{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TQDDZJRBAOFWL7EAXIK6QWEWX6","short_pith_number":"pith:TQDDZJRB","schema_version":"1.0","canonical_sha256":"9c063ca621038b65fc80ba15e85896bfa97947f16d36b0dd83c52d1bb3368a16","source":{"kind":"arxiv","id":"2506.00633","version":3},"attestation_state":"computed","paper":{"title":"From Alignment to Synthesis Contrastive Volumetric Grounding for Text-to-CT Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Camillo Maria Caruso, Daniele Molino, Filippo Ruffini, Paolo Soda, Valerio Guarrasi","submitted_at":"2025-05-31T16:41:55Z","abstract_excerpt":"Generating semantically controllable 3D CT volumes from radiology reports requires more than a rich text encoder, it requires vision-language alignment grounded in volumetric space. Existing Text-to-CT approaches condition generation on encoders pretrained with language only or 2D vision-language objectives, providing conditioning signals that are linguistically expressive but volumetrically blind. We argue this is a structural limitation: the quality of 3D vision-language alignment, not the richness of the text encoder, is the primary bottleneck for semantic controllability in volumetric diff"},"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":"2506.00633","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-31T16:41:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eb6366e0bba59c994e05577bbdefd875f7dd34bb551da7c760a41e797b2e425c","abstract_canon_sha256":"007386efbc331b0612d71a22c4374b1fc23a04d8490ca27e7e8607d3eab2321a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:19:58.835829Z","signature_b64":"71ZQSJQIC8LxUyneK1sJfuBj8YlhxlZfBqDZq2yWKxk4bBZ3G3YTA/LKcyElaJKo2SLFkci7NhElqB4YKL4IBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c063ca621038b65fc80ba15e85896bfa97947f16d36b0dd83c52d1bb3368a16","last_reissued_at":"2026-08-11T01:19:58.833024Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:19:58.833024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Alignment to Synthesis Contrastive Volumetric Grounding for Text-to-CT Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Camillo Maria Caruso, Daniele Molino, Filippo Ruffini, Paolo Soda, Valerio Guarrasi","submitted_at":"2025-05-31T16:41:55Z","abstract_excerpt":"Generating semantically controllable 3D CT volumes from radiology reports requires more than a rich text encoder, it requires vision-language alignment grounded in volumetric space. Existing Text-to-CT approaches condition generation on encoders pretrained with language only or 2D vision-language objectives, providing conditioning signals that are linguistically expressive but volumetrically blind. We argue this is a structural limitation: the quality of 3D vision-language alignment, not the richness of the text encoder, is the primary bottleneck for semantic controllability in volumetric diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00633","kind":"arxiv","version":3},"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/2506.00633/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":"2506.00633","created_at":"2026-08-11T01:19:58.833932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00633v3","created_at":"2026-08-11T01:19:58.833932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00633","created_at":"2026-08-11T01:19:58.833932+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQDDZJRBAOFW","created_at":"2026-08-11T01:19:58.833932+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQDDZJRBAOFWL7EA","created_at":"2026-08-11T01:19:58.833932+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQDDZJRB","created_at":"2026-08-11T01:19:58.833932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.00967","citing_title":"MedSyn2: Flexible Control of 3D CT Generation via Text and Semantically-Defined Segmentation Prompts","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2606.28980","citing_title":"Evidence-Based Text-Conditioned 3D CT Synthesis for Ovarian Cancer","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TQDDZJRBAOFWL7EAXIK6QWEWX6","json":"https://pith.science/pith/TQDDZJRBAOFWL7EAXIK6QWEWX6.json","graph_json":"https://pith.science/api/pith-number/TQDDZJRBAOFWL7EAXIK6QWEWX6/graph.json","events_json":"https://pith.science/api/pith-number/TQDDZJRBAOFWL7EAXIK6QWEWX6/events.json","paper":"https://pith.science/paper/TQDDZJRB"},"agent_actions":{"view_html":"https://pith.science/pith/TQDDZJRBAOFWL7EAXIK6QWEWX6","download_json":"https://pith.science/pith/TQDDZJRBAOFWL7EAXIK6QWEWX6.json","view_paper":"https://pith.science/paper/TQDDZJRB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00633&json=true","fetch_graph":"https://pith.science/api/pith-number/TQDDZJRBAOFWL7EAXIK6QWEWX6/graph.json","fetch_events":"https://pith.science/api/pith-number/TQDDZJRBAOFWL7EAXIK6QWEWX6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQDDZJRBAOFWL7EAXIK6QWEWX6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQDDZJRBAOFWL7EAXIK6QWEWX6/action/storage_attestation","attest_author":"https://pith.science/pith/TQDDZJRBAOFWL7EAXIK6QWEWX6/action/author_attestation","sign_citation":"https://pith.science/pith/TQDDZJRBAOFWL7EAXIK6QWEWX6/action/citation_signature","submit_replication":"https://pith.science/pith/TQDDZJRBAOFWL7EAXIK6QWEWX6/action/replication_record"}},"created_at":"2026-08-11T01:19:58.833932+00:00","updated_at":"2026-08-11T01:19:58.833932+00:00"}