{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PCRT2ADLJYTTPFYRBHPQR3IFP6","short_pith_number":"pith:PCRT2ADL","schema_version":"1.0","canonical_sha256":"78a33d006b4e2737971109df08ed057fb59d30299b55500019c75bcd0a780c3a","source":{"kind":"arxiv","id":"2404.15770","version":2},"attestation_state":"computed","paper":{"title":"ChEX: Interactive Localization and Region Description in Chest X-rays","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Daniel Rueckert, Georgios Kaissis, Philip M\\\"uller","submitted_at":"2024-04-24T09:44:44Z","abstract_excerpt":"Report generation models offer fine-grained textual interpretations of medical images like chest X-rays, yet they often lack interactivity (i.e. the ability to steer the generation process through user queries) and localized interpretability (i.e. visually grounding their predictions), which we deem essential for future adoption in clinical practice. While there have been efforts to tackle these issues, they are either limited in their interactivity by not supporting textual queries or fail to also offer localized interpretability. Therefore, we propose a novel multitask architecture and train"},"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":"2404.15770","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-24T09:44:44Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"5493483e725c05564133fde6e8e7bbcff5164551ced376c745ad6894415092cb","abstract_canon_sha256":"7e68925373b4b807ca5b3a03c0ec9a400bb1fd48b8895cf8ef7291ddf0af4e7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:55.393969Z","signature_b64":"bDeMuIFxqH7l+pHqcqPMESXbeIZNSI4mS/RUQJnmz4JV9ugRW8Di+vYLRlvQ5wmoOtJrZq6NBchykSVCCJS2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78a33d006b4e2737971109df08ed057fb59d30299b55500019c75bcd0a780c3a","last_reissued_at":"2026-07-05T08:43:55.393552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:55.393552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChEX: Interactive Localization and Region Description in Chest X-rays","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Daniel Rueckert, Georgios Kaissis, Philip M\\\"uller","submitted_at":"2024-04-24T09:44:44Z","abstract_excerpt":"Report generation models offer fine-grained textual interpretations of medical images like chest X-rays, yet they often lack interactivity (i.e. the ability to steer the generation process through user queries) and localized interpretability (i.e. visually grounding their predictions), which we deem essential for future adoption in clinical practice. While there have been efforts to tackle these issues, they are either limited in their interactivity by not supporting textual queries or fail to also offer localized interpretability. Therefore, we propose a novel multitask architecture and train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15770","kind":"arxiv","version":2},"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/2404.15770/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":"2404.15770","created_at":"2026-07-05T08:43:55.393602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.15770v2","created_at":"2026-07-05T08:43:55.393602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15770","created_at":"2026-07-05T08:43:55.393602+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCRT2ADLJYTT","created_at":"2026-07-05T08:43:55.393602+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCRT2ADLJYTTPFYR","created_at":"2026-07-05T08:43:55.393602+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCRT2ADL","created_at":"2026-07-05T08:43:55.393602+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03890","citing_title":"CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement","ref_index":76,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PCRT2ADLJYTTPFYRBHPQR3IFP6","json":"https://pith.science/pith/PCRT2ADLJYTTPFYRBHPQR3IFP6.json","graph_json":"https://pith.science/api/pith-number/PCRT2ADLJYTTPFYRBHPQR3IFP6/graph.json","events_json":"https://pith.science/api/pith-number/PCRT2ADLJYTTPFYRBHPQR3IFP6/events.json","paper":"https://pith.science/paper/PCRT2ADL"},"agent_actions":{"view_html":"https://pith.science/pith/PCRT2ADLJYTTPFYRBHPQR3IFP6","download_json":"https://pith.science/pith/PCRT2ADLJYTTPFYRBHPQR3IFP6.json","view_paper":"https://pith.science/paper/PCRT2ADL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.15770&json=true","fetch_graph":"https://pith.science/api/pith-number/PCRT2ADLJYTTPFYRBHPQR3IFP6/graph.json","fetch_events":"https://pith.science/api/pith-number/PCRT2ADLJYTTPFYRBHPQR3IFP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCRT2ADLJYTTPFYRBHPQR3IFP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCRT2ADLJYTTPFYRBHPQR3IFP6/action/storage_attestation","attest_author":"https://pith.science/pith/PCRT2ADLJYTTPFYRBHPQR3IFP6/action/author_attestation","sign_citation":"https://pith.science/pith/PCRT2ADLJYTTPFYRBHPQR3IFP6/action/citation_signature","submit_replication":"https://pith.science/pith/PCRT2ADLJYTTPFYRBHPQR3IFP6/action/replication_record"}},"created_at":"2026-07-05T08:43:55.393602+00:00","updated_at":"2026-07-05T08:43:55.393602+00:00"}