{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EIUTNMPULQWTYVBTTE2IMXYIOO","short_pith_number":"pith:EIUTNMPU","schema_version":"1.0","canonical_sha256":"222936b1f45c2d3c54339934865f0873b77b200f3a0030cad29b79422ee07ef7","source":{"kind":"arxiv","id":"2312.06197","version":3},"attestation_state":"computed","paper":{"title":"MART: Learning Hierarchical Music Audio Representations with Part-Whole Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dong Yao, Jiahao Xun, Jieming Zhu, Liqun Deng, Shengyu Zhang, Wenqiao Zhang, Xin Jiang, Zhenhua Dong, Zhou Zhao","submitted_at":"2023-12-11T08:17:58Z","abstract_excerpt":"Recent research in self-supervised contrastive learning of music representations has demonstrated remarkable results across diverse downstream tasks. However, a prevailing trend in existing methods involves representing equally-sized music clips in either waveform or spectrogram formats, often overlooking the intrinsic part-whole hierarchies within music. In our quest to comprehend the bottom-up structure of music, we introduce MART, a hierarchical music representation learning approach that facilitates feature interactions among cropped music clips while considering their part-whole hierarchi"},"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":"2312.06197","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-11T08:17:58Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"c8165f5f1c25ee36dd5832a85cd9ac04caa9383b9e735ec888e77729c61ae9fb","abstract_canon_sha256":"342395105aa1bea9274351d1a2c442765ec2d29d204d6148fa78d66f6139a155"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:46.761725Z","signature_b64":"U9U5vyIRjkq7gLAmtvbz0/YJsZIPMfU6/RAEz1aU9OE/+UJkwlUsA/oWyHEupjRgsLmkUvIKfZhSn4LL2Zt5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"222936b1f45c2d3c54339934865f0873b77b200f3a0030cad29b79422ee07ef7","last_reissued_at":"2026-07-05T08:09:46.761229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:46.761229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MART: Learning Hierarchical Music Audio Representations with Part-Whole Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dong Yao, Jiahao Xun, Jieming Zhu, Liqun Deng, Shengyu Zhang, Wenqiao Zhang, Xin Jiang, Zhenhua Dong, Zhou Zhao","submitted_at":"2023-12-11T08:17:58Z","abstract_excerpt":"Recent research in self-supervised contrastive learning of music representations has demonstrated remarkable results across diverse downstream tasks. However, a prevailing trend in existing methods involves representing equally-sized music clips in either waveform or spectrogram formats, often overlooking the intrinsic part-whole hierarchies within music. In our quest to comprehend the bottom-up structure of music, we introduce MART, a hierarchical music representation learning approach that facilitates feature interactions among cropped music clips while considering their part-whole hierarchi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06197","kind":"arxiv","version":3},"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/2312.06197/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":"2312.06197","created_at":"2026-07-05T08:09:46.761286+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.06197v3","created_at":"2026-07-05T08:09:46.761286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06197","created_at":"2026-07-05T08:09:46.761286+00:00"},{"alias_kind":"pith_short_12","alias_value":"EIUTNMPULQWT","created_at":"2026-07-05T08:09:46.761286+00:00"},{"alias_kind":"pith_short_16","alias_value":"EIUTNMPULQWTYVBT","created_at":"2026-07-05T08:09:46.761286+00:00"},{"alias_kind":"pith_short_8","alias_value":"EIUTNMPU","created_at":"2026-07-05T08:09:46.761286+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/EIUTNMPULQWTYVBTTE2IMXYIOO","json":"https://pith.science/pith/EIUTNMPULQWTYVBTTE2IMXYIOO.json","graph_json":"https://pith.science/api/pith-number/EIUTNMPULQWTYVBTTE2IMXYIOO/graph.json","events_json":"https://pith.science/api/pith-number/EIUTNMPULQWTYVBTTE2IMXYIOO/events.json","paper":"https://pith.science/paper/EIUTNMPU"},"agent_actions":{"view_html":"https://pith.science/pith/EIUTNMPULQWTYVBTTE2IMXYIOO","download_json":"https://pith.science/pith/EIUTNMPULQWTYVBTTE2IMXYIOO.json","view_paper":"https://pith.science/paper/EIUTNMPU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.06197&json=true","fetch_graph":"https://pith.science/api/pith-number/EIUTNMPULQWTYVBTTE2IMXYIOO/graph.json","fetch_events":"https://pith.science/api/pith-number/EIUTNMPULQWTYVBTTE2IMXYIOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EIUTNMPULQWTYVBTTE2IMXYIOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EIUTNMPULQWTYVBTTE2IMXYIOO/action/storage_attestation","attest_author":"https://pith.science/pith/EIUTNMPULQWTYVBTTE2IMXYIOO/action/author_attestation","sign_citation":"https://pith.science/pith/EIUTNMPULQWTYVBTTE2IMXYIOO/action/citation_signature","submit_replication":"https://pith.science/pith/EIUTNMPULQWTYVBTTE2IMXYIOO/action/replication_record"}},"created_at":"2026-07-05T08:09:46.761286+00:00","updated_at":"2026-07-05T08:09:46.761286+00:00"}