{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WMJ47BYZMMWWRPCHY53TKYFL3C","short_pith_number":"pith:WMJ47BYZ","schema_version":"1.0","canonical_sha256":"b313cf8719632d68bc47c7773560abd89e814408c7ed37887396d8b18bd9a98b","source":{"kind":"arxiv","id":"2406.11364","version":1},"attestation_state":"computed","paper":{"title":"AnoPatch: Towards Better Consistency in Machine Anomalous Sound Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Anbai Jiang, Bing Han, Jia Liu, Pingyi Fan, Wei-Qiang Zhang, Xie Chen, Yanmin Qian, Yufeng Deng, Zhiqiang Lv","submitted_at":"2024-06-17T09:37:29Z","abstract_excerpt":"Large pre-trained models have demonstrated dominant performances in multiple areas, where the consistency between pre-training and fine-tuning is the key to success. However, few works reported satisfactory results of pre-trained models for the machine anomalous sound detection (ASD) task. This may be caused by the inconsistency of the pre-trained model and the inductive bias of machine audio, resulting in inconsistency in data and architecture. Thus, we propose AnoPatch which utilizes a ViT backbone pre-trained on AudioSet and fine-tunes it on machine audio. It is believed that machine audio "},"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":"2406.11364","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-17T09:37:29Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"2369d3d17a1eab2384ea150ee57de5d37a3c07464e5f102727753813d2e41e39","abstract_canon_sha256":"202147bceadb8fb440a996364cbeb35e83c2580109802f984c9994f0c7090782"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:52.477425Z","signature_b64":"clQtkv58067g1aOJHVZhxvdIQxWgA6viJt4g42OCpBU4GCY5pP8nKMWonveTO0wTbabCoIpe3pGhGUvhr6+4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b313cf8719632d68bc47c7773560abd89e814408c7ed37887396d8b18bd9a98b","last_reissued_at":"2026-07-05T08:32:52.477068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:52.477068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnoPatch: Towards Better Consistency in Machine Anomalous Sound Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Anbai Jiang, Bing Han, Jia Liu, Pingyi Fan, Wei-Qiang Zhang, Xie Chen, Yanmin Qian, Yufeng Deng, Zhiqiang Lv","submitted_at":"2024-06-17T09:37:29Z","abstract_excerpt":"Large pre-trained models have demonstrated dominant performances in multiple areas, where the consistency between pre-training and fine-tuning is the key to success. However, few works reported satisfactory results of pre-trained models for the machine anomalous sound detection (ASD) task. This may be caused by the inconsistency of the pre-trained model and the inductive bias of machine audio, resulting in inconsistency in data and architecture. Thus, we propose AnoPatch which utilizes a ViT backbone pre-trained on AudioSet and fine-tunes it on machine audio. It is believed that machine audio "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11364","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/2406.11364/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":"2406.11364","created_at":"2026-07-05T08:32:52.477123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11364v1","created_at":"2026-07-05T08:32:52.477123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11364","created_at":"2026-07-05T08:32:52.477123+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMJ47BYZMMWW","created_at":"2026-07-05T08:32:52.477123+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMJ47BYZMMWWRPCH","created_at":"2026-07-05T08:32:52.477123+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMJ47BYZ","created_at":"2026-07-05T08:32:52.477123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00387","citing_title":"From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning","ref_index":96,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMJ47BYZMMWWRPCHY53TKYFL3C","json":"https://pith.science/pith/WMJ47BYZMMWWRPCHY53TKYFL3C.json","graph_json":"https://pith.science/api/pith-number/WMJ47BYZMMWWRPCHY53TKYFL3C/graph.json","events_json":"https://pith.science/api/pith-number/WMJ47BYZMMWWRPCHY53TKYFL3C/events.json","paper":"https://pith.science/paper/WMJ47BYZ"},"agent_actions":{"view_html":"https://pith.science/pith/WMJ47BYZMMWWRPCHY53TKYFL3C","download_json":"https://pith.science/pith/WMJ47BYZMMWWRPCHY53TKYFL3C.json","view_paper":"https://pith.science/paper/WMJ47BYZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11364&json=true","fetch_graph":"https://pith.science/api/pith-number/WMJ47BYZMMWWRPCHY53TKYFL3C/graph.json","fetch_events":"https://pith.science/api/pith-number/WMJ47BYZMMWWRPCHY53TKYFL3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMJ47BYZMMWWRPCHY53TKYFL3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMJ47BYZMMWWRPCHY53TKYFL3C/action/storage_attestation","attest_author":"https://pith.science/pith/WMJ47BYZMMWWRPCHY53TKYFL3C/action/author_attestation","sign_citation":"https://pith.science/pith/WMJ47BYZMMWWRPCHY53TKYFL3C/action/citation_signature","submit_replication":"https://pith.science/pith/WMJ47BYZMMWWRPCHY53TKYFL3C/action/replication_record"}},"created_at":"2026-07-05T08:32:52.477123+00:00","updated_at":"2026-07-05T08:32:52.477123+00:00"}