{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T56O23BWAH24IZJL7T77TMM7VS","short_pith_number":"pith:T56O23BW","schema_version":"1.0","canonical_sha256":"9f7ced6c3601f5c4652bfcfff9b19facbff581ae6fbbbb55e7aa9055b7157514","source":{"kind":"arxiv","id":"2507.18015","version":1},"attestation_state":"computed","paper":{"title":"Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Delong Zhu, Siwei Lyu, Xinjie Cui, Yuezun Li","submitted_at":"2025-07-24T01:12:28Z","abstract_excerpt":"The rapid advancement of AI technologies has significantly increased the diversity of DeepFake videos circulating online, posing a pressing challenge for \\textit{generalizable forensics}, \\ie, detecting a wide range of unseen DeepFake types using a single model. Addressing this challenge requires datasets that are not only large-scale but also rich in forgery diversity. However, most existing datasets, despite their scale, include only a limited variety of forgery types, making them insufficient for developing generalizable detection methods. Therefore, we build upon our earlier Celeb-DF datas"},"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":"2507.18015","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-24T01:12:28Z","cross_cats_sorted":[],"title_canon_sha256":"dc83e172a2080b9d5656e5b047705d1a6d6f7cb292d88763d15550f225f407ca","abstract_canon_sha256":"29f63b01c5d6eccfc5fc0bbdf3bc342381f5a62e109ea1276b44de7b2b6a81e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:39.413679Z","signature_b64":"TJgR2VNUr3DN6PgPts71n7h3p5m6CMTAE1DgTwOwY5O7uvOK5oFb+4zrcDvTTEPnVN1olk3fKstsHq3al5B2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f7ced6c3601f5c4652bfcfff9b19facbff581ae6fbbbb55e7aa9055b7157514","last_reissued_at":"2026-07-05T11:42:39.413242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:39.413242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Delong Zhu, Siwei Lyu, Xinjie Cui, Yuezun Li","submitted_at":"2025-07-24T01:12:28Z","abstract_excerpt":"The rapid advancement of AI technologies has significantly increased the diversity of DeepFake videos circulating online, posing a pressing challenge for \\textit{generalizable forensics}, \\ie, detecting a wide range of unseen DeepFake types using a single model. Addressing this challenge requires datasets that are not only large-scale but also rich in forgery diversity. However, most existing datasets, despite their scale, include only a limited variety of forgery types, making them insufficient for developing generalizable detection methods. Therefore, we build upon our earlier Celeb-DF datas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18015","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/2507.18015/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":"2507.18015","created_at":"2026-07-05T11:42:39.413298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18015v1","created_at":"2026-07-05T11:42:39.413298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18015","created_at":"2026-07-05T11:42:39.413298+00:00"},{"alias_kind":"pith_short_12","alias_value":"T56O23BWAH24","created_at":"2026-07-05T11:42:39.413298+00:00"},{"alias_kind":"pith_short_16","alias_value":"T56O23BWAH24IZJL","created_at":"2026-07-05T11:42:39.413298+00:00"},{"alias_kind":"pith_short_8","alias_value":"T56O23BW","created_at":"2026-07-05T11:42:39.413298+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26384","citing_title":"What Do Deepfake Benchmarks Measure? An Audit Using Frozen Self-Supervised Representations","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01885","citing_title":"Divide and Conquer: Reliable Multi-View Evidential Learning for Deepfake Detection","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2504.14129","citing_title":"PVLM: Parsing-Aware Vision Language Model with Dynamic Contrastive Learning for Zero-Shot Deepfake Attribution","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2508.06248","citing_title":"Deepfake Detection that Generalizes Across Benchmarks","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04939","citing_title":"SynthForensics: Benchmarking and Evaluating People-Centric Synthetic Video Deepfakes","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10334","citing_title":"The Alpha Blending Hypothesis: Compositing Shortcut in Deepfake Detection","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00960","citing_title":"Energy-Based Constraint Networks: Learning Structural Coherence Across Modalities","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07763","citing_title":"Beyond Surface Artifacts: Capturing Shared Latent Forgery Knowledge Across Modalities","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04405","citing_title":"Detecting Deepfakes via Hamiltonian Dynamics","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T56O23BWAH24IZJL7T77TMM7VS","json":"https://pith.science/pith/T56O23BWAH24IZJL7T77TMM7VS.json","graph_json":"https://pith.science/api/pith-number/T56O23BWAH24IZJL7T77TMM7VS/graph.json","events_json":"https://pith.science/api/pith-number/T56O23BWAH24IZJL7T77TMM7VS/events.json","paper":"https://pith.science/paper/T56O23BW"},"agent_actions":{"view_html":"https://pith.science/pith/T56O23BWAH24IZJL7T77TMM7VS","download_json":"https://pith.science/pith/T56O23BWAH24IZJL7T77TMM7VS.json","view_paper":"https://pith.science/paper/T56O23BW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18015&json=true","fetch_graph":"https://pith.science/api/pith-number/T56O23BWAH24IZJL7T77TMM7VS/graph.json","fetch_events":"https://pith.science/api/pith-number/T56O23BWAH24IZJL7T77TMM7VS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T56O23BWAH24IZJL7T77TMM7VS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T56O23BWAH24IZJL7T77TMM7VS/action/storage_attestation","attest_author":"https://pith.science/pith/T56O23BWAH24IZJL7T77TMM7VS/action/author_attestation","sign_citation":"https://pith.science/pith/T56O23BWAH24IZJL7T77TMM7VS/action/citation_signature","submit_replication":"https://pith.science/pith/T56O23BWAH24IZJL7T77TMM7VS/action/replication_record"}},"created_at":"2026-07-05T11:42:39.413298+00:00","updated_at":"2026-07-05T11:42:39.413298+00:00"}