_b64":"Df7MICz/96IVM/9w6SmY3GWxSYgJMM6nf7t4NM5dWnBvRWv8bO2kFdD5C7eUJe+cDXoJsPXdRGZtw/sxHl8gBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bad01c77d7ea65d0e63510df3ae51c60ed8dd10d09432abe30486cd0a167289","last_reissued_at":"2026-07-05T11:18:29.994373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:29.994373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automating Exploratory Multiomics Research via Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.AI","authors_text":"Bowen Zhou, Dong Li, Ermo Hua, Fuchu He, Kaiyan Zhang, Linhai Xie, Ning Ding, Shang Qu, Xingtai Lv, Yang Li, Yibai Xiong, Yifei Li, Youbang Sun, Yuxin Zuo, Zaoqu Liu, Zhangren Chen","submitted_at":"2025-06-09T09:44:21Z","abstract_excerpt":"This paper introduces PROTEUS, a fully automated system that produces data-driven hypotheses from raw data files. We apply PROTEUS to clinical proteogenomics, a field where effective downstream data analysis and hypothesis proposal is crucial for producing novel discoveries. PROTEUS uses separate modules to simulate different stages of the scientific process, from open-ended data exploration to specific statistical analysis and hypothesis proposal. It formulates research directions, tools, and results in terms of relationships between biological entities, using unified graph structures to mana"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07591","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/2506.07591/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":"2506.07591","created_at":"2026-07-05T11:18:29.994432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07591v1","created_at":"2026-07-05T11:18:29.994432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07591","created_at":"2026-07-05T11:18:29.994432+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOWQDR35P2TF","created_at":"2026-07-05T11:18:29.994432+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOWQDR35P2TF2DTD","created_at":"2026-07-05T11:18:29.994432+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOWQDR35","created_at":"2026-07-05T11:18:29.994432+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/TOWQDR35P2TF2DTDKEG7HLSRYY","json":"https://pith.science/pith/TOWQDR35P2TF2DTDKEG7HLSRYY.json","graph_json":"https://pith.science/api/pith-number/TOWQDR35P2TF2DTDKEG7HLSRYY/graph.json","events_json":"https://pith.science/api/pith-number/TOWQDR35P2TF2DTDKEG7HLSRYY/events.json","paper":"https://pith.science/paper/TOWQDR35"},"agent_actions":{"view_html":"https://pith.science/pith/TOWQDR35P2TF2DTDKEG7HLSRYY","download_json":"https://pith.science/pith/TOWQDR35P2TF2DTDKEG7HLSRYY.json","view_paper":"https://pith.science/paper/TOWQDR35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07591&json=true","fetch_graph":"https://pith.science/api/pith-number/TOWQDR35P2TF2DTDKEG7HLSRYY/graph.json","fetch_events":"https://pith.science/api/pith-number/TOWQDR35P2TF2DTDKEG7HLSRYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOWQDR35P2TF2DTDKEG7HLSRYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOWQDR35P2TF2DTDKEG7HLSRYY/action/storage_attestation","attest_author":"https://pith.science/pith/TOWQDR35P2TF2DTDKEG7HLSRYY/action/author_attestation","sign_citation":"https://pith.science/pith/TOWQDR35P2TF2DTDKEG7HLSRYY/action/citation_signature","submit_replication":"https://pith.science/pith/TOWQDR35P2TF2DTDKEG7HLSRYY/action/replication_record"}},"created_at":"2026-07-05T11:18:29.994432+00:00","updated_at":"2026-07-05T11:18:29.994432+00:00"}