{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CQ3RVAP5ZSKVZBXOHSQWV3OMNR","short_pith_number":"pith:CQ3RVAP5","schema_version":"1.0","canonical_sha256":"14371a81fdcc955c86ee3ca16aedcc6c5d40d5c5204f5729a79c32ce0b64ba55","source":{"kind":"arxiv","id":"2304.13349","version":2},"attestation_state":"computed","paper":{"title":"Discrepancy-Guided Reconstruction Learning for Image Forgery Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dong Zhang, Haipeng Chen, Long Chen, Zenan Shi","submitted_at":"2023-04-26T07:40:43Z","abstract_excerpt":"In this paper, we propose a novel image forgery detection paradigm for boosting the model learning capacity on both forgery-sensitive and genuine compact visual patterns. Compared to the existing methods that only focus on the discrepant-specific patterns (\\eg, noises, textures, and frequencies), our method has a greater generalization. Specifically, we first propose a Discrepancy-Guided Encoder (DisGE) to extract forgery-sensitive visual patterns. DisGE consists of two branches, where the mainstream backbone branch is used to extract general semantic features, and the accessorial discrepant 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":"2304.13349","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-26T07:40:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae1b68b3aed6c49da7a6776572392f831cf72510dd701be699ee12e22bdd0043","abstract_canon_sha256":"ab9a317e973969dcb01b241ec34e6e1c6c7bb17fdd4039b13e8e2229c00f9584"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:44.161803Z","signature_b64":"6H98dyzMDA8PFsNEPKoxfUWjSSaekLpOXZPfRs+4A3lowAVRhkozAypAy9BSK335bQPuPF7MlmK6g5ZWW1XBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14371a81fdcc955c86ee3ca16aedcc6c5d40d5c5204f5729a79c32ce0b64ba55","last_reissued_at":"2026-07-05T06:06:44.161358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:44.161358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discrepancy-Guided Reconstruction Learning for Image Forgery Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dong Zhang, Haipeng Chen, Long Chen, Zenan Shi","submitted_at":"2023-04-26T07:40:43Z","abstract_excerpt":"In this paper, we propose a novel image forgery detection paradigm for boosting the model learning capacity on both forgery-sensitive and genuine compact visual patterns. Compared to the existing methods that only focus on the discrepant-specific patterns (\\eg, noises, textures, and frequencies), our method has a greater generalization. Specifically, we first propose a Discrepancy-Guided Encoder (DisGE) to extract forgery-sensitive visual patterns. DisGE consists of two branches, where the mainstream backbone branch is used to extract general semantic features, and the accessorial discrepant e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13349","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/2304.13349/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":"2304.13349","created_at":"2026-07-05T06:06:44.161425+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.13349v2","created_at":"2026-07-05T06:06:44.161425+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13349","created_at":"2026-07-05T06:06:44.161425+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQ3RVAP5ZSKV","created_at":"2026-07-05T06:06:44.161425+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQ3RVAP5ZSKVZBXO","created_at":"2026-07-05T06:06:44.161425+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQ3RVAP5","created_at":"2026-07-05T06:06:44.161425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20653","citing_title":"RoGA: Towards Generalizable Deepfake Detection through Robust Gradient Alignment","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQ3RVAP5ZSKVZBXOHSQWV3OMNR","json":"https://pith.science/pith/CQ3RVAP5ZSKVZBXOHSQWV3OMNR.json","graph_json":"https://pith.science/api/pith-number/CQ3RVAP5ZSKVZBXOHSQWV3OMNR/graph.json","events_json":"https://pith.science/api/pith-number/CQ3RVAP5ZSKVZBXOHSQWV3OMNR/events.json","paper":"https://pith.science/paper/CQ3RVAP5"},"agent_actions":{"view_html":"https://pith.science/pith/CQ3RVAP5ZSKVZBXOHSQWV3OMNR","download_json":"https://pith.science/pith/CQ3RVAP5ZSKVZBXOHSQWV3OMNR.json","view_paper":"https://pith.science/paper/CQ3RVAP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.13349&json=true","fetch_graph":"https://pith.science/api/pith-number/CQ3RVAP5ZSKVZBXOHSQWV3OMNR/graph.json","fetch_events":"https://pith.science/api/pith-number/CQ3RVAP5ZSKVZBXOHSQWV3OMNR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQ3RVAP5ZSKVZBXOHSQWV3OMNR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQ3RVAP5ZSKVZBXOHSQWV3OMNR/action/storage_attestation","attest_author":"https://pith.science/pith/CQ3RVAP5ZSKVZBXOHSQWV3OMNR/action/author_attestation","sign_citation":"https://pith.science/pith/CQ3RVAP5ZSKVZBXOHSQWV3OMNR/action/citation_signature","submit_replication":"https://pith.science/pith/CQ3RVAP5ZSKVZBXOHSQWV3OMNR/action/replication_record"}},"created_at":"2026-07-05T06:06:44.161425+00:00","updated_at":"2026-07-05T06:06:44.161425+00:00"}