{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ESM66PLMSL6GDOL5EQPYNKF52O","short_pith_number":"pith:ESM66PLM","schema_version":"1.0","canonical_sha256":"2499ef3d6c92fc61b97d241f86a8bdd3bafee6971f93907e49ba59e5a64d3a9d","source":{"kind":"arxiv","id":"2509.01554","version":1},"attestation_state":"computed","paper":{"title":"Unified Supervision For Vision-Language Modeling in 3D Computed Tomography","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hamza Ahmed, Hao-Chih Lee, Sean Huver, Spencer Kim, Timothy Deyer, Vishwesh Nath, Xueyan Mei, Zahi A. Fayad, ZeLong Liu","submitted_at":"2025-09-01T15:30:17Z","abstract_excerpt":"General-purpose vision-language models (VLMs) have emerged as promising tools in radiology, offering zero-shot capabilities that mitigate the need for large labeled datasets. However, in high-stakes domains like diagnostic radiology, these models often lack the discriminative precision required for reliable clinical use. This challenge is compounded by the scarcity and heterogeneity of publicly available volumetric CT datasets, which vary widely in annotation formats and granularity. To address these limitations, we introduce Uniferum, a volumetric VLM that unifies diverse supervision signals,"},"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":"2509.01554","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-01T15:30:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6d7db7792ffe39751a36672157fa0fb2a7ec17876937f5ec969e81b5fe2eb04a","abstract_canon_sha256":"7a410520404fc8dfa864eaa25e2a4b00e0ec123d48928589d334a3b2c21c57bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:03.097556Z","signature_b64":"aVXzLevXBrgL28mLR4xGUyvYPdi2ziajqD9e2QLFJUl+bM65iPXmP403rk2r2wMldkMHJeQJygy19ZQDZATjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2499ef3d6c92fc61b97d241f86a8bdd3bafee6971f93907e49ba59e5a64d3a9d","last_reissued_at":"2026-07-05T12:03:03.097007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:03.097007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Supervision For Vision-Language Modeling in 3D Computed Tomography","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hamza Ahmed, Hao-Chih Lee, Sean Huver, Spencer Kim, Timothy Deyer, Vishwesh Nath, Xueyan Mei, Zahi A. Fayad, ZeLong Liu","submitted_at":"2025-09-01T15:30:17Z","abstract_excerpt":"General-purpose vision-language models (VLMs) have emerged as promising tools in radiology, offering zero-shot capabilities that mitigate the need for large labeled datasets. However, in high-stakes domains like diagnostic radiology, these models often lack the discriminative precision required for reliable clinical use. This challenge is compounded by the scarcity and heterogeneity of publicly available volumetric CT datasets, which vary widely in annotation formats and granularity. To address these limitations, we introduce Uniferum, a volumetric VLM that unifies diverse supervision signals,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01554","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/2509.01554/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":"2509.01554","created_at":"2026-07-05T12:03:03.097075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01554v1","created_at":"2026-07-05T12:03:03.097075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01554","created_at":"2026-07-05T12:03:03.097075+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESM66PLMSL6G","created_at":"2026-07-05T12:03:03.097075+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESM66PLMSL6GDOL5","created_at":"2026-07-05T12:03:03.097075+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESM66PLM","created_at":"2026-07-05T12:03:03.097075+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22442","citing_title":"Efficient Multimodal Clinical Question Answering for Pulmonary Embolism Risk Assessment","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05460","citing_title":"ORACLE-CT: Anatomy-Aware Support Pooling for CT Classification","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ESM66PLMSL6GDOL5EQPYNKF52O","json":"https://pith.science/pith/ESM66PLMSL6GDOL5EQPYNKF52O.json","graph_json":"https://pith.science/api/pith-number/ESM66PLMSL6GDOL5EQPYNKF52O/graph.json","events_json":"https://pith.science/api/pith-number/ESM66PLMSL6GDOL5EQPYNKF52O/events.json","paper":"https://pith.science/paper/ESM66PLM"},"agent_actions":{"view_html":"https://pith.science/pith/ESM66PLMSL6GDOL5EQPYNKF52O","download_json":"https://pith.science/pith/ESM66PLMSL6GDOL5EQPYNKF52O.json","view_paper":"https://pith.science/paper/ESM66PLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01554&json=true","fetch_graph":"https://pith.science/api/pith-number/ESM66PLMSL6GDOL5EQPYNKF52O/graph.json","fetch_events":"https://pith.science/api/pith-number/ESM66PLMSL6GDOL5EQPYNKF52O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESM66PLMSL6GDOL5EQPYNKF52O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESM66PLMSL6GDOL5EQPYNKF52O/action/storage_attestation","attest_author":"https://pith.science/pith/ESM66PLMSL6GDOL5EQPYNKF52O/action/author_attestation","sign_citation":"https://pith.science/pith/ESM66PLMSL6GDOL5EQPYNKF52O/action/citation_signature","submit_replication":"https://pith.science/pith/ESM66PLMSL6GDOL5EQPYNKF52O/action/replication_record"}},"created_at":"2026-07-05T12:03:03.097075+00:00","updated_at":"2026-07-05T12:03:03.097075+00:00"}