{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VBJ2JWJOTI3TEXFZ3RHIF7VFG4","short_pith_number":"pith:VBJ2JWJO","schema_version":"1.0","canonical_sha256":"a853a4d92e9a37325cb9dc4e82fea53718f11687253aa290fd1932445d752c18","source":{"kind":"arxiv","id":"2507.20122","version":2},"attestation_state":"computed","paper":{"title":"From Prompt to Pipeline: Large Language Models for Scientific Workflow Development in Bioinformatics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Banani Roy, Khairul Alam","submitted_at":"2025-07-27T04:08:11Z","abstract_excerpt":"Scientific Workflow Systems such as Galaxy and Nextflow are essential for scalable, reproducible, and automated bioinformatics analyses. However, developing and understanding scientific workflows remains challenging for many domain scientists due to the complexity of tool/module selection, infrastructure requirements, and limited programming expertise. This study explores whether state-of-the-art Large Language Models such as GPT-4o, Gemini 2.5 Flash, and DeepSeek-V3 can assist in generating accurate, complete, and usable bioinformatics workflows. We evaluate a set of representative workflows "},"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":"2507.20122","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-27T04:08:11Z","cross_cats_sorted":[],"title_canon_sha256":"0d261ed751bfc4f5a705c6c82b2a4b9d35c89ede1b95b747be72a8c36f8dd994","abstract_canon_sha256":"31bb000c285581799de848e95c62d8c3510d2a43fab96ced8922a7696a9e5934"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:12.761582Z","signature_b64":"4He59hBJsmHxF+sf/rVtDl6JecjriQl9+F4dqoIGCwWmiz/Gt9Bzkr1dA+LLXsFsaF2cyO7aQF5JnbqQYXBdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a853a4d92e9a37325cb9dc4e82fea53718f11687253aa290fd1932445d752c18","last_reissued_at":"2026-07-05T11:54:12.761135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:12.761135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Prompt to Pipeline: Large Language Models for Scientific Workflow Development in Bioinformatics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Banani Roy, Khairul Alam","submitted_at":"2025-07-27T04:08:11Z","abstract_excerpt":"Scientific Workflow Systems such as Galaxy and Nextflow are essential for scalable, reproducible, and automated bioinformatics analyses. However, developing and understanding scientific workflows remains challenging for many domain scientists due to the complexity of tool/module selection, infrastructure requirements, and limited programming expertise. This study explores whether state-of-the-art Large Language Models such as GPT-4o, Gemini 2.5 Flash, and DeepSeek-V3 can assist in generating accurate, complete, and usable bioinformatics workflows. We evaluate a set of representative workflows "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20122","kind":"arxiv","version":2},"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/2507.20122/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":"2507.20122","created_at":"2026-07-05T11:54:12.761192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20122v2","created_at":"2026-07-05T11:54:12.761192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20122","created_at":"2026-07-05T11:54:12.761192+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBJ2JWJOTI3T","created_at":"2026-07-05T11:54:12.761192+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBJ2JWJOTI3TEXFZ","created_at":"2026-07-05T11:54:12.761192+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBJ2JWJO","created_at":"2026-07-05T11:54:12.761192+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/VBJ2JWJOTI3TEXFZ3RHIF7VFG4","json":"https://pith.science/pith/VBJ2JWJOTI3TEXFZ3RHIF7VFG4.json","graph_json":"https://pith.science/api/pith-number/VBJ2JWJOTI3TEXFZ3RHIF7VFG4/graph.json","events_json":"https://pith.science/api/pith-number/VBJ2JWJOTI3TEXFZ3RHIF7VFG4/events.json","paper":"https://pith.science/paper/VBJ2JWJO"},"agent_actions":{"view_html":"https://pith.science/pith/VBJ2JWJOTI3TEXFZ3RHIF7VFG4","download_json":"https://pith.science/pith/VBJ2JWJOTI3TEXFZ3RHIF7VFG4.json","view_paper":"https://pith.science/paper/VBJ2JWJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20122&json=true","fetch_graph":"https://pith.science/api/pith-number/VBJ2JWJOTI3TEXFZ3RHIF7VFG4/graph.json","fetch_events":"https://pith.science/api/pith-number/VBJ2JWJOTI3TEXFZ3RHIF7VFG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBJ2JWJOTI3TEXFZ3RHIF7VFG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBJ2JWJOTI3TEXFZ3RHIF7VFG4/action/storage_attestation","attest_author":"https://pith.science/pith/VBJ2JWJOTI3TEXFZ3RHIF7VFG4/action/author_attestation","sign_citation":"https://pith.science/pith/VBJ2JWJOTI3TEXFZ3RHIF7VFG4/action/citation_signature","submit_replication":"https://pith.science/pith/VBJ2JWJOTI3TEXFZ3RHIF7VFG4/action/replication_record"}},"created_at":"2026-07-05T11:54:12.761192+00:00","updated_at":"2026-07-05T11:54:12.761192+00:00"}