{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IO465RGJ4KN7NWQO2FOLIZNAP5","short_pith_number":"pith:IO465RGJ","schema_version":"1.0","canonical_sha256":"43b9eec4c9e29bf6da0ed15cb465a07f441189ce5d5b14ee7cef8d0cb7133894","source":{"kind":"arxiv","id":"2407.10736","version":1},"attestation_state":"computed","paper":{"title":"When Synthetic Traces Hide Real Content: Analysis of Stable Diffusion Image Laundering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Paolo Bestagini, Sara Mandelli, Stefano Tubaro","submitted_at":"2024-07-15T14:01:35Z","abstract_excerpt":"In recent years, methods for producing highly realistic synthetic images have significantly advanced, allowing the creation of high-quality images from text prompts that describe the desired content. Even more impressively, Stable Diffusion (SD) models now provide users with the option of creating synthetic images in an image-to-image translation fashion, modifying images in the latent space of advanced autoencoders. This striking evolution, however, brings an alarming consequence: it is possible to pass an image through SD autoencoders to reproduce a synthetic copy of the image with high real"},"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":"2407.10736","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-15T14:01:35Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"ca319fc71d2f05f9d11fed3e93b7fefd922ff7233108848ac08d8afb6a78b68c","abstract_canon_sha256":"49e9d0d554e5634a5b93572097222f2070c37b8cb0cdb89d94fd5f10e5188454"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:03.455730Z","signature_b64":"ojDQj//TsXrNeu2ghxKO0PCNpIS/kwdFjTPR3D9UcNj3SHxEPl+3z7opspIE3WBmvZ7KrXXeC3DGhU4/KKGDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43b9eec4c9e29bf6da0ed15cb465a07f441189ce5d5b14ee7cef8d0cb7133894","last_reissued_at":"2026-07-05T08:44:03.455252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:03.455252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Synthetic Traces Hide Real Content: Analysis of Stable Diffusion Image Laundering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Paolo Bestagini, Sara Mandelli, Stefano Tubaro","submitted_at":"2024-07-15T14:01:35Z","abstract_excerpt":"In recent years, methods for producing highly realistic synthetic images have significantly advanced, allowing the creation of high-quality images from text prompts that describe the desired content. Even more impressively, Stable Diffusion (SD) models now provide users with the option of creating synthetic images in an image-to-image translation fashion, modifying images in the latent space of advanced autoencoders. This striking evolution, however, brings an alarming consequence: it is possible to pass an image through SD autoencoders to reproduce a synthetic copy of the image with high real"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10736","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/2407.10736/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":"2407.10736","created_at":"2026-07-05T08:44:03.455308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10736v1","created_at":"2026-07-05T08:44:03.455308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10736","created_at":"2026-07-05T08:44:03.455308+00:00"},{"alias_kind":"pith_short_12","alias_value":"IO465RGJ4KN7","created_at":"2026-07-05T08:44:03.455308+00:00"},{"alias_kind":"pith_short_16","alias_value":"IO465RGJ4KN7NWQO","created_at":"2026-07-05T08:44:03.455308+00:00"},{"alias_kind":"pith_short_8","alias_value":"IO465RGJ","created_at":"2026-07-05T08:44:03.455308+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00175","citing_title":"Circumventing shortcuts in audio-visual deepfake detection datasets with unsupervised learning","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IO465RGJ4KN7NWQO2FOLIZNAP5","json":"https://pith.science/pith/IO465RGJ4KN7NWQO2FOLIZNAP5.json","graph_json":"https://pith.science/api/pith-number/IO465RGJ4KN7NWQO2FOLIZNAP5/graph.json","events_json":"https://pith.science/api/pith-number/IO465RGJ4KN7NWQO2FOLIZNAP5/events.json","paper":"https://pith.science/paper/IO465RGJ"},"agent_actions":{"view_html":"https://pith.science/pith/IO465RGJ4KN7NWQO2FOLIZNAP5","download_json":"https://pith.science/pith/IO465RGJ4KN7NWQO2FOLIZNAP5.json","view_paper":"https://pith.science/paper/IO465RGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10736&json=true","fetch_graph":"https://pith.science/api/pith-number/IO465RGJ4KN7NWQO2FOLIZNAP5/graph.json","fetch_events":"https://pith.science/api/pith-number/IO465RGJ4KN7NWQO2FOLIZNAP5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IO465RGJ4KN7NWQO2FOLIZNAP5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IO465RGJ4KN7NWQO2FOLIZNAP5/action/storage_attestation","attest_author":"https://pith.science/pith/IO465RGJ4KN7NWQO2FOLIZNAP5/action/author_attestation","sign_citation":"https://pith.science/pith/IO465RGJ4KN7NWQO2FOLIZNAP5/action/citation_signature","submit_replication":"https://pith.science/pith/IO465RGJ4KN7NWQO2FOLIZNAP5/action/replication_record"}},"created_at":"2026-07-05T08:44:03.455308+00:00","updated_at":"2026-07-05T08:44:03.455308+00:00"}