{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NUWTWJOWTDCN4CYBR5TFFOUDOF","short_pith_number":"pith:NUWTWJOW","schema_version":"1.0","canonical_sha256":"6d2d3b25d698c4de0b018f6652ba83716decdc2777c9a0a17cea6c551b218824","source":{"kind":"arxiv","id":"2509.10781","version":1},"attestation_state":"computed","paper":{"title":"Emoanti: audio anti-deepfake with refined emotion-guided representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Dinghao Zou, Sunbowen Lee, Xiaokang Li, Xin Cao, Yicheng Gong","submitted_at":"2025-09-13T01:58:34Z","abstract_excerpt":"Audio deepfake is so sophisticated that the lack of effective detection methods is fatal. While most detection systems primarily rely on low-level acoustic features or pretrained speech representations, they frequently neglect high-level emotional cues, which can offer complementary and potentially anti-deepfake information to enhance generalization. In this work, we propose a novel audio anti-deepfake system that utilizes emotional features (EmoAnti) by exploiting a pretrained Wav2Vec2 (W2V2) model fine-tuned on emotion recognition tasks, which derives emotion-guided representations, then des"},"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":"2509.10781","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-13T01:58:34Z","cross_cats_sorted":[],"title_canon_sha256":"13b7cb41f9d193a73b3475dfac59d1730c27c568afe160d9dfa3118af9dd7626","abstract_canon_sha256":"311cbeca4480b72e96f088a2a62de5938b65c63e05be1f22af7205998ada6aac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:27.939658Z","signature_b64":"291a8cvgTU3NEeXaHD0Ukl23GU/oPhwQQ6d0Gt5yl/B4lR/yGia24YMkZVz/+sKhWX87HGTU3H0jd/oxYaoECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d2d3b25d698c4de0b018f6652ba83716decdc2777c9a0a17cea6c551b218824","last_reissued_at":"2026-07-05T12:11:27.939101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:27.939101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emoanti: audio anti-deepfake with refined emotion-guided representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Dinghao Zou, Sunbowen Lee, Xiaokang Li, Xin Cao, Yicheng Gong","submitted_at":"2025-09-13T01:58:34Z","abstract_excerpt":"Audio deepfake is so sophisticated that the lack of effective detection methods is fatal. While most detection systems primarily rely on low-level acoustic features or pretrained speech representations, they frequently neglect high-level emotional cues, which can offer complementary and potentially anti-deepfake information to enhance generalization. In this work, we propose a novel audio anti-deepfake system that utilizes emotional features (EmoAnti) by exploiting a pretrained Wav2Vec2 (W2V2) model fine-tuned on emotion recognition tasks, which derives emotion-guided representations, then des"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10781","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/2509.10781/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":"2509.10781","created_at":"2026-07-05T12:11:27.939170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.10781v1","created_at":"2026-07-05T12:11:27.939170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10781","created_at":"2026-07-05T12:11:27.939170+00:00"},{"alias_kind":"pith_short_12","alias_value":"NUWTWJOWTDCN","created_at":"2026-07-05T12:11:27.939170+00:00"},{"alias_kind":"pith_short_16","alias_value":"NUWTWJOWTDCN4CYB","created_at":"2026-07-05T12:11:27.939170+00:00"},{"alias_kind":"pith_short_8","alias_value":"NUWTWJOW","created_at":"2026-07-05T12:11:27.939170+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13229","citing_title":"ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NUWTWJOWTDCN4CYBR5TFFOUDOF","json":"https://pith.science/pith/NUWTWJOWTDCN4CYBR5TFFOUDOF.json","graph_json":"https://pith.science/api/pith-number/NUWTWJOWTDCN4CYBR5TFFOUDOF/graph.json","events_json":"https://pith.science/api/pith-number/NUWTWJOWTDCN4CYBR5TFFOUDOF/events.json","paper":"https://pith.science/paper/NUWTWJOW"},"agent_actions":{"view_html":"https://pith.science/pith/NUWTWJOWTDCN4CYBR5TFFOUDOF","download_json":"https://pith.science/pith/NUWTWJOWTDCN4CYBR5TFFOUDOF.json","view_paper":"https://pith.science/paper/NUWTWJOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.10781&json=true","fetch_graph":"https://pith.science/api/pith-number/NUWTWJOWTDCN4CYBR5TFFOUDOF/graph.json","fetch_events":"https://pith.science/api/pith-number/NUWTWJOWTDCN4CYBR5TFFOUDOF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NUWTWJOWTDCN4CYBR5TFFOUDOF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NUWTWJOWTDCN4CYBR5TFFOUDOF/action/storage_attestation","attest_author":"https://pith.science/pith/NUWTWJOWTDCN4CYBR5TFFOUDOF/action/author_attestation","sign_citation":"https://pith.science/pith/NUWTWJOWTDCN4CYBR5TFFOUDOF/action/citation_signature","submit_replication":"https://pith.science/pith/NUWTWJOWTDCN4CYBR5TFFOUDOF/action/replication_record"}},"created_at":"2026-07-05T12:11:27.939170+00:00","updated_at":"2026-07-05T12:11:27.939170+00:00"}