{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:O7IQNZQ4Z3JPL6BAYEF4QICWU7","short_pith_number":"pith:O7IQNZQ4","schema_version":"1.0","canonical_sha256":"77d106e61cced2f5f820c10bc82056a7efaf295a1c9460e2139ba5aa9fad309a","source":{"kind":"arxiv","id":"2105.14376","version":1},"attestation_state":"computed","paper":{"title":"Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Margret Keuper, Mario Fritz, Ning Yu, Yang He","submitted_at":"2021-05-29T21:22:24Z","abstract_excerpt":"The rapid advances in deep generative models over the past years have led to highly {realistic media, known as deepfakes,} that are commonly indistinguishable from real to human eyes. These advances make assessing the authenticity of visual data increasingly difficult and pose a misinformation threat to the trustworthiness of visual content in general. Although recent work has shown strong detection accuracy of such deepfakes, the success largely relies on identifying frequency artifacts in the generated images, which will not yield a sustainable detection approach as generative models continu"},"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":"2105.14376","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-29T21:22:24Z","cross_cats_sorted":[],"title_canon_sha256":"647a70db36d25f7bf02c53b206b03cbdee571a9f1ef04063c37fc945c14b0d60","abstract_canon_sha256":"f0d72873026f6d2e260ac7ac18fd2417d00647a5ea17b3eed3fc935cac59bf4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:23.239245Z","signature_b64":"iXiM/DrMokxkORJXTrn4ejyl0yrhU/cKRuhxU973WCZ4PkOXrs2zT5u7IR1RuLVEMemXL/4WGfGT13qpOLr9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77d106e61cced2f5f820c10bc82056a7efaf295a1c9460e2139ba5aa9fad309a","last_reissued_at":"2026-07-05T02:44:23.238748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:23.238748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Margret Keuper, Mario Fritz, Ning Yu, Yang He","submitted_at":"2021-05-29T21:22:24Z","abstract_excerpt":"The rapid advances in deep generative models over the past years have led to highly {realistic media, known as deepfakes,} that are commonly indistinguishable from real to human eyes. These advances make assessing the authenticity of visual data increasingly difficult and pose a misinformation threat to the trustworthiness of visual content in general. Although recent work has shown strong detection accuracy of such deepfakes, the success largely relies on identifying frequency artifacts in the generated images, which will not yield a sustainable detection approach as generative models continu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14376","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/2105.14376/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":"2105.14376","created_at":"2026-07-05T02:44:23.238807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.14376v1","created_at":"2026-07-05T02:44:23.238807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14376","created_at":"2026-07-05T02:44:23.238807+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7IQNZQ4Z3JP","created_at":"2026-07-05T02:44:23.238807+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7IQNZQ4Z3JPL6BA","created_at":"2026-07-05T02:44:23.238807+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7IQNZQ4","created_at":"2026-07-05T02:44:23.238807+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31192","citing_title":"The Regularizing Power of Language-Training Deepfake Detectors","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04608","citing_title":"Beyond Semantics: Uncovering the Physics of Fakes via Universal Physical Descriptors for Cross-Modal Synthetic Detection","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7IQNZQ4Z3JPL6BAYEF4QICWU7","json":"https://pith.science/pith/O7IQNZQ4Z3JPL6BAYEF4QICWU7.json","graph_json":"https://pith.science/api/pith-number/O7IQNZQ4Z3JPL6BAYEF4QICWU7/graph.json","events_json":"https://pith.science/api/pith-number/O7IQNZQ4Z3JPL6BAYEF4QICWU7/events.json","paper":"https://pith.science/paper/O7IQNZQ4"},"agent_actions":{"view_html":"https://pith.science/pith/O7IQNZQ4Z3JPL6BAYEF4QICWU7","download_json":"https://pith.science/pith/O7IQNZQ4Z3JPL6BAYEF4QICWU7.json","view_paper":"https://pith.science/paper/O7IQNZQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.14376&json=true","fetch_graph":"https://pith.science/api/pith-number/O7IQNZQ4Z3JPL6BAYEF4QICWU7/graph.json","fetch_events":"https://pith.science/api/pith-number/O7IQNZQ4Z3JPL6BAYEF4QICWU7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7IQNZQ4Z3JPL6BAYEF4QICWU7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7IQNZQ4Z3JPL6BAYEF4QICWU7/action/storage_attestation","attest_author":"https://pith.science/pith/O7IQNZQ4Z3JPL6BAYEF4QICWU7/action/author_attestation","sign_citation":"https://pith.science/pith/O7IQNZQ4Z3JPL6BAYEF4QICWU7/action/citation_signature","submit_replication":"https://pith.science/pith/O7IQNZQ4Z3JPL6BAYEF4QICWU7/action/replication_record"}},"created_at":"2026-07-05T02:44:23.238807+00:00","updated_at":"2026-07-05T02:44:23.238807+00:00"}