{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:55LRRMEZQWQUMR52YRYO6VO4BQ","short_pith_number":"pith:55LRRMEZ","schema_version":"1.0","canonical_sha256":"ef5718b09985a14647bac470ef55dc0c3bd2730abbbe771c788e497b5bffa81c","source":{"kind":"arxiv","id":"2607.26432","version":1},"attestation_state":"computed","paper":{"title":"FAS-R1: A Unified Multi-Task MLLM for Reasoning Face Anti-Spoofing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hongrui Li, Hongyang Wang, Jun Feng, Yichen Shi, Yiru Huo, Zitong Yu","submitted_at":"2026-07-29T03:19:12Z","abstract_excerpt":"Face anti-spoofing (FAS) is increasingly expected to provide not only bona fide/spoof decisions, but also attack semantics and image-grounded evidence for human inspection. Existing discriminative FAS models remain largely label-centric, while recent MLLM-based methods offer structured outputs but still rely mainly on supervised fine-tuning, often producing template-like rationales and weak optimization for difficult attacks. We propose FAS-R1, a two-stage reasoning-oriented MLLM framework for unified FAS prediction, covering authenticity classification, attack-type recognition and spoof-regio"},"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":"2607.26432","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T03:19:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"90fd344e9631241519358a462802b0e8ac75a03513466f55087d3033021192c8","abstract_canon_sha256":"7fb2ff6fe42b4040fdd3be3a81e1cbc6389dcf39e854215669fe5d24b6352534"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef5718b09985a14647bac470ef55dc0c3bd2730abbbe771c788e497b5bffa81c","last_reissued_at":"2026-07-30T01:18:24.616977Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:18:24.616977Z"},"graph_snapshot":{"paper":{"title":"FAS-R1: A Unified Multi-Task MLLM for Reasoning Face Anti-Spoofing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hongrui Li, Hongyang Wang, Jun Feng, Yichen Shi, Yiru Huo, Zitong Yu","submitted_at":"2026-07-29T03:19:12Z","abstract_excerpt":"Face anti-spoofing (FAS) is increasingly expected to provide not only bona fide/spoof decisions, but also attack semantics and image-grounded evidence for human inspection. Existing discriminative FAS models remain largely label-centric, while recent MLLM-based methods offer structured outputs but still rely mainly on supervised fine-tuning, often producing template-like rationales and weak optimization for difficult attacks. We propose FAS-R1, a two-stage reasoning-oriented MLLM framework for unified FAS prediction, covering authenticity classification, attack-type recognition and spoof-regio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26432","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/2607.26432/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":"2607.26432","created_at":"2026-07-30T01:18:24.622035+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.26432v1","created_at":"2026-07-30T01:18:24.622035+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26432","created_at":"2026-07-30T01:18:24.622035+00:00"},{"alias_kind":"pith_short_12","alias_value":"55LRRMEZQWQU","created_at":"2026-07-30T01:18:24.622035+00:00"},{"alias_kind":"pith_short_16","alias_value":"55LRRMEZQWQUMR52","created_at":"2026-07-30T01:18:24.622035+00:00"},{"alias_kind":"pith_short_8","alias_value":"55LRRMEZ","created_at":"2026-07-30T01:18:24.622035+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55LRRMEZQWQUMR52YRYO6VO4BQ","json":"https://pith.science/pith/55LRRMEZQWQUMR52YRYO6VO4BQ.json","graph_json":"https://pith.science/api/pith-number/55LRRMEZQWQUMR52YRYO6VO4BQ/graph.json","events_json":"https://pith.science/api/pith-number/55LRRMEZQWQUMR52YRYO6VO4BQ/events.json","paper":"https://pith.science/paper/55LRRMEZ"},"agent_actions":{"view_html":"https://pith.science/pith/55LRRMEZQWQUMR52YRYO6VO4BQ","download_json":"https://pith.science/pith/55LRRMEZQWQUMR52YRYO6VO4BQ.json","view_paper":"https://pith.science/paper/55LRRMEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.26432&json=true","fetch_graph":"https://pith.science/api/pith-number/55LRRMEZQWQUMR52YRYO6VO4BQ/graph.json","fetch_events":"https://pith.science/api/pith-number/55LRRMEZQWQUMR52YRYO6VO4BQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55LRRMEZQWQUMR52YRYO6VO4BQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55LRRMEZQWQUMR52YRYO6VO4BQ/action/storage_attestation","attest_author":"https://pith.science/pith/55LRRMEZQWQUMR52YRYO6VO4BQ/action/author_attestation","sign_citation":"https://pith.science/pith/55LRRMEZQWQUMR52YRYO6VO4BQ/action/citation_signature","submit_replication":"https://pith.science/pith/55LRRMEZQWQUMR52YRYO6VO4BQ/action/replication_record"}},"created_at":"2026-07-30T01:18:24.622035+00:00","updated_at":"2026-07-30T01:18:24.622035+00:00"}