{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DBCIIKHOPUKOCLA2ATV3QPBHXS","short_pith_number":"pith:DBCIIKHO","schema_version":"1.0","canonical_sha256":"18448428ee7d14e12c1a04ebb83c27bc91d0d0e6a99382e6158e2bde9c3dc748","source":{"kind":"arxiv","id":"2305.14165","version":1},"attestation_state":"computed","paper":{"title":"Impact of Light and Shadow on Robustness of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chao Li, Chengyin Hu, Donghua Wang, Guijian Tang, Jialiang Sun, Junqi Wu, Weiwen Shi","submitted_at":"2023-05-23T15:30:56Z","abstract_excerpt":"Deep neural networks (DNNs) have made remarkable strides in various computer vision tasks, including image classification, segmentation, and object detection. However, recent research has revealed a vulnerability in advanced DNNs when faced with deliberate manipulations of input data, known as adversarial attacks. Moreover, the accuracy of DNNs is heavily influenced by the distribution of the training dataset. Distortions or perturbations in the color space of input images can introduce out-of-distribution data, resulting in misclassification. In this work, we propose a brightness-variation da"},"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":"2305.14165","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T15:30:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1278c5d8233b35be7e32a94d553ebb5a123726502a8edda67f8eeac53949dd9d","abstract_canon_sha256":"61137ffca115ba5fa3482f8ac3f8e160c868afad396f59a815112362985c7c66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:01.597053Z","signature_b64":"8BHUCJWPwPAPRZKLD20z8fAy52SUu2qVpCdBIYVJbKldSdhBtuxOidlgbFPHRdjceSYR+FiSwgYilEhfgHy0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18448428ee7d14e12c1a04ebb83c27bc91d0d0e6a99382e6158e2bde9c3dc748","last_reissued_at":"2026-07-05T06:13:01.596570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:01.596570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Impact of Light and Shadow on Robustness of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chao Li, Chengyin Hu, Donghua Wang, Guijian Tang, Jialiang Sun, Junqi Wu, Weiwen Shi","submitted_at":"2023-05-23T15:30:56Z","abstract_excerpt":"Deep neural networks (DNNs) have made remarkable strides in various computer vision tasks, including image classification, segmentation, and object detection. However, recent research has revealed a vulnerability in advanced DNNs when faced with deliberate manipulations of input data, known as adversarial attacks. Moreover, the accuracy of DNNs is heavily influenced by the distribution of the training dataset. Distortions or perturbations in the color space of input images can introduce out-of-distribution data, resulting in misclassification. In this work, we propose a brightness-variation da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14165","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/2305.14165/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":"2305.14165","created_at":"2026-07-05T06:13:01.596626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14165v1","created_at":"2026-07-05T06:13:01.596626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14165","created_at":"2026-07-05T06:13:01.596626+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBCIIKHOPUKO","created_at":"2026-07-05T06:13:01.596626+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBCIIKHOPUKOCLA2","created_at":"2026-07-05T06:13:01.596626+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBCIIKHO","created_at":"2026-07-05T06:13:01.596626+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/DBCIIKHOPUKOCLA2ATV3QPBHXS","json":"https://pith.science/pith/DBCIIKHOPUKOCLA2ATV3QPBHXS.json","graph_json":"https://pith.science/api/pith-number/DBCIIKHOPUKOCLA2ATV3QPBHXS/graph.json","events_json":"https://pith.science/api/pith-number/DBCIIKHOPUKOCLA2ATV3QPBHXS/events.json","paper":"https://pith.science/paper/DBCIIKHO"},"agent_actions":{"view_html":"https://pith.science/pith/DBCIIKHOPUKOCLA2ATV3QPBHXS","download_json":"https://pith.science/pith/DBCIIKHOPUKOCLA2ATV3QPBHXS.json","view_paper":"https://pith.science/paper/DBCIIKHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14165&json=true","fetch_graph":"https://pith.science/api/pith-number/DBCIIKHOPUKOCLA2ATV3QPBHXS/graph.json","fetch_events":"https://pith.science/api/pith-number/DBCIIKHOPUKOCLA2ATV3QPBHXS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBCIIKHOPUKOCLA2ATV3QPBHXS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBCIIKHOPUKOCLA2ATV3QPBHXS/action/storage_attestation","attest_author":"https://pith.science/pith/DBCIIKHOPUKOCLA2ATV3QPBHXS/action/author_attestation","sign_citation":"https://pith.science/pith/DBCIIKHOPUKOCLA2ATV3QPBHXS/action/citation_signature","submit_replication":"https://pith.science/pith/DBCIIKHOPUKOCLA2ATV3QPBHXS/action/replication_record"}},"created_at":"2026-07-05T06:13:01.596626+00:00","updated_at":"2026-07-05T06:13:01.596626+00:00"}