{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3B2RBCWMLPEVUSX2DQJH64FURW","short_pith_number":"pith:3B2RBCWM","schema_version":"1.0","canonical_sha256":"d875108acc5bc95a4afa1c127f70b48d8947d085aa04d619cf6983be631a359e","source":{"kind":"arxiv","id":"2504.04470","version":1},"attestation_state":"computed","paper":{"title":"Domain Generalization for Face Anti-spoofing via Content-aware Composite Prompt Engineering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajian Liu, Bo Zhao, Hui Ma, Jiabao Guo, Jin Zhang, Meng Wang, Richang Hong, Yunfeng Diao","submitted_at":"2025-04-06T13:00:41Z","abstract_excerpt":"The challenge of Domain Generalization (DG) in Face Anti-Spoofing (FAS) is the significant interference of domain-specific signals on subtle spoofing clues. Recently, some CLIP-based algorithms have been developed to alleviate this interference by adjusting the weights of visual classifiers. However, our analysis of this class-wise prompt engineering suffers from two shortcomings for DG FAS: (1) The categories of facial categories, such as real or spoof, have no semantics for the CLIP model, making it difficult to learn accurate category descriptions. (2) A single form of prompt cannot portray"},"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":"2504.04470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-06T13:00:41Z","cross_cats_sorted":[],"title_canon_sha256":"69ba30b545fd364af1d243ce16ba748e08f37bb1bbc7402a39cb192fd01b5c72","abstract_canon_sha256":"371379585c6f6c8fd9f47b074ade2ae1c7987d2d5900fc3983cdb4c6bad39b34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:24.476612Z","signature_b64":"h4JZ1QdUOb/KhzA1+V9oDvXjATnpk+j+YkpcGKiK07tXCzQwc12eA7Y531HQX1HoxTTvcwdfnqhfei4c3w+JBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d875108acc5bc95a4afa1c127f70b48d8947d085aa04d619cf6983be631a359e","last_reissued_at":"2026-07-05T10:45:24.476150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:24.476150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Generalization for Face Anti-spoofing via Content-aware Composite Prompt Engineering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajian Liu, Bo Zhao, Hui Ma, Jiabao Guo, Jin Zhang, Meng Wang, Richang Hong, Yunfeng Diao","submitted_at":"2025-04-06T13:00:41Z","abstract_excerpt":"The challenge of Domain Generalization (DG) in Face Anti-Spoofing (FAS) is the significant interference of domain-specific signals on subtle spoofing clues. Recently, some CLIP-based algorithms have been developed to alleviate this interference by adjusting the weights of visual classifiers. However, our analysis of this class-wise prompt engineering suffers from two shortcomings for DG FAS: (1) The categories of facial categories, such as real or spoof, have no semantics for the CLIP model, making it difficult to learn accurate category descriptions. (2) A single form of prompt cannot portray"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04470","kind":"arxiv","version":1},"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/2504.04470/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":"2504.04470","created_at":"2026-07-05T10:45:24.476206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04470v1","created_at":"2026-07-05T10:45:24.476206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04470","created_at":"2026-07-05T10:45:24.476206+00:00"},{"alias_kind":"pith_short_12","alias_value":"3B2RBCWMLPEV","created_at":"2026-07-05T10:45:24.476206+00:00"},{"alias_kind":"pith_short_16","alias_value":"3B2RBCWMLPEVUSX2","created_at":"2026-07-05T10:45:24.476206+00:00"},{"alias_kind":"pith_short_8","alias_value":"3B2RBCWM","created_at":"2026-07-05T10:45:24.476206+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21895","citing_title":"Exploring Task-Solving Paradigm for Generalized Cross-Domain Face Anti-Spoofing via Reinforcement Fine-Tuning","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3B2RBCWMLPEVUSX2DQJH64FURW","json":"https://pith.science/pith/3B2RBCWMLPEVUSX2DQJH64FURW.json","graph_json":"https://pith.science/api/pith-number/3B2RBCWMLPEVUSX2DQJH64FURW/graph.json","events_json":"https://pith.science/api/pith-number/3B2RBCWMLPEVUSX2DQJH64FURW/events.json","paper":"https://pith.science/paper/3B2RBCWM"},"agent_actions":{"view_html":"https://pith.science/pith/3B2RBCWMLPEVUSX2DQJH64FURW","download_json":"https://pith.science/pith/3B2RBCWMLPEVUSX2DQJH64FURW.json","view_paper":"https://pith.science/paper/3B2RBCWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04470&json=true","fetch_graph":"https://pith.science/api/pith-number/3B2RBCWMLPEVUSX2DQJH64FURW/graph.json","fetch_events":"https://pith.science/api/pith-number/3B2RBCWMLPEVUSX2DQJH64FURW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3B2RBCWMLPEVUSX2DQJH64FURW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3B2RBCWMLPEVUSX2DQJH64FURW/action/storage_attestation","attest_author":"https://pith.science/pith/3B2RBCWMLPEVUSX2DQJH64FURW/action/author_attestation","sign_citation":"https://pith.science/pith/3B2RBCWMLPEVUSX2DQJH64FURW/action/citation_signature","submit_replication":"https://pith.science/pith/3B2RBCWMLPEVUSX2DQJH64FURW/action/replication_record"}},"created_at":"2026-07-05T10:45:24.476206+00:00","updated_at":"2026-07-05T10:45:24.476206+00:00"}