{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L7U2B7BQ6SX7B2OHPASLB34HBL","short_pith_number":"pith:L7U2B7BQ","schema_version":"1.0","canonical_sha256":"5fe9a0fc30f4aff0e9c77824b0ef870aed672c666be97be8c3085e02dc97deb1","source":{"kind":"arxiv","id":"2511.18436","version":2},"attestation_state":"computed","paper":{"title":"When Generative Replay Meets Evolving Deepfakes: Dual Confusion-Aware Regularization for Incremental Face Forgery Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baojin Huang, Hao Shen, Jikang Cheng, Renye Yan, Wei Peng, Zhongyuan Wang","submitted_at":"2025-11-23T13:09:02Z","abstract_excerpt":"The rapid advancement of face generation techniques has introduced an increasing variety of forgery methods, making incremental deepfake detection essential for maintaining robust detectors. While generative replay provides a promising solution to alleviate catastrophic forgetting without storing historical data, its effectiveness is hindered by \\textbf{domain confusion} between generated samples and real data. We observe that replay samples fall into two categories: when the replay generator closely resembles the newly introduced forgery model, generated real samples overlap with the fake dom"},"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":"2511.18436","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-23T13:09:02Z","cross_cats_sorted":[],"title_canon_sha256":"c836affec1b72becbef9c6b3ac1ef353ad9461f596bbf38727df1335023dece8","abstract_canon_sha256":"4c9776c85e3ae5f4a42e3e47e306b061b0776019cfd223758325f394f1d56676"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:20:40.049151Z","signature_b64":"yo6O3pOKMj9x5DXobfbN5u/7vOwA5WTZ4HpHJnRuGsTvqjAz9TrI4ZusB+ZqNJhZAvBea/UoG9l94+WQ96eDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fe9a0fc30f4aff0e9c77824b0ef870aed672c666be97be8c3085e02dc97deb1","last_reissued_at":"2026-07-21T01:20:40.048126Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:20:40.048126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Generative Replay Meets Evolving Deepfakes: Dual Confusion-Aware Regularization for Incremental Face Forgery Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baojin Huang, Hao Shen, Jikang Cheng, Renye Yan, Wei Peng, Zhongyuan Wang","submitted_at":"2025-11-23T13:09:02Z","abstract_excerpt":"The rapid advancement of face generation techniques has introduced an increasing variety of forgery methods, making incremental deepfake detection essential for maintaining robust detectors. While generative replay provides a promising solution to alleviate catastrophic forgetting without storing historical data, its effectiveness is hindered by \\textbf{domain confusion} between generated samples and real data. We observe that replay samples fall into two categories: when the replay generator closely resembles the newly introduced forgery model, generated real samples overlap with the fake dom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.18436","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/2511.18436/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":"2511.18436","created_at":"2026-07-21T01:20:40.048618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.18436v2","created_at":"2026-07-21T01:20:40.048618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.18436","created_at":"2026-07-21T01:20:40.048618+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7U2B7BQ6SX7","created_at":"2026-07-21T01:20:40.048618+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7U2B7BQ6SX7B2OH","created_at":"2026-07-21T01:20:40.048618+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7U2B7BQ","created_at":"2026-07-21T01:20:40.048618+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/L7U2B7BQ6SX7B2OHPASLB34HBL","json":"https://pith.science/pith/L7U2B7BQ6SX7B2OHPASLB34HBL.json","graph_json":"https://pith.science/api/pith-number/L7U2B7BQ6SX7B2OHPASLB34HBL/graph.json","events_json":"https://pith.science/api/pith-number/L7U2B7BQ6SX7B2OHPASLB34HBL/events.json","paper":"https://pith.science/paper/L7U2B7BQ"},"agent_actions":{"view_html":"https://pith.science/pith/L7U2B7BQ6SX7B2OHPASLB34HBL","download_json":"https://pith.science/pith/L7U2B7BQ6SX7B2OHPASLB34HBL.json","view_paper":"https://pith.science/paper/L7U2B7BQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.18436&json=true","fetch_graph":"https://pith.science/api/pith-number/L7U2B7BQ6SX7B2OHPASLB34HBL/graph.json","fetch_events":"https://pith.science/api/pith-number/L7U2B7BQ6SX7B2OHPASLB34HBL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7U2B7BQ6SX7B2OHPASLB34HBL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7U2B7BQ6SX7B2OHPASLB34HBL/action/storage_attestation","attest_author":"https://pith.science/pith/L7U2B7BQ6SX7B2OHPASLB34HBL/action/author_attestation","sign_citation":"https://pith.science/pith/L7U2B7BQ6SX7B2OHPASLB34HBL/action/citation_signature","submit_replication":"https://pith.science/pith/L7U2B7BQ6SX7B2OHPASLB34HBL/action/replication_record"}},"created_at":"2026-07-21T01:20:40.048618+00:00","updated_at":"2026-07-21T01:20:40.048618+00:00"}