{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3ITXCIMZCVVBYXUEFXZOYBPTKM","short_pith_number":"pith:3ITXCIMZ","schema_version":"1.0","canonical_sha256":"da27712199156a1c5e842df2ec05f3530974cfe957922adb8b76e67a7e0a3525","source":{"kind":"arxiv","id":"2508.10559","version":1},"attestation_state":"computed","paper":{"title":"Fake Speech Wild: Detecting Deepfake Speech on Social Media Platform","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Haonnan Cheng, Long Ye, Ruibo Fu, Xiaopeng Wang, Ya Li, Yuankun Xie, Zhengqi Wen, Zhiyong Wang","submitted_at":"2025-08-14T11:56:30Z","abstract_excerpt":"The rapid advancement of speech generation technology has led to the widespread proliferation of deepfake speech across social media platforms. While deepfake audio countermeasures (CMs) achieve promising results on public datasets, their performance degrades significantly in cross-domain scenarios. To advance CMs for real-world deepfake detection, we first propose the Fake Speech Wild (FSW) dataset, which includes 254 hours of real and deepfake audio from four different media platforms, focusing on social media. As CMs, we establish a benchmark using public datasets and advanced selfsupervise"},"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":"2508.10559","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-14T11:56:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"96af92c891e5d1ce7909c56880ce65d63eb841aabfdce1366b2d7fd48766ab1b","abstract_canon_sha256":"9a800ade35a90b933551a82b18d4d10461dcb0fb2198fd0872c26d5456bc1c66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:58.283095Z","signature_b64":"l9kGb0lqgrR2PiUaavEIRmD2B4E7mDeqXDm/6ETLo6GMg3rc+6hwpgLtb8WIm30eosL5ZmAQNlrS4U3rcyMZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da27712199156a1c5e842df2ec05f3530974cfe957922adb8b76e67a7e0a3525","last_reissued_at":"2026-07-05T11:53:58.282650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:58.282650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fake Speech Wild: Detecting Deepfake Speech on Social Media Platform","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Haonnan Cheng, Long Ye, Ruibo Fu, Xiaopeng Wang, Ya Li, Yuankun Xie, Zhengqi Wen, Zhiyong Wang","submitted_at":"2025-08-14T11:56:30Z","abstract_excerpt":"The rapid advancement of speech generation technology has led to the widespread proliferation of deepfake speech across social media platforms. While deepfake audio countermeasures (CMs) achieve promising results on public datasets, their performance degrades significantly in cross-domain scenarios. To advance CMs for real-world deepfake detection, we first propose the Fake Speech Wild (FSW) dataset, which includes 254 hours of real and deepfake audio from four different media platforms, focusing on social media. As CMs, we establish a benchmark using public datasets and advanced selfsupervise"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10559","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/2508.10559/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":"2508.10559","created_at":"2026-07-05T11:53:58.282711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10559v1","created_at":"2026-07-05T11:53:58.282711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10559","created_at":"2026-07-05T11:53:58.282711+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ITXCIMZCVVB","created_at":"2026-07-05T11:53:58.282711+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ITXCIMZCVVBYXUE","created_at":"2026-07-05T11:53:58.282711+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ITXCIMZ","created_at":"2026-07-05T11:53:58.282711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08038","citing_title":"Exploring the Scale and Diversity of Speech Anti-spoofing Datasets: Experiments and Analysis","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23742","citing_title":"RTCFake: Speech Deepfake Detection in Real-Time Communication","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ITXCIMZCVVBYXUEFXZOYBPTKM","json":"https://pith.science/pith/3ITXCIMZCVVBYXUEFXZOYBPTKM.json","graph_json":"https://pith.science/api/pith-number/3ITXCIMZCVVBYXUEFXZOYBPTKM/graph.json","events_json":"https://pith.science/api/pith-number/3ITXCIMZCVVBYXUEFXZOYBPTKM/events.json","paper":"https://pith.science/paper/3ITXCIMZ"},"agent_actions":{"view_html":"https://pith.science/pith/3ITXCIMZCVVBYXUEFXZOYBPTKM","download_json":"https://pith.science/pith/3ITXCIMZCVVBYXUEFXZOYBPTKM.json","view_paper":"https://pith.science/paper/3ITXCIMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10559&json=true","fetch_graph":"https://pith.science/api/pith-number/3ITXCIMZCVVBYXUEFXZOYBPTKM/graph.json","fetch_events":"https://pith.science/api/pith-number/3ITXCIMZCVVBYXUEFXZOYBPTKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ITXCIMZCVVBYXUEFXZOYBPTKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ITXCIMZCVVBYXUEFXZOYBPTKM/action/storage_attestation","attest_author":"https://pith.science/pith/3ITXCIMZCVVBYXUEFXZOYBPTKM/action/author_attestation","sign_citation":"https://pith.science/pith/3ITXCIMZCVVBYXUEFXZOYBPTKM/action/citation_signature","submit_replication":"https://pith.science/pith/3ITXCIMZCVVBYXUEFXZOYBPTKM/action/replication_record"}},"created_at":"2026-07-05T11:53:58.282711+00:00","updated_at":"2026-07-05T11:53:58.282711+00:00"}