{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:B2J4BTMGWFNBRA4R3HLVC7677Y","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"79306f3923c1d8734621c745640aa98f47c7ff11aa4af5ea05ada8a3719157e9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-20T05:43:44Z","title_canon_sha256":"a831cff6f4e0c9f892d252c0a78269a87e4bdf283b6b1ec0a87c9117c6b79e61"},"schema_version":"1.0","source":{"id":"2104.09770","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.09770","created_at":"2026-07-05T04:15:27Z"},{"alias_kind":"arxiv_version","alias_value":"2104.09770v3","created_at":"2026-07-05T04:15:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09770","created_at":"2026-07-05T04:15:27Z"},{"alias_kind":"pith_short_12","alias_value":"B2J4BTMGWFNB","created_at":"2026-07-05T04:15:27Z"},{"alias_kind":"pith_short_16","alias_value":"B2J4BTMGWFNBRA4R","created_at":"2026-07-05T04:15:27Z"},{"alias_kind":"pith_short_8","alias_value":"B2J4BTMG","created_at":"2026-07-05T04:15:27Z"}],"graph_snapshots":[{"event_id":"sha256:be657a690d8d65d0fc810d6b3b5ea8ef14824ff47aff00c2aa651e9508498bb6","target":"graph","created_at":"2026-07-05T04:15:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2104.09770/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The widespread dissemination of Deepfakes demands effective approaches that can detect perceptually convincing forged images. In this paper, we aim to capture the subtle manipulation artifacts at different scales using transformer models. In particular, we introduce a Multi-modal Multi-scale TRansformer (M2TR), which operates on patches of different sizes to detect local inconsistencies in images at different spatial levels. M2TR further learns to detect forgery artifacts in the frequency domain to complement RGB information through a carefully designed cross modality fusion block. In addition","authors_text":"Jingjing Chen, Junke Wang, Ser-Nam Lim, Wenhao Ouyang, Xintong Han, Yu-Gang Jiang, Zuxuan Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-20T05:43:44Z","title":"M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09770","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a345052e649fe2177e86490030b65a03c0935048312a5c8647ba030998852149","target":"record","created_at":"2026-07-05T04:15:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"79306f3923c1d8734621c745640aa98f47c7ff11aa4af5ea05ada8a3719157e9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-20T05:43:44Z","title_canon_sha256":"a831cff6f4e0c9f892d252c0a78269a87e4bdf283b6b1ec0a87c9117c6b79e61"},"schema_version":"1.0","source":{"id":"2104.09770","kind":"arxiv","version":3}},"canonical_sha256":"0e93c0cd86b15a188391d9d7517fdffe2d2176c44731283d60790e4724998a9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e93c0cd86b15a188391d9d7517fdffe2d2176c44731283d60790e4724998a9e","first_computed_at":"2026-07-05T04:15:27.328905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:15:27.328905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IdN/8RZzG4/APv/SwZ2Jef0cb3eGuLgqL6IqsHZ/FIDsKUzIglQT0wFB3NJAXUAfdvwj8cqvTIxTtSUWNNlxDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:15:27.329453Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.09770","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a345052e649fe2177e86490030b65a03c0935048312a5c8647ba030998852149","sha256:be657a690d8d65d0fc810d6b3b5ea8ef14824ff47aff00c2aa651e9508498bb6"],"state_sha256":"9f42819f25008e8f2e51c9657d7d0fefd636cf8c280f64ab6bffe36ac42b586e"}