{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HVFJBUIS4JIWAGZTQLOLHS7AFI","short_pith_number":"pith:HVFJBUIS","schema_version":"1.0","canonical_sha256":"3d4a90d112e251601b3382dcb3cbe02a18195a8284e91994ea854eea10ef92dd","source":{"kind":"arxiv","id":"2509.04985","version":1},"attestation_state":"computed","paper":{"title":"Training a Perceptual Model for Evaluating Auditory Similarity in Music Adversarial Attack","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Peihong Zhang, Rui Sang, Shengchen Li, Yuxuan Liu, Zhixin Li","submitted_at":"2025-09-05T10:23:44Z","abstract_excerpt":"Music Information Retrieval (MIR) systems are highly vulnerable to adversarial attacks that are often imperceptible to humans, primarily due to a misalignment between model feature spaces and human auditory perception. Existing defenses and perceptual metrics frequently fail to adequately capture these auditory nuances, a limitation supported by our initial listening tests showing low correlation between common metrics and human judgments. To bridge this gap, we introduce Perceptually-Aligned MERT Transformer (PAMT), a novel framework for learning robust, perceptually-aligned music representat"},"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":"2509.04985","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-05T10:23:44Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"68a40c8306b982858bd5868593801ffee03fbd091a5766b8da3bff4aa3dcad67","abstract_canon_sha256":"ac220694d07d594ca2b2d0ab09fd7ec5e6fad0e9a1d559516e5e0cfe4e30d6f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:33.980230Z","signature_b64":"2oN5mTMGuFIJge3ln8xMnhT+whLyUD6lt0mx7c4bIv82O32S9qjg/XQ1LogBUv09Y1r21mDQPHYnUYwck91iCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d4a90d112e251601b3382dcb3cbe02a18195a8284e91994ea854eea10ef92dd","last_reissued_at":"2026-07-05T12:05:33.979729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:33.979729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training a Perceptual Model for Evaluating Auditory Similarity in Music Adversarial Attack","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Peihong Zhang, Rui Sang, Shengchen Li, Yuxuan Liu, Zhixin Li","submitted_at":"2025-09-05T10:23:44Z","abstract_excerpt":"Music Information Retrieval (MIR) systems are highly vulnerable to adversarial attacks that are often imperceptible to humans, primarily due to a misalignment between model feature spaces and human auditory perception. Existing defenses and perceptual metrics frequently fail to adequately capture these auditory nuances, a limitation supported by our initial listening tests showing low correlation between common metrics and human judgments. To bridge this gap, we introduce Perceptually-Aligned MERT Transformer (PAMT), a novel framework for learning robust, perceptually-aligned music representat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04985","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/2509.04985/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":"2509.04985","created_at":"2026-07-05T12:05:33.979791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04985v1","created_at":"2026-07-05T12:05:33.979791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04985","created_at":"2026-07-05T12:05:33.979791+00:00"},{"alias_kind":"pith_short_12","alias_value":"HVFJBUIS4JIW","created_at":"2026-07-05T12:05:33.979791+00:00"},{"alias_kind":"pith_short_16","alias_value":"HVFJBUIS4JIWAGZT","created_at":"2026-07-05T12:05:33.979791+00:00"},{"alias_kind":"pith_short_8","alias_value":"HVFJBUIS","created_at":"2026-07-05T12:05:33.979791+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HVFJBUIS4JIWAGZTQLOLHS7AFI","json":"https://pith.science/pith/HVFJBUIS4JIWAGZTQLOLHS7AFI.json","graph_json":"https://pith.science/api/pith-number/HVFJBUIS4JIWAGZTQLOLHS7AFI/graph.json","events_json":"https://pith.science/api/pith-number/HVFJBUIS4JIWAGZTQLOLHS7AFI/events.json","paper":"https://pith.science/paper/HVFJBUIS"},"agent_actions":{"view_html":"https://pith.science/pith/HVFJBUIS4JIWAGZTQLOLHS7AFI","download_json":"https://pith.science/pith/HVFJBUIS4JIWAGZTQLOLHS7AFI.json","view_paper":"https://pith.science/paper/HVFJBUIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04985&json=true","fetch_graph":"https://pith.science/api/pith-number/HVFJBUIS4JIWAGZTQLOLHS7AFI/graph.json","fetch_events":"https://pith.science/api/pith-number/HVFJBUIS4JIWAGZTQLOLHS7AFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HVFJBUIS4JIWAGZTQLOLHS7AFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HVFJBUIS4JIWAGZTQLOLHS7AFI/action/storage_attestation","attest_author":"https://pith.science/pith/HVFJBUIS4JIWAGZTQLOLHS7AFI/action/author_attestation","sign_citation":"https://pith.science/pith/HVFJBUIS4JIWAGZTQLOLHS7AFI/action/citation_signature","submit_replication":"https://pith.science/pith/HVFJBUIS4JIWAGZTQLOLHS7AFI/action/replication_record"}},"created_at":"2026-07-05T12:05:33.979791+00:00","updated_at":"2026-07-05T12:05:33.979791+00:00"}