{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5BUXAITNPCRGUDKMJJNSHT4LTJ","short_pith_number":"pith:5BUXAITN","schema_version":"1.0","canonical_sha256":"e86970226d78a26a0d4c4a5b23cf8b9a6af546a169e61957280992ed25808e3d","source":{"kind":"arxiv","id":"2311.10798","version":1},"attestation_state":"computed","paper":{"title":"INSPECT: A Multimodal Dataset for Pulmonary Embolism Diagnosis and Prognosis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","eess.IV"],"primary_cat":"cs.LG","authors_text":"Chia-Chun Chiang, Curtis P. Langlotz, Ethan Steinberg, Jason A. Fries, Matthew P. Lungren, Nigam H. Shah, Serena Yeung, Shih-Cheng Huang, Zepeng Huo","submitted_at":"2023-11-17T07:28:16Z","abstract_excerpt":"Synthesizing information from multiple data sources plays a crucial role in the practice of modern medicine. Current applications of artificial intelligence in medicine often focus on single-modality data due to a lack of publicly available, multimodal medical datasets. To address this limitation, we introduce INSPECT, which contains de-identified longitudinal records from a large cohort of patients at risk for pulmonary embolism (PE), along with ground truth labels for multiple outcomes. INSPECT contains data from 19,402 patients, including CT images, radiology report impression sections, and"},"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":"2311.10798","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-17T07:28:16Z","cross_cats_sorted":["cs.AI","cs.CV","eess.IV"],"title_canon_sha256":"b63a84105a03031849c30ee2910ae70f3caaa1fc3356d368bd027b0a9b46f4ce","abstract_canon_sha256":"837cab1387479a611413bdb6ea3ebbe5743529f7aeb1c9f0181bce502f103a85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:22.424854Z","signature_b64":"nqggk/0SFgU82CyQEHzJE0BRwsxRYRqlluUPVoDIMQ3FAzADcxCGpsERfnQm4BeNTc/1V+uLLoHwnJJJb6eEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e86970226d78a26a0d4c4a5b23cf8b9a6af546a169e61957280992ed25808e3d","last_reissued_at":"2026-07-05T07:14:22.424392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:22.424392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"INSPECT: A Multimodal Dataset for Pulmonary Embolism Diagnosis and Prognosis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","eess.IV"],"primary_cat":"cs.LG","authors_text":"Chia-Chun Chiang, Curtis P. Langlotz, Ethan Steinberg, Jason A. Fries, Matthew P. Lungren, Nigam H. Shah, Serena Yeung, Shih-Cheng Huang, Zepeng Huo","submitted_at":"2023-11-17T07:28:16Z","abstract_excerpt":"Synthesizing information from multiple data sources plays a crucial role in the practice of modern medicine. Current applications of artificial intelligence in medicine often focus on single-modality data due to a lack of publicly available, multimodal medical datasets. To address this limitation, we introduce INSPECT, which contains de-identified longitudinal records from a large cohort of patients at risk for pulmonary embolism (PE), along with ground truth labels for multiple outcomes. INSPECT contains data from 19,402 patients, including CT images, radiology report impression sections, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10798","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/2311.10798/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":"2311.10798","created_at":"2026-07-05T07:14:22.424453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.10798v1","created_at":"2026-07-05T07:14:22.424453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10798","created_at":"2026-07-05T07:14:22.424453+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BUXAITNPCRG","created_at":"2026-07-05T07:14:22.424453+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BUXAITNPCRGUDKM","created_at":"2026-07-05T07:14:22.424453+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BUXAITN","created_at":"2026-07-05T07:14:22.424453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17213","citing_title":"Revisiting LLM Adaptation for 3D CT Report Generation: A Study of Scaling and Diagnostic Priors","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31437","citing_title":"Astra: a generalizable report generation foundation model for 3D computed tomography","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00602","citing_title":"ASAP: Advancing Medical Volumetric Representation Learning with Anatomy-aware Semantically-adaptive Pre-training","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04133","citing_title":"Learning Robust Visual Features in Computed Tomography Enables Efficient Transfer Learning for Clinical Tasks","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18250","citing_title":"Medical Image Understanding Improves Survival Prediction via Visual Instruction Tuning","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5BUXAITNPCRGUDKMJJNSHT4LTJ","json":"https://pith.science/pith/5BUXAITNPCRGUDKMJJNSHT4LTJ.json","graph_json":"https://pith.science/api/pith-number/5BUXAITNPCRGUDKMJJNSHT4LTJ/graph.json","events_json":"https://pith.science/api/pith-number/5BUXAITNPCRGUDKMJJNSHT4LTJ/events.json","paper":"https://pith.science/paper/5BUXAITN"},"agent_actions":{"view_html":"https://pith.science/pith/5BUXAITNPCRGUDKMJJNSHT4LTJ","download_json":"https://pith.science/pith/5BUXAITNPCRGUDKMJJNSHT4LTJ.json","view_paper":"https://pith.science/paper/5BUXAITN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.10798&json=true","fetch_graph":"https://pith.science/api/pith-number/5BUXAITNPCRGUDKMJJNSHT4LTJ/graph.json","fetch_events":"https://pith.science/api/pith-number/5BUXAITNPCRGUDKMJJNSHT4LTJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BUXAITNPCRGUDKMJJNSHT4LTJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BUXAITNPCRGUDKMJJNSHT4LTJ/action/storage_attestation","attest_author":"https://pith.science/pith/5BUXAITNPCRGUDKMJJNSHT4LTJ/action/author_attestation","sign_citation":"https://pith.science/pith/5BUXAITNPCRGUDKMJJNSHT4LTJ/action/citation_signature","submit_replication":"https://pith.science/pith/5BUXAITNPCRGUDKMJJNSHT4LTJ/action/replication_record"}},"created_at":"2026-07-05T07:14:22.424453+00:00","updated_at":"2026-07-05T07:14:22.424453+00:00"}