{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VIY2KA52LWBRR2P2KTUWCMRDNZ","short_pith_number":"pith:VIY2KA52","schema_version":"1.0","canonical_sha256":"aa31a503ba5d8318e9fa54e96132236e598409a79311b8692139a39a812946a0","source":{"kind":"arxiv","id":"2605.20159","version":1},"attestation_state":"computed","paper":{"title":"Interpretable Computer Vision for Defect Detection in X-ray Tomography of Aerospace SiC/SiC Composites","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonio Pe\\~na Corredor, Julien Lesseur, Paul Rivalland (SES), Romain Nunez, Thomas Philippe","submitted_at":"2026-05-19T17:46:49Z","abstract_excerpt":"Non-destructive testing of aerospace SiC/SiC composites via X-ray computed tomography (XCT) relies on expert visual assessment, with current workflows offering limited traceability for accept/reject decisions. Deep convolutional networks can automate defect detection, yet their black-box nature conflicts with the transparency that industrial inspection practice demands. To close this gap, we introduce p-ResNet-50, a convolutional framework extended with a prototype layer that couples high detection accuracy with case-based explanations. Six learned prototypes are explicitly aligned with expert"},"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":"2605.20159","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T17:46:49Z","cross_cats_sorted":["cond-mat.mtrl-sci","cs.LG"],"title_canon_sha256":"984a971e8dc12fef314e99898ebaf0f98526cd523373093664c227f336d3407a","abstract_canon_sha256":"14ee5f04ac3ebf77361d17913d7571322aa9e0120b7c4ba7e4c1580ac3edb34b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T02:06:05.451828Z","signature_b64":"NOyHRVFnLjfHbWJtnNhlMLNDvYVGaiPk0ewx+TB1JTBK3XkBNsEw82Sx/uDQ+IEWnG//3tQXDQFjMJivFhBxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa31a503ba5d8318e9fa54e96132236e598409a79311b8692139a39a812946a0","last_reissued_at":"2026-05-20T02:06:05.451138Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T02:06:05.451138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Computer Vision for Defect Detection in X-ray Tomography of Aerospace SiC/SiC Composites","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonio Pe\\~na Corredor, Julien Lesseur, Paul Rivalland (SES), Romain Nunez, Thomas Philippe","submitted_at":"2026-05-19T17:46:49Z","abstract_excerpt":"Non-destructive testing of aerospace SiC/SiC composites via X-ray computed tomography (XCT) relies on expert visual assessment, with current workflows offering limited traceability for accept/reject decisions. Deep convolutional networks can automate defect detection, yet their black-box nature conflicts with the transparency that industrial inspection practice demands. To close this gap, we introduce p-ResNet-50, a convolutional framework extended with a prototype layer that couples high detection accuracy with case-based explanations. Six learned prototypes are explicitly aligned with expert"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20159","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/2605.20159/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":"2605.20159","created_at":"2026-05-20T02:06:05.451248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20159v1","created_at":"2026-05-20T02:06:05.451248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20159","created_at":"2026-05-20T02:06:05.451248+00:00"},{"alias_kind":"pith_short_12","alias_value":"VIY2KA52LWBR","created_at":"2026-05-20T02:06:05.451248+00:00"},{"alias_kind":"pith_short_16","alias_value":"VIY2KA52LWBRR2P2","created_at":"2026-05-20T02:06:05.451248+00:00"},{"alias_kind":"pith_short_8","alias_value":"VIY2KA52","created_at":"2026-05-20T02:06:05.451248+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/VIY2KA52LWBRR2P2KTUWCMRDNZ","json":"https://pith.science/pith/VIY2KA52LWBRR2P2KTUWCMRDNZ.json","graph_json":"https://pith.science/api/pith-number/VIY2KA52LWBRR2P2KTUWCMRDNZ/graph.json","events_json":"https://pith.science/api/pith-number/VIY2KA52LWBRR2P2KTUWCMRDNZ/events.json","paper":"https://pith.science/paper/VIY2KA52"},"agent_actions":{"view_html":"https://pith.science/pith/VIY2KA52LWBRR2P2KTUWCMRDNZ","download_json":"https://pith.science/pith/VIY2KA52LWBRR2P2KTUWCMRDNZ.json","view_paper":"https://pith.science/paper/VIY2KA52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20159&json=true","fetch_graph":"https://pith.science/api/pith-number/VIY2KA52LWBRR2P2KTUWCMRDNZ/graph.json","fetch_events":"https://pith.science/api/pith-number/VIY2KA52LWBRR2P2KTUWCMRDNZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VIY2KA52LWBRR2P2KTUWCMRDNZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VIY2KA52LWBRR2P2KTUWCMRDNZ/action/storage_attestation","attest_author":"https://pith.science/pith/VIY2KA52LWBRR2P2KTUWCMRDNZ/action/author_attestation","sign_citation":"https://pith.science/pith/VIY2KA52LWBRR2P2KTUWCMRDNZ/action/citation_signature","submit_replication":"https://pith.science/pith/VIY2KA52LWBRR2P2KTUWCMRDNZ/action/replication_record"}},"created_at":"2026-05-20T02:06:05.451248+00:00","updated_at":"2026-05-20T02:06:05.451248+00:00"}