{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PRAMR5NZTCUPPTXTJTME3BCIFZ","short_pith_number":"pith:PRAMR5NZ","schema_version":"1.0","canonical_sha256":"7c40c8f5b998a8f7cef34cd84d84482e53adf993da0157bbd950609532bcf6a2","source":{"kind":"arxiv","id":"2607.14581","version":1},"attestation_state":"computed","paper":{"title":"Multi-LLM Collaborative MRI Report Generation for Visual Instruction Tuning in Brain Oncology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Hyunjin Park, Jonghun Kim, Sinyoung Ra","submitted_at":"2026-07-16T05:21:47Z","abstract_excerpt":"Recent advances in large language models (LLMs) and their extension to vision-language models (VLMs) have made it easier to combine text and images for tasks such as report generation. Existing VLMs in medicine typically focus on 2D images (chest X-rays), and their extension to 3D imaging has been difficult because of the lack of paired 3D imaging-text data. Thus, we introduce a new method for creating a 3D image-text dataset for brain oncology using 3D MRI scans of glioma and meningioma cases. We use a cooperative system in which several LLMs work together to generate and check reports, ensur"},"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":"2607.14581","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T05:21:47Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"aa8b8e841fdbb76aca74996574a06e52e645a181d60a52040ec3e9a531afadd2","abstract_canon_sha256":"666f0fa76bb0ca80dcb0f5249ff08eea0443dab1d1e5546240336d5f485edf98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:21:19.268044Z","signature_b64":"BYZ+IPAZKnqfAm0pl6fs6aRWHw79BIyGkToLw632XZqvY1hT5dGThUUTOm3qm9Nyvrun4+sRiWWON0pXJeWiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c40c8f5b998a8f7cef34cd84d84482e53adf993da0157bbd950609532bcf6a2","last_reissued_at":"2026-07-17T01:21:19.267325Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:21:19.267325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-LLM Collaborative MRI Report Generation for Visual Instruction Tuning in Brain Oncology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Hyunjin Park, Jonghun Kim, Sinyoung Ra","submitted_at":"2026-07-16T05:21:47Z","abstract_excerpt":"Recent advances in large language models (LLMs) and their extension to vision-language models (VLMs) have made it easier to combine text and images for tasks such as report generation. Existing VLMs in medicine typically focus on 2D images (chest X-rays), and their extension to 3D imaging has been difficult because of the lack of paired 3D imaging-text data. Thus, we introduce a new method for creating a 3D image-text dataset for brain oncology using 3D MRI scans of glioma and meningioma cases. We use a cooperative system in which several LLMs work together to generate and check reports, ensur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14581","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/2607.14581/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":"2607.14581","created_at":"2026-07-17T01:21:19.267724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14581v1","created_at":"2026-07-17T01:21:19.267724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14581","created_at":"2026-07-17T01:21:19.267724+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRAMR5NZTCUP","created_at":"2026-07-17T01:21:19.267724+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRAMR5NZTCUPPTXT","created_at":"2026-07-17T01:21:19.267724+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRAMR5NZ","created_at":"2026-07-17T01:21:19.267724+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/PRAMR5NZTCUPPTXTJTME3BCIFZ","json":"https://pith.science/pith/PRAMR5NZTCUPPTXTJTME3BCIFZ.json","graph_json":"https://pith.science/api/pith-number/PRAMR5NZTCUPPTXTJTME3BCIFZ/graph.json","events_json":"https://pith.science/api/pith-number/PRAMR5NZTCUPPTXTJTME3BCIFZ/events.json","paper":"https://pith.science/paper/PRAMR5NZ"},"agent_actions":{"view_html":"https://pith.science/pith/PRAMR5NZTCUPPTXTJTME3BCIFZ","download_json":"https://pith.science/pith/PRAMR5NZTCUPPTXTJTME3BCIFZ.json","view_paper":"https://pith.science/paper/PRAMR5NZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14581&json=true","fetch_graph":"https://pith.science/api/pith-number/PRAMR5NZTCUPPTXTJTME3BCIFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/PRAMR5NZTCUPPTXTJTME3BCIFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRAMR5NZTCUPPTXTJTME3BCIFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRAMR5NZTCUPPTXTJTME3BCIFZ/action/storage_attestation","attest_author":"https://pith.science/pith/PRAMR5NZTCUPPTXTJTME3BCIFZ/action/author_attestation","sign_citation":"https://pith.science/pith/PRAMR5NZTCUPPTXTJTME3BCIFZ/action/citation_signature","submit_replication":"https://pith.science/pith/PRAMR5NZTCUPPTXTJTME3BCIFZ/action/replication_record"}},"created_at":"2026-07-17T01:21:19.267724+00:00","updated_at":"2026-07-17T01:21:19.267724+00:00"}