{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2PHR2S5JQPCADHCC2RRKWYIYMA","short_pith_number":"pith:2PHR2S5J","schema_version":"1.0","canonical_sha256":"d3cf1d4ba983c4019c42d462ab611860332175851ef5fc7d822cff5cb7f418e7","source":{"kind":"arxiv","id":"2505.11079","version":2},"attestation_state":"computed","paper":{"title":"ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenglong Wang, Hao Gu, Jiangyan Yi, Jianhua Tao, Jiayi He, Yong Ren, Yujie Chen, Zheng Lian, Zhengqi Wen","submitted_at":"2025-05-16T10:10:03Z","abstract_excerpt":"Audio deepfake detection (ADD) has grown increasingly important due to the rise of high-fidelity audio generative models and their potential for misuse. Given that audio large language models (ALLMs) have made significant progress in various audio processing tasks, a heuristic question arises: \\textit{Can ALLMs be leveraged to solve ADD?}. In this paper, we first conduct a comprehensive zero-shot evaluation of ALLMs on ADD, revealing their ineffectiveness. To this end, we propose ALLM4ADD, an ALLM-driven framework for ADD. Specifically, we reformulate ADD task as an audio question answering pr"},"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":"2505.11079","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-16T10:10:03Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"cb389f0583acff893cce67dd32004a044d77337865c175131a47ae56a93bc2a6","abstract_canon_sha256":"c00442a56f24ed206d40fb6f5275082f23599b0f05177f001dde849b1e80534f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:23.776311Z","signature_b64":"Z/Eq9lhLftRhJ/YX0qiq4LHWO4dvcTqb9dQ3m01eHZTTu3M+u4Og2W7yn16x4pFRi06i+3+IrLOJwm11bkgNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3cf1d4ba983c4019c42d462ab611860332175851ef5fc7d822cff5cb7f418e7","last_reissued_at":"2026-07-05T11:33:23.775908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:23.775908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenglong Wang, Hao Gu, Jiangyan Yi, Jianhua Tao, Jiayi He, Yong Ren, Yujie Chen, Zheng Lian, Zhengqi Wen","submitted_at":"2025-05-16T10:10:03Z","abstract_excerpt":"Audio deepfake detection (ADD) has grown increasingly important due to the rise of high-fidelity audio generative models and their potential for misuse. Given that audio large language models (ALLMs) have made significant progress in various audio processing tasks, a heuristic question arises: \\textit{Can ALLMs be leveraged to solve ADD?}. In this paper, we first conduct a comprehensive zero-shot evaluation of ALLMs on ADD, revealing their ineffectiveness. To this end, we propose ALLM4ADD, an ALLM-driven framework for ADD. Specifically, we reformulate ADD task as an audio question answering pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11079","kind":"arxiv","version":2},"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/2505.11079/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":"2505.11079","created_at":"2026-07-05T11:33:23.775973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11079v2","created_at":"2026-07-05T11:33:23.775973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11079","created_at":"2026-07-05T11:33:23.775973+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PHR2S5JQPCA","created_at":"2026-07-05T11:33:23.775973+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PHR2S5JQPCADHCC","created_at":"2026-07-05T11:33:23.775973+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PHR2S5J","created_at":"2026-07-05T11:33:23.775973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17249","citing_title":"R4ec: A Reasoning, Reflection, and Refinement Framework for Recommendation Systems","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2PHR2S5JQPCADHCC2RRKWYIYMA","json":"https://pith.science/pith/2PHR2S5JQPCADHCC2RRKWYIYMA.json","graph_json":"https://pith.science/api/pith-number/2PHR2S5JQPCADHCC2RRKWYIYMA/graph.json","events_json":"https://pith.science/api/pith-number/2PHR2S5JQPCADHCC2RRKWYIYMA/events.json","paper":"https://pith.science/paper/2PHR2S5J"},"agent_actions":{"view_html":"https://pith.science/pith/2PHR2S5JQPCADHCC2RRKWYIYMA","download_json":"https://pith.science/pith/2PHR2S5JQPCADHCC2RRKWYIYMA.json","view_paper":"https://pith.science/paper/2PHR2S5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11079&json=true","fetch_graph":"https://pith.science/api/pith-number/2PHR2S5JQPCADHCC2RRKWYIYMA/graph.json","fetch_events":"https://pith.science/api/pith-number/2PHR2S5JQPCADHCC2RRKWYIYMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PHR2S5JQPCADHCC2RRKWYIYMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PHR2S5JQPCADHCC2RRKWYIYMA/action/storage_attestation","attest_author":"https://pith.science/pith/2PHR2S5JQPCADHCC2RRKWYIYMA/action/author_attestation","sign_citation":"https://pith.science/pith/2PHR2S5JQPCADHCC2RRKWYIYMA/action/citation_signature","submit_replication":"https://pith.science/pith/2PHR2S5JQPCADHCC2RRKWYIYMA/action/replication_record"}},"created_at":"2026-07-05T11:33:23.775973+00:00","updated_at":"2026-07-05T11:33:23.775973+00:00"}