{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JE6CKDRU27CB7SXVR6HSDGK4IW","short_pith_number":"pith:JE6CKDRU","schema_version":"1.0","canonical_sha256":"493c250e34d7c41fcaf58f8f21995c45b95fdc111add2976b0cc54b3b89fe7c0","source":{"kind":"arxiv","id":"2504.10021","version":2},"attestation_state":"computed","paper":{"title":"Masked Autoencoder Self Pre-Training for Defect Detection in Microelectronics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alireza Javanmardi, Alwin Hoffmann, Emilio Zarbali, Nikolai R\\\"ohrich, Richard Nordsieck","submitted_at":"2025-04-14T09:25:50Z","abstract_excerpt":"While transformers have surpassed convolutional neural networks (CNNs) in various computer vision tasks, microelectronics defect detection still largely relies on CNNs. We hypothesize that this gap is due to the fact that a) transformers have an increased need for data and b) (labelled) image generation procedures for microelectronics are costly, and data is therefore sparse. Whereas in other domains, pre-training on large natural image datasets can mitigate this problem, in microelectronics transfer learning is hindered due to the dissimilarity of domain data and natural images. We address th"},"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":"2504.10021","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-14T09:25:50Z","cross_cats_sorted":[],"title_canon_sha256":"31154f30b61636a024aa4930bcaea3855c656f1b5f7c20cd21d0d7566c35830e","abstract_canon_sha256":"e2ade620580042e4124edb530b89e2aec5e53c37a067c8e4b516f3b09b55e957"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:19.902214Z","signature_b64":"G2SYJbEaeEq+Kzf0DRx71svVIzL1Att8BWD1OgegSc5e3ptVQUJCi3TmtjG3c1RBaTkeT+qQvKqF+8HlpiTEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"493c250e34d7c41fcaf58f8f21995c45b95fdc111add2976b0cc54b3b89fe7c0","last_reissued_at":"2026-07-05T11:52:19.901720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:19.901720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Masked Autoencoder Self Pre-Training for Defect Detection in Microelectronics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alireza Javanmardi, Alwin Hoffmann, Emilio Zarbali, Nikolai R\\\"ohrich, Richard Nordsieck","submitted_at":"2025-04-14T09:25:50Z","abstract_excerpt":"While transformers have surpassed convolutional neural networks (CNNs) in various computer vision tasks, microelectronics defect detection still largely relies on CNNs. We hypothesize that this gap is due to the fact that a) transformers have an increased need for data and b) (labelled) image generation procedures for microelectronics are costly, and data is therefore sparse. Whereas in other domains, pre-training on large natural image datasets can mitigate this problem, in microelectronics transfer learning is hindered due to the dissimilarity of domain data and natural images. We address th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10021","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/2504.10021/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":"2504.10021","created_at":"2026-07-05T11:52:19.901780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.10021v2","created_at":"2026-07-05T11:52:19.901780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10021","created_at":"2026-07-05T11:52:19.901780+00:00"},{"alias_kind":"pith_short_12","alias_value":"JE6CKDRU27CB","created_at":"2026-07-05T11:52:19.901780+00:00"},{"alias_kind":"pith_short_16","alias_value":"JE6CKDRU27CB7SXV","created_at":"2026-07-05T11:52:19.901780+00:00"},{"alias_kind":"pith_short_8","alias_value":"JE6CKDRU","created_at":"2026-07-05T11:52:19.901780+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.06122","citing_title":"Is Self-Pretraining really useful to improve diagnosis in medical Time Series?","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JE6CKDRU27CB7SXVR6HSDGK4IW","json":"https://pith.science/pith/JE6CKDRU27CB7SXVR6HSDGK4IW.json","graph_json":"https://pith.science/api/pith-number/JE6CKDRU27CB7SXVR6HSDGK4IW/graph.json","events_json":"https://pith.science/api/pith-number/JE6CKDRU27CB7SXVR6HSDGK4IW/events.json","paper":"https://pith.science/paper/JE6CKDRU"},"agent_actions":{"view_html":"https://pith.science/pith/JE6CKDRU27CB7SXVR6HSDGK4IW","download_json":"https://pith.science/pith/JE6CKDRU27CB7SXVR6HSDGK4IW.json","view_paper":"https://pith.science/paper/JE6CKDRU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.10021&json=true","fetch_graph":"https://pith.science/api/pith-number/JE6CKDRU27CB7SXVR6HSDGK4IW/graph.json","fetch_events":"https://pith.science/api/pith-number/JE6CKDRU27CB7SXVR6HSDGK4IW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JE6CKDRU27CB7SXVR6HSDGK4IW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JE6CKDRU27CB7SXVR6HSDGK4IW/action/storage_attestation","attest_author":"https://pith.science/pith/JE6CKDRU27CB7SXVR6HSDGK4IW/action/author_attestation","sign_citation":"https://pith.science/pith/JE6CKDRU27CB7SXVR6HSDGK4IW/action/citation_signature","submit_replication":"https://pith.science/pith/JE6CKDRU27CB7SXVR6HSDGK4IW/action/replication_record"}},"created_at":"2026-07-05T11:52:19.901780+00:00","updated_at":"2026-07-05T11:52:19.901780+00:00"}