{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:A3JFIMF5XZU2WLXYQQXBJGT3BZ","short_pith_number":"pith:A3JFIMF5","schema_version":"1.0","canonical_sha256":"06d25430bdbe69ab2ef8842e149a7b0e5efabfbfc7fdafc2bd447d37e7f9c16c","source":{"kind":"arxiv","id":"1805.04953","version":1},"attestation_state":"computed","paper":{"title":"Learning Rich Features for Image Manipulation Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Larry S. Davis, Peng Zhou, Vlad I. Morariu, Xintong Han","submitted_at":"2018-05-13T21:29:38Z","abstract_excerpt":"Image manipulation detection is different from traditional semantic object detection because it pays more attention to tampering artifacts than to image content, which suggests that richer features need to be learned. We propose a two-stream Faster R-CNN network and train it endto- end to detect the tampered regions given a manipulated image. One of the two streams is an RGB stream whose purpose is to extract features from the RGB image input to find tampering artifacts like strong contrast difference, unnatural tampered boundaries, and so on. The other is a noise stream that leverages the noi"},"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":"1805.04953","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-05-13T21:29:38Z","cross_cats_sorted":[],"title_canon_sha256":"eb5271c6f672b9171413494762b566b2b6f5deae05b66bb89277124605a903c4","abstract_canon_sha256":"d85eab02af0415e3095e6d3e682c582f1079753f8dcb9848afee2da22f558004"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:04.260283Z","signature_b64":"v23uWBmp74PRoH0ELLkqP+HgrC7rBA8sXjBmun6qLJEwUAD6EgVay9/XiheTn5HHv4AR8B2smnrg9AtZRjZzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06d25430bdbe69ab2ef8842e149a7b0e5efabfbfc7fdafc2bd447d37e7f9c16c","last_reissued_at":"2026-05-18T00:16:04.259866Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:04.259866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Rich Features for Image Manipulation Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Larry S. Davis, Peng Zhou, Vlad I. Morariu, Xintong Han","submitted_at":"2018-05-13T21:29:38Z","abstract_excerpt":"Image manipulation detection is different from traditional semantic object detection because it pays more attention to tampering artifacts than to image content, which suggests that richer features need to be learned. We propose a two-stream Faster R-CNN network and train it endto- end to detect the tampered regions given a manipulated image. One of the two streams is an RGB stream whose purpose is to extract features from the RGB image input to find tampering artifacts like strong contrast difference, unnatural tampered boundaries, and so on. The other is a noise stream that leverages the noi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.04953","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":""},"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":"1805.04953","created_at":"2026-05-18T00:16:04.259946+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.04953v1","created_at":"2026-05-18T00:16:04.259946+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.04953","created_at":"2026-05-18T00:16:04.259946+00:00"},{"alias_kind":"pith_short_12","alias_value":"A3JFIMF5XZU2","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"A3JFIMF5XZU2WLXY","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"A3JFIMF5","created_at":"2026-05-18T12:32:13.499390+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/A3JFIMF5XZU2WLXYQQXBJGT3BZ","json":"https://pith.science/pith/A3JFIMF5XZU2WLXYQQXBJGT3BZ.json","graph_json":"https://pith.science/api/pith-number/A3JFIMF5XZU2WLXYQQXBJGT3BZ/graph.json","events_json":"https://pith.science/api/pith-number/A3JFIMF5XZU2WLXYQQXBJGT3BZ/events.json","paper":"https://pith.science/paper/A3JFIMF5"},"agent_actions":{"view_html":"https://pith.science/pith/A3JFIMF5XZU2WLXYQQXBJGT3BZ","download_json":"https://pith.science/pith/A3JFIMF5XZU2WLXYQQXBJGT3BZ.json","view_paper":"https://pith.science/paper/A3JFIMF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.04953&json=true","fetch_graph":"https://pith.science/api/pith-number/A3JFIMF5XZU2WLXYQQXBJGT3BZ/graph.json","fetch_events":"https://pith.science/api/pith-number/A3JFIMF5XZU2WLXYQQXBJGT3BZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A3JFIMF5XZU2WLXYQQXBJGT3BZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A3JFIMF5XZU2WLXYQQXBJGT3BZ/action/storage_attestation","attest_author":"https://pith.science/pith/A3JFIMF5XZU2WLXYQQXBJGT3BZ/action/author_attestation","sign_citation":"https://pith.science/pith/A3JFIMF5XZU2WLXYQQXBJGT3BZ/action/citation_signature","submit_replication":"https://pith.science/pith/A3JFIMF5XZU2WLXYQQXBJGT3BZ/action/replication_record"}},"created_at":"2026-05-18T00:16:04.259946+00:00","updated_at":"2026-05-18T00:16:04.259946+00:00"}