{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JCAEP5XQ46UZFMORKHCJ2DFC73","short_pith_number":"pith:JCAEP5XQ","schema_version":"1.0","canonical_sha256":"488047f6f0e7a992b1d151c49d0ca2feeda9ea5e6e986e574af5111a90bffc54","source":{"kind":"arxiv","id":"2507.17359","version":1},"attestation_state":"computed","paper":{"title":"Exploring Active Learning for Semiconductor Defect Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuan-Sheng Foo, Jie Wang, Lile Cai, Lining Zhang, Ramanpreet Singh Pahwa, Richard Chang, Xun Xu","submitted_at":"2025-07-23T09:44:11Z","abstract_excerpt":"The development of X-Ray microscopy (XRM) technology has enabled non-destructive inspection of semiconductor structures for defect identification. Deep learning is widely used as the state-of-the-art approach to perform visual analysis tasks. However, deep learning based models require large amount of annotated data to train. This can be time-consuming and expensive to obtain especially for dense prediction tasks like semantic segmentation. In this work, we explore active learning (AL) as a potential solution to alleviate the annotation burden. We identify two unique challenges when applying A"},"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":"2507.17359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-23T09:44:11Z","cross_cats_sorted":[],"title_canon_sha256":"97ab9a933f6fcb14c4d2ac17f38ed3fdfc8d890c64c7e2794c5c8f4a58bb60b5","abstract_canon_sha256":"d414f7759b58bf91858304cc9a8c81e39ae816f891e3f9d3aa53bb3d498cf326"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:06.200964Z","signature_b64":"zIxfNdizbWiZede47YArOdWqFhcgwcFIiL0cI+gzs41fhUJeDQfW2rbUplLbTxp424b9/kZyoEmyUudYedgjAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"488047f6f0e7a992b1d151c49d0ca2feeda9ea5e6e986e574af5111a90bffc54","last_reissued_at":"2026-07-05T11:42:06.200556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:06.200556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Active Learning for Semiconductor Defect Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuan-Sheng Foo, Jie Wang, Lile Cai, Lining Zhang, Ramanpreet Singh Pahwa, Richard Chang, Xun Xu","submitted_at":"2025-07-23T09:44:11Z","abstract_excerpt":"The development of X-Ray microscopy (XRM) technology has enabled non-destructive inspection of semiconductor structures for defect identification. Deep learning is widely used as the state-of-the-art approach to perform visual analysis tasks. However, deep learning based models require large amount of annotated data to train. This can be time-consuming and expensive to obtain especially for dense prediction tasks like semantic segmentation. In this work, we explore active learning (AL) as a potential solution to alleviate the annotation burden. We identify two unique challenges when applying A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17359","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/2507.17359/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":"2507.17359","created_at":"2026-07-05T11:42:06.200611+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.17359v1","created_at":"2026-07-05T11:42:06.200611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17359","created_at":"2026-07-05T11:42:06.200611+00:00"},{"alias_kind":"pith_short_12","alias_value":"JCAEP5XQ46UZ","created_at":"2026-07-05T11:42:06.200611+00:00"},{"alias_kind":"pith_short_16","alias_value":"JCAEP5XQ46UZFMOR","created_at":"2026-07-05T11:42:06.200611+00:00"},{"alias_kind":"pith_short_8","alias_value":"JCAEP5XQ","created_at":"2026-07-05T11:42:06.200611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17359","citing_title":"Exploring Active Learning for Semiconductor Defect Segmentation","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JCAEP5XQ46UZFMORKHCJ2DFC73","json":"https://pith.science/pith/JCAEP5XQ46UZFMORKHCJ2DFC73.json","graph_json":"https://pith.science/api/pith-number/JCAEP5XQ46UZFMORKHCJ2DFC73/graph.json","events_json":"https://pith.science/api/pith-number/JCAEP5XQ46UZFMORKHCJ2DFC73/events.json","paper":"https://pith.science/paper/JCAEP5XQ"},"agent_actions":{"view_html":"https://pith.science/pith/JCAEP5XQ46UZFMORKHCJ2DFC73","download_json":"https://pith.science/pith/JCAEP5XQ46UZFMORKHCJ2DFC73.json","view_paper":"https://pith.science/paper/JCAEP5XQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.17359&json=true","fetch_graph":"https://pith.science/api/pith-number/JCAEP5XQ46UZFMORKHCJ2DFC73/graph.json","fetch_events":"https://pith.science/api/pith-number/JCAEP5XQ46UZFMORKHCJ2DFC73/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JCAEP5XQ46UZFMORKHCJ2DFC73/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JCAEP5XQ46UZFMORKHCJ2DFC73/action/storage_attestation","attest_author":"https://pith.science/pith/JCAEP5XQ46UZFMORKHCJ2DFC73/action/author_attestation","sign_citation":"https://pith.science/pith/JCAEP5XQ46UZFMORKHCJ2DFC73/action/citation_signature","submit_replication":"https://pith.science/pith/JCAEP5XQ46UZFMORKHCJ2DFC73/action/replication_record"}},"created_at":"2026-07-05T11:42:06.200611+00:00","updated_at":"2026-07-05T11:42:06.200611+00:00"}