{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SGU6OELIALV3JO5YBC75PMXJUC","short_pith_number":"pith:SGU6OELI","schema_version":"1.0","canonical_sha256":"91a9e7116802ebb4bbb808bfd7b2e9a08c5a64531929b3a240170582880e6935","source":{"kind":"arxiv","id":"2008.03412","version":3},"attestation_state":"computed","paper":{"title":"Two-branch Recurrent Network for Isolating Deepfakes in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aditya Killekar, Iacopo Masi, Royston Marian Mascarenhas, Shenoy Pratik Gurudatt, Wael AbdAlmageed","submitted_at":"2020-08-08T01:38:56Z","abstract_excerpt":"The current spike of hyper-realistic faces artificially generated using deepfakes calls for media forensics solutions that are tailored to video streams and work reliably with a low false alarm rate at the video level. We present a method for deepfake detection based on a two-branch network structure that isolates digitally manipulated faces by learning to amplify artifacts while suppressing the high-level face content. Unlike current methods that extract spatial frequencies as a preprocessing step, we propose a two-branch structure: one branch propagates the original information, while the ot"},"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":"2008.03412","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-08T01:38:56Z","cross_cats_sorted":["cs.CY","cs.LG"],"title_canon_sha256":"dd8d4f44a49a43783bf881fca4c2830d24caa10ad33126d80a81d4faf96a7182","abstract_canon_sha256":"10706f0eae506ec407235cb5f4d40ea0b5fb26e42c28edc400c5a88b10bb991c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:33:00.158139Z","signature_b64":"bvuy9BM3P8w+lyg6OE+jX6l/+L9ttxJQnQ4QcyYRZylK9zxanjTm5HaMnW1tu5RcZWuxxMBysjNEzVSq7R2mDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91a9e7116802ebb4bbb808bfd7b2e9a08c5a64531929b3a240170582880e6935","last_reissued_at":"2026-07-05T01:33:00.157662Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:33:00.157662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Two-branch Recurrent Network for Isolating Deepfakes in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aditya Killekar, Iacopo Masi, Royston Marian Mascarenhas, Shenoy Pratik Gurudatt, Wael AbdAlmageed","submitted_at":"2020-08-08T01:38:56Z","abstract_excerpt":"The current spike of hyper-realistic faces artificially generated using deepfakes calls for media forensics solutions that are tailored to video streams and work reliably with a low false alarm rate at the video level. We present a method for deepfake detection based on a two-branch network structure that isolates digitally manipulated faces by learning to amplify artifacts while suppressing the high-level face content. Unlike current methods that extract spatial frequencies as a preprocessing step, we propose a two-branch structure: one branch propagates the original information, while the ot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03412","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/2008.03412/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":"2008.03412","created_at":"2026-07-05T01:33:00.157722+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.03412v3","created_at":"2026-07-05T01:33:00.157722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03412","created_at":"2026-07-05T01:33:00.157722+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGU6OELIALV3","created_at":"2026-07-05T01:33:00.157722+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGU6OELIALV3JO5Y","created_at":"2026-07-05T01:33:00.157722+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGU6OELI","created_at":"2026-07-05T01:33:00.157722+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31192","citing_title":"The Regularizing Power of Language-Training Deepfake Detectors","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SGU6OELIALV3JO5YBC75PMXJUC","json":"https://pith.science/pith/SGU6OELIALV3JO5YBC75PMXJUC.json","graph_json":"https://pith.science/api/pith-number/SGU6OELIALV3JO5YBC75PMXJUC/graph.json","events_json":"https://pith.science/api/pith-number/SGU6OELIALV3JO5YBC75PMXJUC/events.json","paper":"https://pith.science/paper/SGU6OELI"},"agent_actions":{"view_html":"https://pith.science/pith/SGU6OELIALV3JO5YBC75PMXJUC","download_json":"https://pith.science/pith/SGU6OELIALV3JO5YBC75PMXJUC.json","view_paper":"https://pith.science/paper/SGU6OELI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.03412&json=true","fetch_graph":"https://pith.science/api/pith-number/SGU6OELIALV3JO5YBC75PMXJUC/graph.json","fetch_events":"https://pith.science/api/pith-number/SGU6OELIALV3JO5YBC75PMXJUC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGU6OELIALV3JO5YBC75PMXJUC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGU6OELIALV3JO5YBC75PMXJUC/action/storage_attestation","attest_author":"https://pith.science/pith/SGU6OELIALV3JO5YBC75PMXJUC/action/author_attestation","sign_citation":"https://pith.science/pith/SGU6OELIALV3JO5YBC75PMXJUC/action/citation_signature","submit_replication":"https://pith.science/pith/SGU6OELIALV3JO5YBC75PMXJUC/action/replication_record"}},"created_at":"2026-07-05T01:33:00.157722+00:00","updated_at":"2026-07-05T01:33:00.157722+00:00"}