{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MG5TKPLJ2L32RBY2GIXHGR5D4Z","short_pith_number":"pith:MG5TKPLJ","schema_version":"1.0","canonical_sha256":"61bb353d69d2f7a8871a322e7347a3e6648dd4c32b511bb9b274051dba634913","source":{"kind":"arxiv","id":"2411.11016","version":2},"attestation_state":"computed","paper":{"title":"Time Step Generating: A Universal Synthesized Deepfake Image Detector","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dingjie Peng, Haoyuan Liu, Hiroshi Watanabe, Luoxu Jing, Ziyue Zeng","submitted_at":"2024-11-17T09:39:50Z","abstract_excerpt":"Currently, high-fidelity text-to-image models are developed in an accelerating pace. Among them, Diffusion Models have led to a remarkable improvement in the quality of image generation, making it vary challenging to distinguish between real and synthesized images. It simultaneously raises serious concerns regarding privacy and security. Some methods are proposed to distinguish the diffusion model generated images through reconstructing. However, the inversion and denoising processes are time-consuming and heavily reliant on the pre-trained generative model. Consequently, if the pre-trained ge"},"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":"2411.11016","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-17T09:39:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c3cad9b124dc94a205ad81fbdf8c76f4a8cc9e34dc8728a4307e1f8431fcdf7a","abstract_canon_sha256":"2a99f2c7e59aa30642676c2c50cd4fefa9d62ebc7db33a024f6f144ed61ca832"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:58.635308Z","signature_b64":"qMJdTIzyfwrdiRCvgwKeBZIQrSVf86VcZg85Esbr6gWI+ev/JPpLg6A1nUrpI7f04VyJUS5r+dsOMh5KuUWfAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61bb353d69d2f7a8871a322e7347a3e6648dd4c32b511bb9b274051dba634913","last_reissued_at":"2026-07-05T09:37:58.634759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:58.634759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time Step Generating: A Universal Synthesized Deepfake Image Detector","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dingjie Peng, Haoyuan Liu, Hiroshi Watanabe, Luoxu Jing, Ziyue Zeng","submitted_at":"2024-11-17T09:39:50Z","abstract_excerpt":"Currently, high-fidelity text-to-image models are developed in an accelerating pace. Among them, Diffusion Models have led to a remarkable improvement in the quality of image generation, making it vary challenging to distinguish between real and synthesized images. It simultaneously raises serious concerns regarding privacy and security. Some methods are proposed to distinguish the diffusion model generated images through reconstructing. However, the inversion and denoising processes are time-consuming and heavily reliant on the pre-trained generative model. Consequently, if the pre-trained ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11016","kind":"arxiv","version":2},"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/2411.11016/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":"2411.11016","created_at":"2026-07-05T09:37:58.634813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11016v2","created_at":"2026-07-05T09:37:58.634813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11016","created_at":"2026-07-05T09:37:58.634813+00:00"},{"alias_kind":"pith_short_12","alias_value":"MG5TKPLJ2L32","created_at":"2026-07-05T09:37:58.634813+00:00"},{"alias_kind":"pith_short_16","alias_value":"MG5TKPLJ2L32RBY2","created_at":"2026-07-05T09:37:58.634813+00:00"},{"alias_kind":"pith_short_8","alias_value":"MG5TKPLJ","created_at":"2026-07-05T09:37:58.634813+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05466","citing_title":"Towards Reliable Identification of Diffusion-based Image Manipulations","ref_index":90,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MG5TKPLJ2L32RBY2GIXHGR5D4Z","json":"https://pith.science/pith/MG5TKPLJ2L32RBY2GIXHGR5D4Z.json","graph_json":"https://pith.science/api/pith-number/MG5TKPLJ2L32RBY2GIXHGR5D4Z/graph.json","events_json":"https://pith.science/api/pith-number/MG5TKPLJ2L32RBY2GIXHGR5D4Z/events.json","paper":"https://pith.science/paper/MG5TKPLJ"},"agent_actions":{"view_html":"https://pith.science/pith/MG5TKPLJ2L32RBY2GIXHGR5D4Z","download_json":"https://pith.science/pith/MG5TKPLJ2L32RBY2GIXHGR5D4Z.json","view_paper":"https://pith.science/paper/MG5TKPLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11016&json=true","fetch_graph":"https://pith.science/api/pith-number/MG5TKPLJ2L32RBY2GIXHGR5D4Z/graph.json","fetch_events":"https://pith.science/api/pith-number/MG5TKPLJ2L32RBY2GIXHGR5D4Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MG5TKPLJ2L32RBY2GIXHGR5D4Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MG5TKPLJ2L32RBY2GIXHGR5D4Z/action/storage_attestation","attest_author":"https://pith.science/pith/MG5TKPLJ2L32RBY2GIXHGR5D4Z/action/author_attestation","sign_citation":"https://pith.science/pith/MG5TKPLJ2L32RBY2GIXHGR5D4Z/action/citation_signature","submit_replication":"https://pith.science/pith/MG5TKPLJ2L32RBY2GIXHGR5D4Z/action/replication_record"}},"created_at":"2026-07-05T09:37:58.634813+00:00","updated_at":"2026-07-05T09:37:58.634813+00:00"}