{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OGNF6TKRRKNGC7WX4QYV3ML7J3","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":"0ae56760dc2183a30744bd42a83f9cbcd028119b5cf19fe794e13301219800db","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-11T17:02:34Z","title_canon_sha256":"8a6fd035f9684a801ca98f26da17b62c0be46a96d202ed678a0ad616c7072b4b"},"schema_version":"1.0","source":{"id":"2302.05744","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.05744","created_at":"2026-07-05T05:40:57Z"},{"alias_kind":"arxiv_version","alias_value":"2302.05744v1","created_at":"2026-07-05T05:40:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05744","created_at":"2026-07-05T05:40:57Z"},{"alias_kind":"pith_short_12","alias_value":"OGNF6TKRRKNG","created_at":"2026-07-05T05:40:57Z"},{"alias_kind":"pith_short_16","alias_value":"OGNF6TKRRKNGC7WX","created_at":"2026-07-05T05:40:57Z"},{"alias_kind":"pith_short_8","alias_value":"OGNF6TKR","created_at":"2026-07-05T05:40:57Z"}],"graph_snapshots":[{"event_id":"sha256:ab5c3d2d8b061b58b96989872927a80a0b720b5a59d5d8d3285748342de6ca8c","target":"graph","created_at":"2026-07-05T05:40:57Z","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/2302.05744/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, vision transformer (ViT) based multimodal learning methods have been proposed to improve the robustness of face anti-spoofing (FAS) systems. However, there are still no works to explore the fundamental natures (\\textit{e.g.}, modality-aware inputs, suitable multimodal pre-training, and efficient finetuning) in vanilla ViT for multimodal FAS. In this paper, we investigate three key factors (i.e., inputs, pre-training, and finetuning) in ViT for multimodal FAS with RGB, Infrared (IR), and Depth. First, in terms of the ViT inputs, we find that leveraging local feature descriptors benefi","authors_text":"Alex Kot, Rizhao Cai, Xin Liu, Yawen Cui, Yongjian Hu, Zitong Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-11T17:02:34Z","title":"Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05744","kind":"arxiv","version":1},"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":"sha256:4f0b21e6274685eede25b82093a811ceffdf50cf62f13a1b03c9630c9ab1732c","target":"record","created_at":"2026-07-05T05:40:57Z","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":"0ae56760dc2183a30744bd42a83f9cbcd028119b5cf19fe794e13301219800db","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-11T17:02:34Z","title_canon_sha256":"8a6fd035f9684a801ca98f26da17b62c0be46a96d202ed678a0ad616c7072b4b"},"schema_version":"1.0","source":{"id":"2302.05744","kind":"arxiv","version":1}},"canonical_sha256":"719a5f4d518a9a617ed7e4315db17f4eca67d5773771bca674963c103fe0444b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"719a5f4d518a9a617ed7e4315db17f4eca67d5773771bca674963c103fe0444b","first_computed_at":"2026-07-05T05:40:57.808172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:40:57.808172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OvCY4GKF119bLXwysHTLCuTTZOu4PEz71wQPlOI9mhC4RrST6ec7f9cKzvYcJnicer1RM1EFkd/5ZwhfvIuoCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:40:57.808614Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.05744","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f0b21e6274685eede25b82093a811ceffdf50cf62f13a1b03c9630c9ab1732c","sha256:ab5c3d2d8b061b58b96989872927a80a0b720b5a59d5d8d3285748342de6ca8c"],"state_sha256":"17ce183ace97c648f7003ac9edaf9c92b868459b61faf5eb5bd17cd8942c5eed"}