{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H4WNEXU2SZKJCLHY3OLA7GYQWP","short_pith_number":"pith:H4WNEXU2","schema_version":"1.0","canonical_sha256":"3f2cd25e9a9654912cf8db960f9b10b3c6eb6e3356104753a2f8028794ad02af","source":{"kind":"arxiv","id":"2403.10076","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Adversarial Robustness of Image Shadow Removal with Shadow-adaptive Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bihan Wen, Chong Wang, Lanqing Guo, Yi Yu","submitted_at":"2024-03-15T07:43:42Z","abstract_excerpt":"Shadow removal is a task aimed at erasing regional shadows present in images and reinstating visually pleasing natural scenes with consistent illumination. While recent deep learning techniques have demonstrated impressive performance in image shadow removal, their robustness against adversarial attacks remains largely unexplored. Furthermore, many existing attack frameworks typically allocate a uniform budget for perturbations across the entire input image, which may not be suitable for attacking shadow images. This is primarily due to the unique characteristic of spatially varying illuminati"},"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":"2403.10076","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T07:43:42Z","cross_cats_sorted":[],"title_canon_sha256":"f62196b24f2b8adec4b4c155ba2fea0f94d432429a114a7e94626e3726facd43","abstract_canon_sha256":"6b2b0cd59d9f365b9aa0cbb33968f7dbca02904ca28d5c21e7632cc2cacf0ca9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:29.854537Z","signature_b64":"QuITs9XtDgs/fxmjcimPHkVWzRVWTQWwRdQOV8SEhEs3pf5xvAFUtAqaPXL2W5bB/IpvQNz8VDFnVtHueoG8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f2cd25e9a9654912cf8db960f9b10b3c6eb6e3356104753a2f8028794ad02af","last_reissued_at":"2026-07-05T07:56:29.854137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:29.854137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Adversarial Robustness of Image Shadow Removal with Shadow-adaptive Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bihan Wen, Chong Wang, Lanqing Guo, Yi Yu","submitted_at":"2024-03-15T07:43:42Z","abstract_excerpt":"Shadow removal is a task aimed at erasing regional shadows present in images and reinstating visually pleasing natural scenes with consistent illumination. While recent deep learning techniques have demonstrated impressive performance in image shadow removal, their robustness against adversarial attacks remains largely unexplored. Furthermore, many existing attack frameworks typically allocate a uniform budget for perturbations across the entire input image, which may not be suitable for attacking shadow images. This is primarily due to the unique characteristic of spatially varying illuminati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10076","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/2403.10076/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":"2403.10076","created_at":"2026-07-05T07:56:29.854200+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10076v1","created_at":"2026-07-05T07:56:29.854200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10076","created_at":"2026-07-05T07:56:29.854200+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4WNEXU2SZKJ","created_at":"2026-07-05T07:56:29.854200+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4WNEXU2SZKJCLHY","created_at":"2026-07-05T07:56:29.854200+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4WNEXU2","created_at":"2026-07-05T07:56:29.854200+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/H4WNEXU2SZKJCLHY3OLA7GYQWP","json":"https://pith.science/pith/H4WNEXU2SZKJCLHY3OLA7GYQWP.json","graph_json":"https://pith.science/api/pith-number/H4WNEXU2SZKJCLHY3OLA7GYQWP/graph.json","events_json":"https://pith.science/api/pith-number/H4WNEXU2SZKJCLHY3OLA7GYQWP/events.json","paper":"https://pith.science/paper/H4WNEXU2"},"agent_actions":{"view_html":"https://pith.science/pith/H4WNEXU2SZKJCLHY3OLA7GYQWP","download_json":"https://pith.science/pith/H4WNEXU2SZKJCLHY3OLA7GYQWP.json","view_paper":"https://pith.science/paper/H4WNEXU2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10076&json=true","fetch_graph":"https://pith.science/api/pith-number/H4WNEXU2SZKJCLHY3OLA7GYQWP/graph.json","fetch_events":"https://pith.science/api/pith-number/H4WNEXU2SZKJCLHY3OLA7GYQWP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4WNEXU2SZKJCLHY3OLA7GYQWP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4WNEXU2SZKJCLHY3OLA7GYQWP/action/storage_attestation","attest_author":"https://pith.science/pith/H4WNEXU2SZKJCLHY3OLA7GYQWP/action/author_attestation","sign_citation":"https://pith.science/pith/H4WNEXU2SZKJCLHY3OLA7GYQWP/action/citation_signature","submit_replication":"https://pith.science/pith/H4WNEXU2SZKJCLHY3OLA7GYQWP/action/replication_record"}},"created_at":"2026-07-05T07:56:29.854200+00:00","updated_at":"2026-07-05T07:56:29.854200+00:00"}