{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OQSLESFXSG52AH36FZB6YGHIOB","short_pith_number":"pith:OQSLESFX","schema_version":"1.0","canonical_sha256":"7424b248b791bba01f7e2e43ec18e8706b49ff3df7acd195b9857b011ba850b7","source":{"kind":"arxiv","id":"2112.02922","version":1},"attestation_state":"computed","paper":{"title":"Anomaly Detection in IR Images of PV Modules using Supervised Contrastive Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Maier, Christoph Brabec, Claudia Buerhop-Lutz, Ian Marius Peters, Jens Hauch, Lukas Bommes, Mathis Hoffmann, Tobias Pickel","submitted_at":"2021-12-06T10:42:28Z","abstract_excerpt":"Increasing deployment of photovoltaic (PV) plants requires methods for automatic detection of faulty PV modules in modalities, such as infrared (IR) images. Recently, deep learning has become popular for this. However, related works typically sample train and test data from the same distribution ignoring the presence of domain shift between data of different PV plants. Instead, we frame fault detection as more realistic unsupervised domain adaptation problem where we train on labelled data of one source PV plant and make predictions on another target plant. We train a ResNet-34 convolutional n"},"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":"2112.02922","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-06T10:42:28Z","cross_cats_sorted":[],"title_canon_sha256":"15069fd2499b63254d596cd161cd8d0e05ca7ef57791afbec88e49de5f9d1970","abstract_canon_sha256":"eb3ec75451c03af3ba193675a688fe2de67232decd99cda6251675be41fe1c08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:59.333628Z","signature_b64":"+EVV66pbaz1IGt+MrE8t7Rje/nt9uwu5pKGodb6T9AV+ixeaeAkRqw76mcYwHuQowmIimt2WzrONmZj4pO3lBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7424b248b791bba01f7e2e43ec18e8706b49ff3df7acd195b9857b011ba850b7","last_reissued_at":"2026-07-05T03:37:59.333216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:59.333216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Anomaly Detection in IR Images of PV Modules using Supervised Contrastive Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Maier, Christoph Brabec, Claudia Buerhop-Lutz, Ian Marius Peters, Jens Hauch, Lukas Bommes, Mathis Hoffmann, Tobias Pickel","submitted_at":"2021-12-06T10:42:28Z","abstract_excerpt":"Increasing deployment of photovoltaic (PV) plants requires methods for automatic detection of faulty PV modules in modalities, such as infrared (IR) images. Recently, deep learning has become popular for this. However, related works typically sample train and test data from the same distribution ignoring the presence of domain shift between data of different PV plants. Instead, we frame fault detection as more realistic unsupervised domain adaptation problem where we train on labelled data of one source PV plant and make predictions on another target plant. We train a ResNet-34 convolutional n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02922","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/2112.02922/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":"2112.02922","created_at":"2026-07-05T03:37:59.333269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.02922v1","created_at":"2026-07-05T03:37:59.333269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02922","created_at":"2026-07-05T03:37:59.333269+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQSLESFXSG52","created_at":"2026-07-05T03:37:59.333269+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQSLESFXSG52AH36","created_at":"2026-07-05T03:37:59.333269+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQSLESFX","created_at":"2026-07-05T03:37:59.333269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.07039","citing_title":"Benchmarking Vision Transformers and CNNs for Thermal Photovoltaic Fault Detection with Explainable AI Validation","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQSLESFXSG52AH36FZB6YGHIOB","json":"https://pith.science/pith/OQSLESFXSG52AH36FZB6YGHIOB.json","graph_json":"https://pith.science/api/pith-number/OQSLESFXSG52AH36FZB6YGHIOB/graph.json","events_json":"https://pith.science/api/pith-number/OQSLESFXSG52AH36FZB6YGHIOB/events.json","paper":"https://pith.science/paper/OQSLESFX"},"agent_actions":{"view_html":"https://pith.science/pith/OQSLESFXSG52AH36FZB6YGHIOB","download_json":"https://pith.science/pith/OQSLESFXSG52AH36FZB6YGHIOB.json","view_paper":"https://pith.science/paper/OQSLESFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.02922&json=true","fetch_graph":"https://pith.science/api/pith-number/OQSLESFXSG52AH36FZB6YGHIOB/graph.json","fetch_events":"https://pith.science/api/pith-number/OQSLESFXSG52AH36FZB6YGHIOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQSLESFXSG52AH36FZB6YGHIOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQSLESFXSG52AH36FZB6YGHIOB/action/storage_attestation","attest_author":"https://pith.science/pith/OQSLESFXSG52AH36FZB6YGHIOB/action/author_attestation","sign_citation":"https://pith.science/pith/OQSLESFXSG52AH36FZB6YGHIOB/action/citation_signature","submit_replication":"https://pith.science/pith/OQSLESFXSG52AH36FZB6YGHIOB/action/replication_record"}},"created_at":"2026-07-05T03:37:59.333269+00:00","updated_at":"2026-07-05T03:37:59.333269+00:00"}