{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RZASFO7QDTVWLC6O5UYZU3GTOI","short_pith_number":"pith:RZASFO7Q","schema_version":"1.0","canonical_sha256":"8e4122bbf01ceb658bceed319a6cd37208833650c9e318dbe5f1a8b41d3a1122","source":{"kind":"arxiv","id":"2607.04314","version":1},"attestation_state":"computed","paper":{"title":"MOSAIC: Interpretable Multi-Token Cross-Attention of Biophonetic and Self-Supervised Representations for Unified Voice Anti-Spoofing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Yugwon Won","submitted_at":"2026-07-05T14:02:09Z","abstract_excerpt":"The dominant trend in voice anti-spoofing fuses self-supervised (SSL) backbones (e.g., WavLM) with handcrafted features, yet such fusion typically lacks transparency in cue-to-layer interactions, and simple concatenation limits cross-modal learning. We propose MOSAIC (Multi-token Oriented Speech Anti-spoofing via Integrated Cross-attention), an interpretable multi-token cross-attention framework that splits a 152-dimensional biophonetic feature vector into six semantic-group query tokens (Praat, phase, LFCC mean/std, sub-band mean/std) and attends them over thirteen mean-std pooled WavLM-Large"},"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":"2607.04314","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-05T14:02:09Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"dbb65e3919d68975314358fc976ee1fa3a46e7a5937f64fc14fb5aff69c7f737","abstract_canon_sha256":"96c7a83032ba83f3c69e4988503afdd10059691946f7b229a689898ac4ef2775"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:08.391173Z","signature_b64":"Q/7b+T36bXUMq+sqrWr0n5J3K6uWFR2L7WI2WlDVOAJwnLtAG3w2UlmEDsh1kXXO0otz8BPbDQ85SQvybiHWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e4122bbf01ceb658bceed319a6cd37208833650c9e318dbe5f1a8b41d3a1122","last_reissued_at":"2026-07-07T02:19:08.390539Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:08.390539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MOSAIC: Interpretable Multi-Token Cross-Attention of Biophonetic and Self-Supervised Representations for Unified Voice Anti-Spoofing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Yugwon Won","submitted_at":"2026-07-05T14:02:09Z","abstract_excerpt":"The dominant trend in voice anti-spoofing fuses self-supervised (SSL) backbones (e.g., WavLM) with handcrafted features, yet such fusion typically lacks transparency in cue-to-layer interactions, and simple concatenation limits cross-modal learning. We propose MOSAIC (Multi-token Oriented Speech Anti-spoofing via Integrated Cross-attention), an interpretable multi-token cross-attention framework that splits a 152-dimensional biophonetic feature vector into six semantic-group query tokens (Praat, phase, LFCC mean/std, sub-band mean/std) and attends them over thirteen mean-std pooled WavLM-Large"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04314","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/2607.04314/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":"2607.04314","created_at":"2026-07-07T02:19:08.390637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04314v1","created_at":"2026-07-07T02:19:08.390637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04314","created_at":"2026-07-07T02:19:08.390637+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZASFO7QDTVW","created_at":"2026-07-07T02:19:08.390637+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZASFO7QDTVWLC6O","created_at":"2026-07-07T02:19:08.390637+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZASFO7Q","created_at":"2026-07-07T02:19:08.390637+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/RZASFO7QDTVWLC6O5UYZU3GTOI","json":"https://pith.science/pith/RZASFO7QDTVWLC6O5UYZU3GTOI.json","graph_json":"https://pith.science/api/pith-number/RZASFO7QDTVWLC6O5UYZU3GTOI/graph.json","events_json":"https://pith.science/api/pith-number/RZASFO7QDTVWLC6O5UYZU3GTOI/events.json","paper":"https://pith.science/paper/RZASFO7Q"},"agent_actions":{"view_html":"https://pith.science/pith/RZASFO7QDTVWLC6O5UYZU3GTOI","download_json":"https://pith.science/pith/RZASFO7QDTVWLC6O5UYZU3GTOI.json","view_paper":"https://pith.science/paper/RZASFO7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04314&json=true","fetch_graph":"https://pith.science/api/pith-number/RZASFO7QDTVWLC6O5UYZU3GTOI/graph.json","fetch_events":"https://pith.science/api/pith-number/RZASFO7QDTVWLC6O5UYZU3GTOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZASFO7QDTVWLC6O5UYZU3GTOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZASFO7QDTVWLC6O5UYZU3GTOI/action/storage_attestation","attest_author":"https://pith.science/pith/RZASFO7QDTVWLC6O5UYZU3GTOI/action/author_attestation","sign_citation":"https://pith.science/pith/RZASFO7QDTVWLC6O5UYZU3GTOI/action/citation_signature","submit_replication":"https://pith.science/pith/RZASFO7QDTVWLC6O5UYZU3GTOI/action/replication_record"}},"created_at":"2026-07-07T02:19:08.390637+00:00","updated_at":"2026-07-07T02:19:08.390637+00:00"}