{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZKS2MFM2K22KBKFPSHBALTFUMV","short_pith_number":"pith:ZKS2MFM2","schema_version":"1.0","canonical_sha256":"caa5a6159a56b4a0a8af91c205ccb465415d5677f53efa28953785bf5a7ca9f9","source":{"kind":"arxiv","id":"2411.13553","version":2},"attestation_state":"computed","paper":{"title":"AI-generated Image Detection: Passive or Watermark?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CR","authors_text":"Amir Sadovnik, Arka Daw, Moyang Guo, Neil Gong, Yuepeng Hu, Zeyu Li, Zhengyuan Jiang","submitted_at":"2024-11-20T18:59:58Z","abstract_excerpt":"While text-to-image models offer numerous benefits, they also pose significant societal risks. Detecting AI-generated images is crucial for mitigating these risks. Detection methods can be broadly categorized into passive and watermark-based approaches: passive detectors rely on artifacts present in AI-generated images, whereas watermark-based detectors proactively embed watermarks into such images. A key question is which type of detector performs better in terms of effectiveness, robustness, and efficiency. However, the current literature lacks a comprehensive understanding of this issue. In"},"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":"2411.13553","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-11-20T18:59:58Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"8fd1e65a1dc6e66b47f8eacf8876ae31d9246c4a566fb43b45bbb69ab8dd4ab9","abstract_canon_sha256":"204335e7483bb00d5b9d501c7b7664f65635eb624262afe023dcd80dbdc32375"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:20.572804Z","signature_b64":"4T6Q09hyRYeGFwtbkEqI6Y4zWEL2Rn09QIMEroMviJEiR2Em3pewlxO1VZFcWmKKdkZ+rHAZ3/86MzQmZWJkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caa5a6159a56b4a0a8af91c205ccb465415d5677f53efa28953785bf5a7ca9f9","last_reissued_at":"2026-07-05T09:59:20.572329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:20.572329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI-generated Image Detection: Passive or Watermark?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CR","authors_text":"Amir Sadovnik, Arka Daw, Moyang Guo, Neil Gong, Yuepeng Hu, Zeyu Li, Zhengyuan Jiang","submitted_at":"2024-11-20T18:59:58Z","abstract_excerpt":"While text-to-image models offer numerous benefits, they also pose significant societal risks. Detecting AI-generated images is crucial for mitigating these risks. Detection methods can be broadly categorized into passive and watermark-based approaches: passive detectors rely on artifacts present in AI-generated images, whereas watermark-based detectors proactively embed watermarks into such images. A key question is which type of detector performs better in terms of effectiveness, robustness, and efficiency. However, the current literature lacks a comprehensive understanding of this issue. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13553","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/2411.13553/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":"2411.13553","created_at":"2026-07-05T09:59:20.572384+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13553v2","created_at":"2026-07-05T09:59:20.572384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13553","created_at":"2026-07-05T09:59:20.572384+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKS2MFM2K22K","created_at":"2026-07-05T09:59:20.572384+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKS2MFM2K22KBKFP","created_at":"2026-07-05T09:59:20.572384+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKS2MFM2","created_at":"2026-07-05T09:59:20.572384+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/ZKS2MFM2K22KBKFPSHBALTFUMV","json":"https://pith.science/pith/ZKS2MFM2K22KBKFPSHBALTFUMV.json","graph_json":"https://pith.science/api/pith-number/ZKS2MFM2K22KBKFPSHBALTFUMV/graph.json","events_json":"https://pith.science/api/pith-number/ZKS2MFM2K22KBKFPSHBALTFUMV/events.json","paper":"https://pith.science/paper/ZKS2MFM2"},"agent_actions":{"view_html":"https://pith.science/pith/ZKS2MFM2K22KBKFPSHBALTFUMV","download_json":"https://pith.science/pith/ZKS2MFM2K22KBKFPSHBALTFUMV.json","view_paper":"https://pith.science/paper/ZKS2MFM2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13553&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKS2MFM2K22KBKFPSHBALTFUMV/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKS2MFM2K22KBKFPSHBALTFUMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKS2MFM2K22KBKFPSHBALTFUMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKS2MFM2K22KBKFPSHBALTFUMV/action/storage_attestation","attest_author":"https://pith.science/pith/ZKS2MFM2K22KBKFPSHBALTFUMV/action/author_attestation","sign_citation":"https://pith.science/pith/ZKS2MFM2K22KBKFPSHBALTFUMV/action/citation_signature","submit_replication":"https://pith.science/pith/ZKS2MFM2K22KBKFPSHBALTFUMV/action/replication_record"}},"created_at":"2026-07-05T09:59:20.572384+00:00","updated_at":"2026-07-05T09:59:20.572384+00:00"}