{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CJCNEXZLXVENCMLJ57EW5UDS5N","short_pith_number":"pith:CJCNEXZL","schema_version":"1.0","canonical_sha256":"1244d25f2bbd48d13169efc96ed072eb6a0d41b3f8878e4a0db69033c45302d8","source":{"kind":"arxiv","id":"2307.15157","version":2},"attestation_state":"computed","paper":{"title":"R-LPIPS: An Adversarially Robust Perceptual Similarity Metric","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Alexandre Araujo, Farshad Khorrami, Prashanth Krishnamurthy, Sara Ghazanfari, Siddharth Garg","submitted_at":"2023-07-27T19:11:31Z","abstract_excerpt":"Similarity metrics have played a significant role in computer vision to capture the underlying semantics of images. In recent years, advanced similarity metrics, such as the Learned Perceptual Image Patch Similarity (LPIPS), have emerged. These metrics leverage deep features extracted from trained neural networks and have demonstrated a remarkable ability to closely align with human perception when evaluating relative image similarity. However, it is now well-known that neural networks are susceptible to adversarial examples, i.e., small perturbations invisible to humans crafted to deliberatel"},"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":"2307.15157","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-27T19:11:31Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"a2d59eb3c893b4c2869383a44e17d848224a48029b6ab7bc9eade5fc00dcbe6c","abstract_canon_sha256":"81f7288f3628731275c00c7d4a118cd5355954a5178586e3710b3eed91b4fec7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:54.315457Z","signature_b64":"Fdhl0pufWD8HQDvpAO++6005npqlPihuCI5kkkWYcxRhbq0CX31tdgtt651PamnMrAp+IRP+WZb3KsTI9uTdDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1244d25f2bbd48d13169efc96ed072eb6a0d41b3f8878e4a0db69033c45302d8","last_reissued_at":"2026-07-05T06:35:54.315094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:54.315094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R-LPIPS: An Adversarially Robust Perceptual Similarity Metric","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Alexandre Araujo, Farshad Khorrami, Prashanth Krishnamurthy, Sara Ghazanfari, Siddharth Garg","submitted_at":"2023-07-27T19:11:31Z","abstract_excerpt":"Similarity metrics have played a significant role in computer vision to capture the underlying semantics of images. In recent years, advanced similarity metrics, such as the Learned Perceptual Image Patch Similarity (LPIPS), have emerged. These metrics leverage deep features extracted from trained neural networks and have demonstrated a remarkable ability to closely align with human perception when evaluating relative image similarity. However, it is now well-known that neural networks are susceptible to adversarial examples, i.e., small perturbations invisible to humans crafted to deliberatel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15157","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/2307.15157/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":"2307.15157","created_at":"2026-07-05T06:35:54.315151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.15157v2","created_at":"2026-07-05T06:35:54.315151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15157","created_at":"2026-07-05T06:35:54.315151+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJCNEXZLXVEN","created_at":"2026-07-05T06:35:54.315151+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJCNEXZLXVENCMLJ","created_at":"2026-07-05T06:35:54.315151+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJCNEXZL","created_at":"2026-07-05T06:35:54.315151+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25191","citing_title":"Injecting Image Guidance into Text-Conditioned Diffusion Models at Inference","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20510","citing_title":"ShadeBench: A Benchmark Dataset for Building Shade Simulation in Sustainable Society","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17500","citing_title":"The Silent Brush: Evaluating Artistic Style Leakage in AI Art Generation","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CJCNEXZLXVENCMLJ57EW5UDS5N","json":"https://pith.science/pith/CJCNEXZLXVENCMLJ57EW5UDS5N.json","graph_json":"https://pith.science/api/pith-number/CJCNEXZLXVENCMLJ57EW5UDS5N/graph.json","events_json":"https://pith.science/api/pith-number/CJCNEXZLXVENCMLJ57EW5UDS5N/events.json","paper":"https://pith.science/paper/CJCNEXZL"},"agent_actions":{"view_html":"https://pith.science/pith/CJCNEXZLXVENCMLJ57EW5UDS5N","download_json":"https://pith.science/pith/CJCNEXZLXVENCMLJ57EW5UDS5N.json","view_paper":"https://pith.science/paper/CJCNEXZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.15157&json=true","fetch_graph":"https://pith.science/api/pith-number/CJCNEXZLXVENCMLJ57EW5UDS5N/graph.json","fetch_events":"https://pith.science/api/pith-number/CJCNEXZLXVENCMLJ57EW5UDS5N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJCNEXZLXVENCMLJ57EW5UDS5N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJCNEXZLXVENCMLJ57EW5UDS5N/action/storage_attestation","attest_author":"https://pith.science/pith/CJCNEXZLXVENCMLJ57EW5UDS5N/action/author_attestation","sign_citation":"https://pith.science/pith/CJCNEXZLXVENCMLJ57EW5UDS5N/action/citation_signature","submit_replication":"https://pith.science/pith/CJCNEXZLXVENCMLJ57EW5UDS5N/action/replication_record"}},"created_at":"2026-07-05T06:35:54.315151+00:00","updated_at":"2026-07-05T06:35:54.315151+00:00"}