{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DBU5ZBHETF6PLRG6MHIW4INZFK","short_pith_number":"pith:DBU5ZBHE","schema_version":"1.0","canonical_sha256":"1869dc84e4997cf5c4de61d16e21b92aaa0518818566652b54dcc63da75654e1","source":{"kind":"arxiv","id":"2501.01184","version":3},"attestation_state":"computed","paper":{"title":"Vulnerability-Aware Spatio-Temporal Learning for Generalizable Deepfake Video Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anis Kacem, Dat Nguyen, Djamila Aouada, Enjie Ghorbel, Marcella Astrid","submitted_at":"2025-01-02T10:21:34Z","abstract_excerpt":"Detecting deepfake videos is highly challenging given the complexity of characterizing spatio-temporal artifacts. Most existing methods rely on binary classifiers trained using real and fake image sequences, therefore hindering their generalization capabilities to unseen generation methods. Moreover, with the constant progress in generative Artificial Intelligence (AI), deepfake artifacts are becoming imperceptible at both the spatial and the temporal levels, making them extremely difficult to capture. To address these issues, we propose a fine-grained deepfake video detection approach called "},"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":"2501.01184","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T10:21:34Z","cross_cats_sorted":[],"title_canon_sha256":"5ff47b75fc4a7c3e42d5dc06e56eab966b427f6131b5e090abc87ee54a707ec7","abstract_canon_sha256":"b60267adf4a511dd7e2a09942c92ae60c8d164a3554f93d197653f6b652e6c8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:46.802894Z","signature_b64":"+Y1Ma0T9Y6uX80Eqx642etfTeQjCFlbi4sFIg0SosbR6X+FR3tQFehwtekJ1yB59JQRYcxxwjYq4+LJbH5UaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1869dc84e4997cf5c4de61d16e21b92aaa0518818566652b54dcc63da75654e1","last_reissued_at":"2026-07-05T11:39:46.802394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:46.802394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vulnerability-Aware Spatio-Temporal Learning for Generalizable Deepfake Video Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anis Kacem, Dat Nguyen, Djamila Aouada, Enjie Ghorbel, Marcella Astrid","submitted_at":"2025-01-02T10:21:34Z","abstract_excerpt":"Detecting deepfake videos is highly challenging given the complexity of characterizing spatio-temporal artifacts. Most existing methods rely on binary classifiers trained using real and fake image sequences, therefore hindering their generalization capabilities to unseen generation methods. Moreover, with the constant progress in generative Artificial Intelligence (AI), deepfake artifacts are becoming imperceptible at both the spatial and the temporal levels, making them extremely difficult to capture. To address these issues, we propose a fine-grained deepfake video detection approach called "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01184","kind":"arxiv","version":3},"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/2501.01184/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":"2501.01184","created_at":"2026-07-05T11:39:46.802461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01184v3","created_at":"2026-07-05T11:39:46.802461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01184","created_at":"2026-07-05T11:39:46.802461+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBU5ZBHETF6P","created_at":"2026-07-05T11:39:46.802461+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBU5ZBHETF6PLRG6","created_at":"2026-07-05T11:39:46.802461+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBU5ZBHE","created_at":"2026-07-05T11:39:46.802461+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31192","citing_title":"The Regularizing Power of Language-Training Deepfake Detectors","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17133","citing_title":"CAM-VFD: Cross-Attention Multimodal Video Forgery Detection","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17573","citing_title":"Deepfake Detection in Social Media: A Temporal Artifact Analysis Using 3D Convolutional Neural Networks","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00630","citing_title":"CMTA: Leveraging Cross-Modal Temporal Artifacts for Generalizable AI-Generated Video Detection","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DBU5ZBHETF6PLRG6MHIW4INZFK","json":"https://pith.science/pith/DBU5ZBHETF6PLRG6MHIW4INZFK.json","graph_json":"https://pith.science/api/pith-number/DBU5ZBHETF6PLRG6MHIW4INZFK/graph.json","events_json":"https://pith.science/api/pith-number/DBU5ZBHETF6PLRG6MHIW4INZFK/events.json","paper":"https://pith.science/paper/DBU5ZBHE"},"agent_actions":{"view_html":"https://pith.science/pith/DBU5ZBHETF6PLRG6MHIW4INZFK","download_json":"https://pith.science/pith/DBU5ZBHETF6PLRG6MHIW4INZFK.json","view_paper":"https://pith.science/paper/DBU5ZBHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01184&json=true","fetch_graph":"https://pith.science/api/pith-number/DBU5ZBHETF6PLRG6MHIW4INZFK/graph.json","fetch_events":"https://pith.science/api/pith-number/DBU5ZBHETF6PLRG6MHIW4INZFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBU5ZBHETF6PLRG6MHIW4INZFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBU5ZBHETF6PLRG6MHIW4INZFK/action/storage_attestation","attest_author":"https://pith.science/pith/DBU5ZBHETF6PLRG6MHIW4INZFK/action/author_attestation","sign_citation":"https://pith.science/pith/DBU5ZBHETF6PLRG6MHIW4INZFK/action/citation_signature","submit_replication":"https://pith.science/pith/DBU5ZBHETF6PLRG6MHIW4INZFK/action/replication_record"}},"created_at":"2026-07-05T11:39:46.802461+00:00","updated_at":"2026-07-05T11:39:46.802461+00:00"}