{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KUVCJXCCVH5RPY2FKJSTGAE4FK","short_pith_number":"pith:KUVCJXCC","schema_version":"1.0","canonical_sha256":"552a24dc42a9fb17e345526533009c2aaf5720bdeb346c372cc39884e5bbaf49","source":{"kind":"arxiv","id":"2407.03514","version":1},"attestation_state":"computed","paper":{"title":"Towards Attention-based Contrastive Learning for Audio Spoof Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ali Shahriyari, Ben Colman, Chirag Goel, Gaurav Bharaj, Surya Koppisetti","submitted_at":"2024-07-03T21:25:12Z","abstract_excerpt":"Vision transformers (ViT) have made substantial progress for classification tasks in computer vision. Recently, Gong et. al. '21, introduced attention-based modeling for several audio tasks. However, relatively unexplored is the use of a ViT for audio spoof detection task. We bridge this gap and introduce ViTs for this task. A vanilla baseline built on fine-tuning the SSAST (Gong et. al. '22) audio ViT model achieves sub-optimal equal error rates (EERs). To improve performance, we propose a novel attention-based contrastive learning framework (SSAST-CL) that uses cross-attention to aid the rep"},"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":"2407.03514","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-03T21:25:12Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"c795147175142387e75cd3531e4db9fa5ea790a67ed5e9b8faeecb014ab64261","abstract_canon_sha256":"10f007f3b6da584571412f93cc1f3d1144c35285f4f18d11004815a94b89bb47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:56.235690Z","signature_b64":"cvdwv1nl6Iu2pYT/6Iw7yrswujxNbOX4xzGo8UkHsxkQZsJteTRqtZPe6uvIjqO7K/9jCcjluGqnLxNNq80mBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"552a24dc42a9fb17e345526533009c2aaf5720bdeb346c372cc39884e5bbaf49","last_reissued_at":"2026-07-05T08:39:56.235251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:56.235251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Attention-based Contrastive Learning for Audio Spoof Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ali Shahriyari, Ben Colman, Chirag Goel, Gaurav Bharaj, Surya Koppisetti","submitted_at":"2024-07-03T21:25:12Z","abstract_excerpt":"Vision transformers (ViT) have made substantial progress for classification tasks in computer vision. Recently, Gong et. al. '21, introduced attention-based modeling for several audio tasks. However, relatively unexplored is the use of a ViT for audio spoof detection task. We bridge this gap and introduce ViTs for this task. A vanilla baseline built on fine-tuning the SSAST (Gong et. al. '22) audio ViT model achieves sub-optimal equal error rates (EERs). To improve performance, we propose a novel attention-based contrastive learning framework (SSAST-CL) that uses cross-attention to aid the rep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03514","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/2407.03514/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":"2407.03514","created_at":"2026-07-05T08:39:56.235308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03514v1","created_at":"2026-07-05T08:39:56.235308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03514","created_at":"2026-07-05T08:39:56.235308+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUVCJXCCVH5R","created_at":"2026-07-05T08:39:56.235308+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUVCJXCCVH5RPY2F","created_at":"2026-07-05T08:39:56.235308+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUVCJXCC","created_at":"2026-07-05T08:39:56.235308+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.07323","citing_title":"When Fine-Tuning is Not Enough: Lessons from HSAD on Hybrid and Adversarial Audio Spoof Detection","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KUVCJXCCVH5RPY2FKJSTGAE4FK","json":"https://pith.science/pith/KUVCJXCCVH5RPY2FKJSTGAE4FK.json","graph_json":"https://pith.science/api/pith-number/KUVCJXCCVH5RPY2FKJSTGAE4FK/graph.json","events_json":"https://pith.science/api/pith-number/KUVCJXCCVH5RPY2FKJSTGAE4FK/events.json","paper":"https://pith.science/paper/KUVCJXCC"},"agent_actions":{"view_html":"https://pith.science/pith/KUVCJXCCVH5RPY2FKJSTGAE4FK","download_json":"https://pith.science/pith/KUVCJXCCVH5RPY2FKJSTGAE4FK.json","view_paper":"https://pith.science/paper/KUVCJXCC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03514&json=true","fetch_graph":"https://pith.science/api/pith-number/KUVCJXCCVH5RPY2FKJSTGAE4FK/graph.json","fetch_events":"https://pith.science/api/pith-number/KUVCJXCCVH5RPY2FKJSTGAE4FK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUVCJXCCVH5RPY2FKJSTGAE4FK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUVCJXCCVH5RPY2FKJSTGAE4FK/action/storage_attestation","attest_author":"https://pith.science/pith/KUVCJXCCVH5RPY2FKJSTGAE4FK/action/author_attestation","sign_citation":"https://pith.science/pith/KUVCJXCCVH5RPY2FKJSTGAE4FK/action/citation_signature","submit_replication":"https://pith.science/pith/KUVCJXCCVH5RPY2FKJSTGAE4FK/action/replication_record"}},"created_at":"2026-07-05T08:39:56.235308+00:00","updated_at":"2026-07-05T08:39:56.235308+00:00"}