{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RB4XBSXULDDUWQSMFRLOFKY6BR","short_pith_number":"pith:RB4XBSXU","schema_version":"1.0","canonical_sha256":"887970caf458c74b424c2c56e2ab1e0c6927d7ff6d3cb3de232345256868a09c","source":{"kind":"arxiv","id":"2310.03182","version":1},"attestation_state":"computed","paper":{"title":"Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Amilcare Gentili, An Yan, Chengyu Dong, Chun-Nan Hsu, Jingbo Shang, Julian McAuley, Petros Karypis, Yiwu Zhong, Yu Wang, Zexue He, Zihan Wang","submitted_at":"2023-10-04T21:57:09Z","abstract_excerpt":"Medical image classification is a critical problem for healthcare, with the potential to alleviate the workload of doctors and facilitate diagnoses of patients. However, two challenges arise when deploying deep learning models to real-world healthcare applications. First, neural models tend to learn spurious correlations instead of desired features, which could fall short when generalizing to new domains (e.g., patients with different ages). Second, these black-box models lack interpretability. When making diagnostic predictions, it is important to understand why a model makes a decision for t"},"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":"2310.03182","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-04T21:57:09Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"1239905764bc863ac5d8b117f5d13692ce6af5fa2b74123540f403288b8e7fbd","abstract_canon_sha256":"b95a57dd6a8253277fda28a8a536dc81a6f58164d1cf9174984811ca19e65e74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:29.768507Z","signature_b64":"OnH/E/Dyh46iq6x/+a1u0Ntcv3mY95gh2nzH12c7NHPpQ4dLH5hxIExfRqHkIy/JrQwluRgeT1j0R/ZwYKuHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"887970caf458c74b424c2c56e2ab1e0c6927d7ff6d3cb3de232345256868a09c","last_reissued_at":"2026-07-05T06:57:29.767968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:29.767968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Amilcare Gentili, An Yan, Chengyu Dong, Chun-Nan Hsu, Jingbo Shang, Julian McAuley, Petros Karypis, Yiwu Zhong, Yu Wang, Zexue He, Zihan Wang","submitted_at":"2023-10-04T21:57:09Z","abstract_excerpt":"Medical image classification is a critical problem for healthcare, with the potential to alleviate the workload of doctors and facilitate diagnoses of patients. However, two challenges arise when deploying deep learning models to real-world healthcare applications. First, neural models tend to learn spurious correlations instead of desired features, which could fall short when generalizing to new domains (e.g., patients with different ages). Second, these black-box models lack interpretability. When making diagnostic predictions, it is important to understand why a model makes a decision for t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03182","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/2310.03182/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":"2310.03182","created_at":"2026-07-05T06:57:29.768036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.03182v1","created_at":"2026-07-05T06:57:29.768036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03182","created_at":"2026-07-05T06:57:29.768036+00:00"},{"alias_kind":"pith_short_12","alias_value":"RB4XBSXULDDU","created_at":"2026-07-05T06:57:29.768036+00:00"},{"alias_kind":"pith_short_16","alias_value":"RB4XBSXULDDUWQSM","created_at":"2026-07-05T06:57:29.768036+00:00"},{"alias_kind":"pith_short_8","alias_value":"RB4XBSXU","created_at":"2026-07-05T06:57:29.768036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30313","citing_title":"TRACE: A Concept Bottleneck Model for Longitudinal 3D Glioblastoma Response Assessment","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04326","citing_title":"Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30313","citing_title":"TRACE: A Concept Bottleneck Model for Longitudinal 3D Glioblastoma Response Assessment","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25304","citing_title":"When Interpretability Becomes a Liability: Adversarial Attacks on CBM Concept Layers","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21455","citing_title":"Mitigating Label Bias with Interpretable Rubric Embeddings","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2403.19647","citing_title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RB4XBSXULDDUWQSMFRLOFKY6BR","json":"https://pith.science/pith/RB4XBSXULDDUWQSMFRLOFKY6BR.json","graph_json":"https://pith.science/api/pith-number/RB4XBSXULDDUWQSMFRLOFKY6BR/graph.json","events_json":"https://pith.science/api/pith-number/RB4XBSXULDDUWQSMFRLOFKY6BR/events.json","paper":"https://pith.science/paper/RB4XBSXU"},"agent_actions":{"view_html":"https://pith.science/pith/RB4XBSXULDDUWQSMFRLOFKY6BR","download_json":"https://pith.science/pith/RB4XBSXULDDUWQSMFRLOFKY6BR.json","view_paper":"https://pith.science/paper/RB4XBSXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.03182&json=true","fetch_graph":"https://pith.science/api/pith-number/RB4XBSXULDDUWQSMFRLOFKY6BR/graph.json","fetch_events":"https://pith.science/api/pith-number/RB4XBSXULDDUWQSMFRLOFKY6BR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RB4XBSXULDDUWQSMFRLOFKY6BR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RB4XBSXULDDUWQSMFRLOFKY6BR/action/storage_attestation","attest_author":"https://pith.science/pith/RB4XBSXULDDUWQSMFRLOFKY6BR/action/author_attestation","sign_citation":"https://pith.science/pith/RB4XBSXULDDUWQSMFRLOFKY6BR/action/citation_signature","submit_replication":"https://pith.science/pith/RB4XBSXULDDUWQSMFRLOFKY6BR/action/replication_record"}},"created_at":"2026-07-05T06:57:29.768036+00:00","updated_at":"2026-07-05T06:57:29.768036+00:00"}