{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EKVQXP6XWKXVNZR2XMUIL2IHQU","short_pith_number":"pith:EKVQXP6X","schema_version":"1.0","canonical_sha256":"22ab0bbfd7b2af56e63abb2885e90785391ad692150f67f6442f215b2ba94217","source":{"kind":"arxiv","id":"1812.02510","version":2},"attestation_state":"computed","paper":{"title":"ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas R\\\"ossler, Christian Riess, Davide Cozzolino, Justus Thies, Luisa Verdoliva, Matthias Nie{\\ss}ner","submitted_at":"2018-12-06T13:11:09Z","abstract_excerpt":"Distinguishing manipulated from real images is becoming increasingly difficult as new sophisticated image forgery approaches come out by the day. Naive classification approaches based on Convolutional Neural Networks (CNNs) show excellent performance in detecting image manipulations when they are trained on a specific forgery method. However, on examples from unseen manipulation approaches, their performance drops significantly. To address this limitation in transferability, we introduce Forensic-Transfer (FT). We devise a learning-based forensic detector which adapts well to new domains, i.e."},"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":"1812.02510","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-06T13:11:09Z","cross_cats_sorted":[],"title_canon_sha256":"80da6db1d864d0e4054484dd20f7490a1cfeb2c792c46672cd72b513ef40ea14","abstract_canon_sha256":"904687fb842bf577d25ba4f54400b4d8944097e1d77315ff428f680c1e370c78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:22:23.118923Z","signature_b64":"XY08AxPD7Q2UmO07XAQMeVYXpYrqhDyMdOIbMZfjLZEyfOKO83AcZ/5B2wxgZjy3fKhIl/7xeOcKHabsVYPqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22ab0bbfd7b2af56e63abb2885e90785391ad692150f67f6442f215b2ba94217","last_reissued_at":"2026-07-05T00:22:23.118448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:22:23.118448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas R\\\"ossler, Christian Riess, Davide Cozzolino, Justus Thies, Luisa Verdoliva, Matthias Nie{\\ss}ner","submitted_at":"2018-12-06T13:11:09Z","abstract_excerpt":"Distinguishing manipulated from real images is becoming increasingly difficult as new sophisticated image forgery approaches come out by the day. Naive classification approaches based on Convolutional Neural Networks (CNNs) show excellent performance in detecting image manipulations when they are trained on a specific forgery method. However, on examples from unseen manipulation approaches, their performance drops significantly. To address this limitation in transferability, we introduce Forensic-Transfer (FT). We devise a learning-based forensic detector which adapts well to new domains, i.e."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02510","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/1812.02510/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":"1812.02510","created_at":"2026-07-05T00:22:23.118505+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.02510v2","created_at":"2026-07-05T00:22:23.118505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02510","created_at":"2026-07-05T00:22:23.118505+00:00"},{"alias_kind":"pith_short_12","alias_value":"EKVQXP6XWKXV","created_at":"2026-07-05T00:22:23.118505+00:00"},{"alias_kind":"pith_short_16","alias_value":"EKVQXP6XWKXVNZR2","created_at":"2026-07-05T00:22:23.118505+00:00"},{"alias_kind":"pith_short_8","alias_value":"EKVQXP6X","created_at":"2026-07-05T00:22:23.118505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.15406","citing_title":"Causal Fingerprints of AI Generative Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15633","citing_title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection","ref_index":149,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27590","citing_title":"Fake3DGS: A Benchmark for 3D Manipulation Detection in Neural Rendering","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EKVQXP6XWKXVNZR2XMUIL2IHQU","json":"https://pith.science/pith/EKVQXP6XWKXVNZR2XMUIL2IHQU.json","graph_json":"https://pith.science/api/pith-number/EKVQXP6XWKXVNZR2XMUIL2IHQU/graph.json","events_json":"https://pith.science/api/pith-number/EKVQXP6XWKXVNZR2XMUIL2IHQU/events.json","paper":"https://pith.science/paper/EKVQXP6X"},"agent_actions":{"view_html":"https://pith.science/pith/EKVQXP6XWKXVNZR2XMUIL2IHQU","download_json":"https://pith.science/pith/EKVQXP6XWKXVNZR2XMUIL2IHQU.json","view_paper":"https://pith.science/paper/EKVQXP6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.02510&json=true","fetch_graph":"https://pith.science/api/pith-number/EKVQXP6XWKXVNZR2XMUIL2IHQU/graph.json","fetch_events":"https://pith.science/api/pith-number/EKVQXP6XWKXVNZR2XMUIL2IHQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EKVQXP6XWKXVNZR2XMUIL2IHQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EKVQXP6XWKXVNZR2XMUIL2IHQU/action/storage_attestation","attest_author":"https://pith.science/pith/EKVQXP6XWKXVNZR2XMUIL2IHQU/action/author_attestation","sign_citation":"https://pith.science/pith/EKVQXP6XWKXVNZR2XMUIL2IHQU/action/citation_signature","submit_replication":"https://pith.science/pith/EKVQXP6XWKXVNZR2XMUIL2IHQU/action/replication_record"}},"created_at":"2026-07-05T00:22:23.118505+00:00","updated_at":"2026-07-05T00:22:23.118505+00:00"}