{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CT3737HE3XEA7KU25WAV7M5MXN","short_pith_number":"pith:CT3737HE","schema_version":"1.0","canonical_sha256":"14f7fdfce4ddc80faa9aed815fb3acbb695bbdab3b7bbb265a8ec02c384e3667","source":{"kind":"arxiv","id":"2501.03482","version":1},"attestation_state":"computed","paper":{"title":"VOILA: Complexity-Aware Universal Segmentation of CT images by Voxel Interacting with Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dawei Ding, Wanyuan Pang, Yu Gao, Zishuo Wan","submitted_at":"2025-01-07T03:00:58Z","abstract_excerpt":"Satisfactory progress has been achieved recently in universal segmentation of CT images. Following the success of vision-language methods, there is a growing trend towards utilizing text prompts and contrastive learning to develop universal segmentation models. However, there exists a significant imbalance in information density between 3D images and text prompts. Moreover, the standard fully connected layer segmentation approach faces significant challenges in handling multiple classes and exhibits poor generalizability. To address these challenges, we propose the VOxel Interacting with LAngu"},"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":"2501.03482","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T03:00:58Z","cross_cats_sorted":[],"title_canon_sha256":"137171c1dc877b060215f1f89d64cbee2f9233f769466eb0c002e0f5a557974d","abstract_canon_sha256":"ef7573643cea5773f4ecd7177aa1ff0fcff4a787b2f4bbc8be6a16d38ab39a67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:55.474612Z","signature_b64":"NHfwWPl3pro8qcJQXVo3e9VgOMI3D6lFhoKjDCF/mhPpCfGKFP/kIqvFV+p4C5LVTC/sMJXTlJKKohQmr/RbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14f7fdfce4ddc80faa9aed815fb3acbb695bbdab3b7bbb265a8ec02c384e3667","last_reissued_at":"2026-07-05T09:57:55.474140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:55.474140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VOILA: Complexity-Aware Universal Segmentation of CT images by Voxel Interacting with Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dawei Ding, Wanyuan Pang, Yu Gao, Zishuo Wan","submitted_at":"2025-01-07T03:00:58Z","abstract_excerpt":"Satisfactory progress has been achieved recently in universal segmentation of CT images. Following the success of vision-language methods, there is a growing trend towards utilizing text prompts and contrastive learning to develop universal segmentation models. However, there exists a significant imbalance in information density between 3D images and text prompts. Moreover, the standard fully connected layer segmentation approach faces significant challenges in handling multiple classes and exhibits poor generalizability. To address these challenges, we propose the VOxel Interacting with LAngu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03482","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/2501.03482/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":"2501.03482","created_at":"2026-07-05T09:57:55.474203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03482v1","created_at":"2026-07-05T09:57:55.474203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03482","created_at":"2026-07-05T09:57:55.474203+00:00"},{"alias_kind":"pith_short_12","alias_value":"CT3737HE3XEA","created_at":"2026-07-05T09:57:55.474203+00:00"},{"alias_kind":"pith_short_16","alias_value":"CT3737HE3XEA7KU2","created_at":"2026-07-05T09:57:55.474203+00:00"},{"alias_kind":"pith_short_8","alias_value":"CT3737HE","created_at":"2026-07-05T09:57:55.474203+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/CT3737HE3XEA7KU25WAV7M5MXN","json":"https://pith.science/pith/CT3737HE3XEA7KU25WAV7M5MXN.json","graph_json":"https://pith.science/api/pith-number/CT3737HE3XEA7KU25WAV7M5MXN/graph.json","events_json":"https://pith.science/api/pith-number/CT3737HE3XEA7KU25WAV7M5MXN/events.json","paper":"https://pith.science/paper/CT3737HE"},"agent_actions":{"view_html":"https://pith.science/pith/CT3737HE3XEA7KU25WAV7M5MXN","download_json":"https://pith.science/pith/CT3737HE3XEA7KU25WAV7M5MXN.json","view_paper":"https://pith.science/paper/CT3737HE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03482&json=true","fetch_graph":"https://pith.science/api/pith-number/CT3737HE3XEA7KU25WAV7M5MXN/graph.json","fetch_events":"https://pith.science/api/pith-number/CT3737HE3XEA7KU25WAV7M5MXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CT3737HE3XEA7KU25WAV7M5MXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CT3737HE3XEA7KU25WAV7M5MXN/action/storage_attestation","attest_author":"https://pith.science/pith/CT3737HE3XEA7KU25WAV7M5MXN/action/author_attestation","sign_citation":"https://pith.science/pith/CT3737HE3XEA7KU25WAV7M5MXN/action/citation_signature","submit_replication":"https://pith.science/pith/CT3737HE3XEA7KU25WAV7M5MXN/action/replication_record"}},"created_at":"2026-07-05T09:57:55.474203+00:00","updated_at":"2026-07-05T09:57:55.474203+00:00"}