{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RJ7GDQZZG5DP4QIUYHP6QZ5OYB","short_pith_number":"pith:RJ7GDQZZ","schema_version":"1.0","canonical_sha256":"8a7e61c3393746fe4114c1dfe867aec042a69033d24f36406e817cc18d0a4cdc","source":{"kind":"arxiv","id":"2606.08420","version":1},"attestation_state":"computed","paper":{"title":"CheXanatomy: Anatomy-Aware Vision-Language Modeling for Chest Radiographs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Bluethgen, Curtis Langlotz, Sergios Gatidis","submitted_at":"2026-06-07T02:41:05Z","abstract_excerpt":"Vision-language models (VLMs) pretrained on large-scale image-text pairs demonstrate strong image-level understanding, but are primarily optimized for global alignment and do not explicitly encode fine-grained anatomical structure, limiting their suitability for spatially precise tasks such as segmentation. We introduce CheXanatomy, a framework that integrates explicit anatomical knowledge into a pretrained VLM through autoregressive token-space supervision. Instead of adding task-specific decoder heads, the model is trained to generate anatomical segmentation masks via next-token prediction. "},"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":"2606.08420","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-07T02:41:05Z","cross_cats_sorted":[],"title_canon_sha256":"6e9148a8fc446a62feb8a2874bc86aa9c69162e87b433bc2ee944bc0394ec803","abstract_canon_sha256":"c7d63089077c91320f59fc9a1e531ca35b345b999f95797f4af63259cbc578b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:36.197035Z","signature_b64":"Jeflgrm/AdUVMuSJRHUQHZ2hBgf88Mo6QrrNJgRg/NQhJFYZr8Bz8vBYwsj16EF1n0iBVGnr7j9Yu3bv1V0GDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a7e61c3393746fe4114c1dfe867aec042a69033d24f36406e817cc18d0a4cdc","last_reissued_at":"2026-06-09T01:05:36.196618Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:36.196618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CheXanatomy: Anatomy-Aware Vision-Language Modeling for Chest Radiographs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Bluethgen, Curtis Langlotz, Sergios Gatidis","submitted_at":"2026-06-07T02:41:05Z","abstract_excerpt":"Vision-language models (VLMs) pretrained on large-scale image-text pairs demonstrate strong image-level understanding, but are primarily optimized for global alignment and do not explicitly encode fine-grained anatomical structure, limiting their suitability for spatially precise tasks such as segmentation. We introduce CheXanatomy, a framework that integrates explicit anatomical knowledge into a pretrained VLM through autoregressive token-space supervision. Instead of adding task-specific decoder heads, the model is trained to generate anatomical segmentation masks via next-token prediction. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08420","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/2606.08420/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":"2606.08420","created_at":"2026-06-09T01:05:36.196681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08420v1","created_at":"2026-06-09T01:05:36.196681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08420","created_at":"2026-06-09T01:05:36.196681+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJ7GDQZZG5DP","created_at":"2026-06-09T01:05:36.196681+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJ7GDQZZG5DP4QIU","created_at":"2026-06-09T01:05:36.196681+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJ7GDQZZ","created_at":"2026-06-09T01:05:36.196681+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/RJ7GDQZZG5DP4QIUYHP6QZ5OYB","json":"https://pith.science/pith/RJ7GDQZZG5DP4QIUYHP6QZ5OYB.json","graph_json":"https://pith.science/api/pith-number/RJ7GDQZZG5DP4QIUYHP6QZ5OYB/graph.json","events_json":"https://pith.science/api/pith-number/RJ7GDQZZG5DP4QIUYHP6QZ5OYB/events.json","paper":"https://pith.science/paper/RJ7GDQZZ"},"agent_actions":{"view_html":"https://pith.science/pith/RJ7GDQZZG5DP4QIUYHP6QZ5OYB","download_json":"https://pith.science/pith/RJ7GDQZZG5DP4QIUYHP6QZ5OYB.json","view_paper":"https://pith.science/paper/RJ7GDQZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08420&json=true","fetch_graph":"https://pith.science/api/pith-number/RJ7GDQZZG5DP4QIUYHP6QZ5OYB/graph.json","fetch_events":"https://pith.science/api/pith-number/RJ7GDQZZG5DP4QIUYHP6QZ5OYB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJ7GDQZZG5DP4QIUYHP6QZ5OYB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJ7GDQZZG5DP4QIUYHP6QZ5OYB/action/storage_attestation","attest_author":"https://pith.science/pith/RJ7GDQZZG5DP4QIUYHP6QZ5OYB/action/author_attestation","sign_citation":"https://pith.science/pith/RJ7GDQZZG5DP4QIUYHP6QZ5OYB/action/citation_signature","submit_replication":"https://pith.science/pith/RJ7GDQZZG5DP4QIUYHP6QZ5OYB/action/replication_record"}},"created_at":"2026-06-09T01:05:36.196681+00:00","updated_at":"2026-06-09T01:05:36.196681+00:00"}