{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7SY47WMKQ2E43EO7TVTDP6M4OS","short_pith_number":"pith:7SY47WMK","schema_version":"1.0","canonical_sha256":"fcb1cfd98a8689cd91df9d6637f99c748bc470aa41bdfc3bed184b4aae56e182","source":{"kind":"arxiv","id":"2403.07240","version":1},"attestation_state":"computed","paper":{"title":"Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuangchuang Tan, Guanghua Gu, Ping Liu, Shikui Wei, Yao Zhao, Yunchao Wei","submitted_at":"2024-03-12T01:28:00Z","abstract_excerpt":"This research addresses the challenge of developing a universal deepfake detector that can effectively identify unseen deepfake images despite limited training data. Existing frequency-based paradigms have relied on frequency-level artifacts introduced during the up-sampling in GAN pipelines to detect forgeries. However, the rapid advancements in synthesis technology have led to specific artifacts for each generation model. Consequently, these detectors have exhibited a lack of proficiency in learning the frequency domain and tend to overfit to the artifacts present in the training data, leadi"},"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":"2403.07240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T01:28:00Z","cross_cats_sorted":[],"title_canon_sha256":"79c996297af32ea77c904136735fecb00e2c3a3d5319ce569bb418f7788d8891","abstract_canon_sha256":"cee4bc2fafbf639d7b81416a9c289b5bd7c0af449dc564d4e14fa693dad4a333"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:01.099951Z","signature_b64":"cWLW+Ft/A6RnVXcHND1j/y4wzOA4QS8TpMb5g/YpgRlweCvsJIHG57GKZ9eqnPmJV0kHjz1jvRMqrgSd9M4/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcb1cfd98a8689cd91df9d6637f99c748bc470aa41bdfc3bed184b4aae56e182","last_reissued_at":"2026-07-05T07:55:01.099560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:01.099560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuangchuang Tan, Guanghua Gu, Ping Liu, Shikui Wei, Yao Zhao, Yunchao Wei","submitted_at":"2024-03-12T01:28:00Z","abstract_excerpt":"This research addresses the challenge of developing a universal deepfake detector that can effectively identify unseen deepfake images despite limited training data. Existing frequency-based paradigms have relied on frequency-level artifacts introduced during the up-sampling in GAN pipelines to detect forgeries. However, the rapid advancements in synthesis technology have led to specific artifacts for each generation model. Consequently, these detectors have exhibited a lack of proficiency in learning the frequency domain and tend to overfit to the artifacts present in the training data, leadi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07240","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/2403.07240/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":"2403.07240","created_at":"2026-07-05T07:55:01.099621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.07240v1","created_at":"2026-07-05T07:55:01.099621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07240","created_at":"2026-07-05T07:55:01.099621+00:00"},{"alias_kind":"pith_short_12","alias_value":"7SY47WMKQ2E4","created_at":"2026-07-05T07:55:01.099621+00:00"},{"alias_kind":"pith_short_16","alias_value":"7SY47WMKQ2E43EO7","created_at":"2026-07-05T07:55:01.099621+00:00"},{"alias_kind":"pith_short_8","alias_value":"7SY47WMK","created_at":"2026-07-05T07:55:01.099621+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17268","citing_title":"Fractal Characterization of Low-Correlation Signals in AI-Generated Image Detection","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7SY47WMKQ2E43EO7TVTDP6M4OS","json":"https://pith.science/pith/7SY47WMKQ2E43EO7TVTDP6M4OS.json","graph_json":"https://pith.science/api/pith-number/7SY47WMKQ2E43EO7TVTDP6M4OS/graph.json","events_json":"https://pith.science/api/pith-number/7SY47WMKQ2E43EO7TVTDP6M4OS/events.json","paper":"https://pith.science/paper/7SY47WMK"},"agent_actions":{"view_html":"https://pith.science/pith/7SY47WMKQ2E43EO7TVTDP6M4OS","download_json":"https://pith.science/pith/7SY47WMKQ2E43EO7TVTDP6M4OS.json","view_paper":"https://pith.science/paper/7SY47WMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.07240&json=true","fetch_graph":"https://pith.science/api/pith-number/7SY47WMKQ2E43EO7TVTDP6M4OS/graph.json","fetch_events":"https://pith.science/api/pith-number/7SY47WMKQ2E43EO7TVTDP6M4OS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7SY47WMKQ2E43EO7TVTDP6M4OS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7SY47WMKQ2E43EO7TVTDP6M4OS/action/storage_attestation","attest_author":"https://pith.science/pith/7SY47WMKQ2E43EO7TVTDP6M4OS/action/author_attestation","sign_citation":"https://pith.science/pith/7SY47WMKQ2E43EO7TVTDP6M4OS/action/citation_signature","submit_replication":"https://pith.science/pith/7SY47WMKQ2E43EO7TVTDP6M4OS/action/replication_record"}},"created_at":"2026-07-05T07:55:01.099621+00:00","updated_at":"2026-07-05T07:55:01.099621+00:00"}