{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GSAWRHSVJDWOXQNGZGCG6W34JH","short_pith_number":"pith:GSAWRHSV","schema_version":"1.0","canonical_sha256":"3481689e5548ecebc1a6c9846f5b7c49ecf63ef0cc4f67d76d216bbdc7cfadf1","source":{"kind":"arxiv","id":"2603.26885","version":2},"attestation_state":"computed","paper":{"title":"TTE-CAM: Self-Explainable Class Activation Maps for Pretrained Black-Box CNNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kerol Djoumessi, Philipp Berens","submitted_at":"2026-03-27T18:02:32Z","abstract_excerpt":"Convolutional neural networks (CNNs) achieve state-of-the-art performance in medical image analysis yet remain opaque, limiting adoption in high-stakes clinical settings. Existing approaches face a fundamental trade-off: post-hoc methods provide unfaithful approximate explanations, while inherently interpretable architectures are faithful but often sacrifice predictive performance. We introduce TTE-CAM, a test-time framework that bridges this gap by converting pretrained black-box CNNs into self-explainable models via a convolution-based replacement of their classification head, initialized fr"},"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":"2603.26885","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-27T18:02:32Z","cross_cats_sorted":[],"title_canon_sha256":"b3cdb3e1a7fe0a5a9702e17c021bbf7cc323756309cf9f6ae67ee8e6c983e148","abstract_canon_sha256":"aad84925940f1a9148948e5cf4468a160e7229349b048b9e781738c40ead4fc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:38.576583Z","signature_b64":"Jye9Rp2KTZmC5g+flrQl0K5K1U4NSxzjK1C8uwtymJnWtlPAVEnjs7qKJUx+VgucH4KmNNKh25G9M3UoweEgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3481689e5548ecebc1a6c9846f5b7c49ecf63ef0cc4f67d76d216bbdc7cfadf1","last_reissued_at":"2026-06-01T01:02:38.575676Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:38.575676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TTE-CAM: Self-Explainable Class Activation Maps for Pretrained Black-Box CNNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kerol Djoumessi, Philipp Berens","submitted_at":"2026-03-27T18:02:32Z","abstract_excerpt":"Convolutional neural networks (CNNs) achieve state-of-the-art performance in medical image analysis yet remain opaque, limiting adoption in high-stakes clinical settings. Existing approaches face a fundamental trade-off: post-hoc methods provide unfaithful approximate explanations, while inherently interpretable architectures are faithful but often sacrifice predictive performance. We introduce TTE-CAM, a test-time framework that bridges this gap by converting pretrained black-box CNNs into self-explainable models via a convolution-based replacement of their classification head, initialized fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.26885","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/2603.26885/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":"2603.26885","created_at":"2026-06-01T01:02:38.575805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.26885v2","created_at":"2026-06-01T01:02:38.575805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.26885","created_at":"2026-06-01T01:02:38.575805+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSAWRHSVJDWO","created_at":"2026-06-01T01:02:38.575805+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSAWRHSVJDWOXQNG","created_at":"2026-06-01T01:02:38.575805+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSAWRHSV","created_at":"2026-06-01T01:02:38.575805+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/GSAWRHSVJDWOXQNGZGCG6W34JH","json":"https://pith.science/pith/GSAWRHSVJDWOXQNGZGCG6W34JH.json","graph_json":"https://pith.science/api/pith-number/GSAWRHSVJDWOXQNGZGCG6W34JH/graph.json","events_json":"https://pith.science/api/pith-number/GSAWRHSVJDWOXQNGZGCG6W34JH/events.json","paper":"https://pith.science/paper/GSAWRHSV"},"agent_actions":{"view_html":"https://pith.science/pith/GSAWRHSVJDWOXQNGZGCG6W34JH","download_json":"https://pith.science/pith/GSAWRHSVJDWOXQNGZGCG6W34JH.json","view_paper":"https://pith.science/paper/GSAWRHSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.26885&json=true","fetch_graph":"https://pith.science/api/pith-number/GSAWRHSVJDWOXQNGZGCG6W34JH/graph.json","fetch_events":"https://pith.science/api/pith-number/GSAWRHSVJDWOXQNGZGCG6W34JH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSAWRHSVJDWOXQNGZGCG6W34JH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSAWRHSVJDWOXQNGZGCG6W34JH/action/storage_attestation","attest_author":"https://pith.science/pith/GSAWRHSVJDWOXQNGZGCG6W34JH/action/author_attestation","sign_citation":"https://pith.science/pith/GSAWRHSVJDWOXQNGZGCG6W34JH/action/citation_signature","submit_replication":"https://pith.science/pith/GSAWRHSVJDWOXQNGZGCG6W34JH/action/replication_record"}},"created_at":"2026-06-01T01:02:38.575805+00:00","updated_at":"2026-06-01T01:02:38.575805+00:00"}