{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RKNGIOBPUX2IVCIACOC4NTGM4P","short_pith_number":"pith:RKNGIOBP","schema_version":"1.0","canonical_sha256":"8a9a64382fa5f48a89001385c6cccce3cccea73dedfe6e1a66a5573740828ab2","source":{"kind":"arxiv","id":"2608.03890","version":1},"attestation_state":"computed","paper":{"title":"CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Abhyuday Kumara Swamy, Anirban Porya, Mercy Prasanna Ranjit, Niharika Vadlamudi, Nikhilesh Chowdary Eathamukkala, Pradeep Narayan, Pranay Narhari Umredkar, Prasanth V V, Sathvik Joel, Tanuja Ganu, Vivek Rajagopal","submitted_at":"2026-08-04T16:23:39Z","abstract_excerpt":"A clinically useful chest X-ray system must go beyond fluent report generation: it should classify findings with tunable decision thresholds, localize them spatially, and derive the anatomical measurements upon which many diagnoses depend. Today's Vision-Language Models (VLMs) treat these as separate problems, if they address them at all, leaving a gap between what radiologists need and what generative models provide. We introduce CARE-X, a chest X-ray VLM that narrows this gap by unifying auxiliary discriminative supervision with reward-aligned generation. CARE-X augments its generative backb"},"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":"2608.03890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T16:23:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8a073d7bb9945f809b54c13cff502d7b6fa14f5c43af78bddc179452e8b8a452","abstract_canon_sha256":"6524f72263f0833d15086b8c4701aceacbf0a8eb43f0b465a12ed8f5ece5c61f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:37:19.800249Z","signature_b64":"5bRTw3dfehoQvIdESnjVrcra2KnoemQzWWeLw4/oJJVxmn2yX1uqVK/F5G52YLt/gR9hezQQ1VEZrRF1wmR/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a9a64382fa5f48a89001385c6cccce3cccea73dedfe6e1a66a5573740828ab2","last_reissued_at":"2026-08-05T01:37:19.798691Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:37:19.798691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Abhyuday Kumara Swamy, Anirban Porya, Mercy Prasanna Ranjit, Niharika Vadlamudi, Nikhilesh Chowdary Eathamukkala, Pradeep Narayan, Pranay Narhari Umredkar, Prasanth V V, Sathvik Joel, Tanuja Ganu, Vivek Rajagopal","submitted_at":"2026-08-04T16:23:39Z","abstract_excerpt":"A clinically useful chest X-ray system must go beyond fluent report generation: it should classify findings with tunable decision thresholds, localize them spatially, and derive the anatomical measurements upon which many diagnoses depend. Today's Vision-Language Models (VLMs) treat these as separate problems, if they address them at all, leaving a gap between what radiologists need and what generative models provide. We introduce CARE-X, a chest X-ray VLM that narrows this gap by unifying auxiliary discriminative supervision with reward-aligned generation. CARE-X augments its generative backb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03890","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/2608.03890/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":"2608.03890","created_at":"2026-08-05T01:37:19.799206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03890v1","created_at":"2026-08-05T01:37:19.799206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03890","created_at":"2026-08-05T01:37:19.799206+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKNGIOBPUX2I","created_at":"2026-08-05T01:37:19.799206+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKNGIOBPUX2IVCIA","created_at":"2026-08-05T01:37:19.799206+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKNGIOBP","created_at":"2026-08-05T01:37:19.799206+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/RKNGIOBPUX2IVCIACOC4NTGM4P","json":"https://pith.science/pith/RKNGIOBPUX2IVCIACOC4NTGM4P.json","graph_json":"https://pith.science/api/pith-number/RKNGIOBPUX2IVCIACOC4NTGM4P/graph.json","events_json":"https://pith.science/api/pith-number/RKNGIOBPUX2IVCIACOC4NTGM4P/events.json","paper":"https://pith.science/paper/RKNGIOBP"},"agent_actions":{"view_html":"https://pith.science/pith/RKNGIOBPUX2IVCIACOC4NTGM4P","download_json":"https://pith.science/pith/RKNGIOBPUX2IVCIACOC4NTGM4P.json","view_paper":"https://pith.science/paper/RKNGIOBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03890&json=true","fetch_graph":"https://pith.science/api/pith-number/RKNGIOBPUX2IVCIACOC4NTGM4P/graph.json","fetch_events":"https://pith.science/api/pith-number/RKNGIOBPUX2IVCIACOC4NTGM4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKNGIOBPUX2IVCIACOC4NTGM4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKNGIOBPUX2IVCIACOC4NTGM4P/action/storage_attestation","attest_author":"https://pith.science/pith/RKNGIOBPUX2IVCIACOC4NTGM4P/action/author_attestation","sign_citation":"https://pith.science/pith/RKNGIOBPUX2IVCIACOC4NTGM4P/action/citation_signature","submit_replication":"https://pith.science/pith/RKNGIOBPUX2IVCIACOC4NTGM4P/action/replication_record"}},"created_at":"2026-08-05T01:37:19.799206+00:00","updated_at":"2026-08-05T01:37:19.799206+00:00"}