{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NQA34KMBUWY4YS6R2LDHRJ6AZP","short_pith_number":"pith:NQA34KMB","schema_version":"1.0","canonical_sha256":"6c01be2981a5b1cc4bd1d2c678a7c0cbf21dead6ad2e0228ef9cec5e93b994d7","source":{"kind":"arxiv","id":"2501.00700","version":2},"attestation_state":"computed","paper":{"title":"Knowledge-Guided Prompt Learning for Deepfake Facial Image Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Deng, Hao Wang, Zhidong Zhao","submitted_at":"2025-01-01T02:18:18Z","abstract_excerpt":"Recent generative models demonstrate impressive performance on synthesizing photographic images, which makes humans hardly to distinguish them from pristine ones, especially on realistic-looking synthetic facial images. Previous works mostly focus on mining discriminative artifacts from vast amount of visual data. However, they usually lack the exploration of prior knowledge and rarely pay attention to the domain shift between training categories (e.g., natural and indoor objects) and testing ones (e.g., fine-grained human facial images), resulting in unsatisfactory detection performance. To a"},"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":"2501.00700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-01T02:18:18Z","cross_cats_sorted":[],"title_canon_sha256":"3905f9db0a4daccd0af0262257c1bf37228d6cfd7a92fa0de4c81d81514fe524","abstract_canon_sha256":"648c1b7e4cf43a6205cebb39b3e30b545372222ad8671eed2a452c9514988c05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:45.534891Z","signature_b64":"cyLCIZxKQclET56er3n9C2e95WfiFgI1zORfFxxGozHSZFncUEH8rgGteQmUHCVyyHI+gsmhxleNVpSIcPVMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c01be2981a5b1cc4bd1d2c678a7c0cbf21dead6ad2e0228ef9cec5e93b994d7","last_reissued_at":"2026-07-05T10:00:45.534351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:45.534351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge-Guided Prompt Learning for Deepfake Facial Image Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Deng, Hao Wang, Zhidong Zhao","submitted_at":"2025-01-01T02:18:18Z","abstract_excerpt":"Recent generative models demonstrate impressive performance on synthesizing photographic images, which makes humans hardly to distinguish them from pristine ones, especially on realistic-looking synthetic facial images. Previous works mostly focus on mining discriminative artifacts from vast amount of visual data. However, they usually lack the exploration of prior knowledge and rarely pay attention to the domain shift between training categories (e.g., natural and indoor objects) and testing ones (e.g., fine-grained human facial images), resulting in unsatisfactory detection performance. To a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00700","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/2501.00700/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":"2501.00700","created_at":"2026-07-05T10:00:45.534415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00700v2","created_at":"2026-07-05T10:00:45.534415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00700","created_at":"2026-07-05T10:00:45.534415+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQA34KMBUWY4","created_at":"2026-07-05T10:00:45.534415+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQA34KMBUWY4YS6R","created_at":"2026-07-05T10:00:45.534415+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQA34KMB","created_at":"2026-07-05T10:00:45.534415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08709","citing_title":"UniShield: Unified Face Attack Detection via KG-Informed Multimodal Reasoning","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NQA34KMBUWY4YS6R2LDHRJ6AZP","json":"https://pith.science/pith/NQA34KMBUWY4YS6R2LDHRJ6AZP.json","graph_json":"https://pith.science/api/pith-number/NQA34KMBUWY4YS6R2LDHRJ6AZP/graph.json","events_json":"https://pith.science/api/pith-number/NQA34KMBUWY4YS6R2LDHRJ6AZP/events.json","paper":"https://pith.science/paper/NQA34KMB"},"agent_actions":{"view_html":"https://pith.science/pith/NQA34KMBUWY4YS6R2LDHRJ6AZP","download_json":"https://pith.science/pith/NQA34KMBUWY4YS6R2LDHRJ6AZP.json","view_paper":"https://pith.science/paper/NQA34KMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00700&json=true","fetch_graph":"https://pith.science/api/pith-number/NQA34KMBUWY4YS6R2LDHRJ6AZP/graph.json","fetch_events":"https://pith.science/api/pith-number/NQA34KMBUWY4YS6R2LDHRJ6AZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQA34KMBUWY4YS6R2LDHRJ6AZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQA34KMBUWY4YS6R2LDHRJ6AZP/action/storage_attestation","attest_author":"https://pith.science/pith/NQA34KMBUWY4YS6R2LDHRJ6AZP/action/author_attestation","sign_citation":"https://pith.science/pith/NQA34KMBUWY4YS6R2LDHRJ6AZP/action/citation_signature","submit_replication":"https://pith.science/pith/NQA34KMBUWY4YS6R2LDHRJ6AZP/action/replication_record"}},"created_at":"2026-07-05T10:00:45.534415+00:00","updated_at":"2026-07-05T10:00:45.534415+00:00"}