{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5DL5NCFPCZ2VCRJC54S7VOBCFP","short_pith_number":"pith:5DL5NCFP","schema_version":"1.0","canonical_sha256":"e8d7d688af1675514522ef25fab8222bcc4dcde45d92151ddadf8980cae6dd51","source":{"kind":"arxiv","id":"2408.09933","version":1},"attestation_state":"computed","paper":{"title":"SZU-AFS Antispoofing System for the ASVspoof 5 Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Li, Jiafeng Zhong, Sengui Zheng, Yuxiong Xu, Zefeng Liu","submitted_at":"2024-08-19T12:12:29Z","abstract_excerpt":"This paper presents the SZU-AFS anti-spoofing system, designed for Track 1 of the ASVspoof 5 Challenge under open conditions. The system is built with four stages: selecting a baseline model, exploring effective data augmentation (DA) methods for fine-tuning, applying a co-enhancement strategy based on gradient norm aware minimization (GAM) for secondary fine-tuning, and fusing logits scores from the two best-performing fine-tuned models. The system utilizes the Wav2Vec2 front-end feature extractor and the AASIST back-end classifier as the baseline model. During model fine-tuning, three distin"},"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":"2408.09933","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-08-19T12:12:29Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"df0c4121ff8013c4d105e59f43e676953aa4933fb7ae77dbfc58a5e852ac5085","abstract_canon_sha256":"ee7dedef0b14b5e4610dfde0af244ea638d81fc5f66dfce761f54cc752e6f101"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:39.163248Z","signature_b64":"2t6e3WEsg36C4cDe2yAyS/QgRiV/S4AQSYfTifjlS3ACuH1Iyk+XiLCd2QMgMCI9wWXO6FQRRkRwx0hp9A4TCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8d7d688af1675514522ef25fab8222bcc4dcde45d92151ddadf8980cae6dd51","last_reissued_at":"2026-07-05T08:56:39.162793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:39.162793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SZU-AFS Antispoofing System for the ASVspoof 5 Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Li, Jiafeng Zhong, Sengui Zheng, Yuxiong Xu, Zefeng Liu","submitted_at":"2024-08-19T12:12:29Z","abstract_excerpt":"This paper presents the SZU-AFS anti-spoofing system, designed for Track 1 of the ASVspoof 5 Challenge under open conditions. The system is built with four stages: selecting a baseline model, exploring effective data augmentation (DA) methods for fine-tuning, applying a co-enhancement strategy based on gradient norm aware minimization (GAM) for secondary fine-tuning, and fusing logits scores from the two best-performing fine-tuned models. The system utilizes the Wav2Vec2 front-end feature extractor and the AASIST back-end classifier as the baseline model. During model fine-tuning, three distin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09933","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/2408.09933/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":"2408.09933","created_at":"2026-07-05T08:56:39.162852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09933v1","created_at":"2026-07-05T08:56:39.162852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09933","created_at":"2026-07-05T08:56:39.162852+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DL5NCFPCZ2V","created_at":"2026-07-05T08:56:39.162852+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DL5NCFPCZ2VCRJC","created_at":"2026-07-05T08:56:39.162852+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DL5NCFP","created_at":"2026-07-05T08:56:39.162852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17133","citing_title":"Tandem spoofing-robust automatic speaker verification based on time-domain embeddings","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5DL5NCFPCZ2VCRJC54S7VOBCFP","json":"https://pith.science/pith/5DL5NCFPCZ2VCRJC54S7VOBCFP.json","graph_json":"https://pith.science/api/pith-number/5DL5NCFPCZ2VCRJC54S7VOBCFP/graph.json","events_json":"https://pith.science/api/pith-number/5DL5NCFPCZ2VCRJC54S7VOBCFP/events.json","paper":"https://pith.science/paper/5DL5NCFP"},"agent_actions":{"view_html":"https://pith.science/pith/5DL5NCFPCZ2VCRJC54S7VOBCFP","download_json":"https://pith.science/pith/5DL5NCFPCZ2VCRJC54S7VOBCFP.json","view_paper":"https://pith.science/paper/5DL5NCFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09933&json=true","fetch_graph":"https://pith.science/api/pith-number/5DL5NCFPCZ2VCRJC54S7VOBCFP/graph.json","fetch_events":"https://pith.science/api/pith-number/5DL5NCFPCZ2VCRJC54S7VOBCFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DL5NCFPCZ2VCRJC54S7VOBCFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DL5NCFPCZ2VCRJC54S7VOBCFP/action/storage_attestation","attest_author":"https://pith.science/pith/5DL5NCFPCZ2VCRJC54S7VOBCFP/action/author_attestation","sign_citation":"https://pith.science/pith/5DL5NCFPCZ2VCRJC54S7VOBCFP/action/citation_signature","submit_replication":"https://pith.science/pith/5DL5NCFPCZ2VCRJC54S7VOBCFP/action/replication_record"}},"created_at":"2026-07-05T08:56:39.162852+00:00","updated_at":"2026-07-05T08:56:39.162852+00:00"}