{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DG2MXG4JP3HDRE4GJEMCYVSBGF","short_pith_number":"pith:DG2MXG4J","schema_version":"1.0","canonical_sha256":"19b4cb9b897ece38938649182c5641316cfad9edf14cbcd1221fbcb23fbc0264","source":{"kind":"arxiv","id":"2403.09579","version":1},"attestation_state":"computed","paper":{"title":"uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Afrina Tabassum, Dung Tran, Ismini Lourentzou, Kazuhito Koishida, Trung Dang","submitted_at":"2024-03-14T17:13:37Z","abstract_excerpt":"Masked Autoencoders (MAEs) learn rich low-level representations from unlabeled data but require substantial labeled data to effectively adapt to downstream tasks. Conversely, Instance Discrimination (ID) emphasizes high-level semantics, offering a potential solution to alleviate annotation requirements in MAEs. Although combining these two approaches can address downstream tasks with limited labeled data, naively integrating ID into MAEs leads to extended training times and high computational costs. To address this challenge, we introduce uaMix-MAE, an efficient ID tuning strategy that leverag"},"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":"2403.09579","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-03-14T17:13:37Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"ad3f21c646f9389b2a82993728b5a9c7f66765a9a34339356f996b738a48280c","abstract_canon_sha256":"c409cbe361eeeb9afd126007165828a852d649a0be2cb2dec3ef7c7c1294aa1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:11.642490Z","signature_b64":"/XPQIxoljWFTRqQlp69Bt8ue3NYdTKFaLj6OCltJYWtiw1lx/MBpqhj6TzqmQTWri8dkI3jfONJu+lIR1OkcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19b4cb9b897ece38938649182c5641316cfad9edf14cbcd1221fbcb23fbc0264","last_reissued_at":"2026-07-05T07:56:11.641956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:11.641956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Afrina Tabassum, Dung Tran, Ismini Lourentzou, Kazuhito Koishida, Trung Dang","submitted_at":"2024-03-14T17:13:37Z","abstract_excerpt":"Masked Autoencoders (MAEs) learn rich low-level representations from unlabeled data but require substantial labeled data to effectively adapt to downstream tasks. Conversely, Instance Discrimination (ID) emphasizes high-level semantics, offering a potential solution to alleviate annotation requirements in MAEs. Although combining these two approaches can address downstream tasks with limited labeled data, naively integrating ID into MAEs leads to extended training times and high computational costs. To address this challenge, we introduce uaMix-MAE, an efficient ID tuning strategy that leverag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09579","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/2403.09579/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":"2403.09579","created_at":"2026-07-05T07:56:11.642026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09579v1","created_at":"2026-07-05T07:56:11.642026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09579","created_at":"2026-07-05T07:56:11.642026+00:00"},{"alias_kind":"pith_short_12","alias_value":"DG2MXG4JP3HD","created_at":"2026-07-05T07:56:11.642026+00:00"},{"alias_kind":"pith_short_16","alias_value":"DG2MXG4JP3HDRE4G","created_at":"2026-07-05T07:56:11.642026+00:00"},{"alias_kind":"pith_short_8","alias_value":"DG2MXG4J","created_at":"2026-07-05T07:56:11.642026+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/DG2MXG4JP3HDRE4GJEMCYVSBGF","json":"https://pith.science/pith/DG2MXG4JP3HDRE4GJEMCYVSBGF.json","graph_json":"https://pith.science/api/pith-number/DG2MXG4JP3HDRE4GJEMCYVSBGF/graph.json","events_json":"https://pith.science/api/pith-number/DG2MXG4JP3HDRE4GJEMCYVSBGF/events.json","paper":"https://pith.science/paper/DG2MXG4J"},"agent_actions":{"view_html":"https://pith.science/pith/DG2MXG4JP3HDRE4GJEMCYVSBGF","download_json":"https://pith.science/pith/DG2MXG4JP3HDRE4GJEMCYVSBGF.json","view_paper":"https://pith.science/paper/DG2MXG4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09579&json=true","fetch_graph":"https://pith.science/api/pith-number/DG2MXG4JP3HDRE4GJEMCYVSBGF/graph.json","fetch_events":"https://pith.science/api/pith-number/DG2MXG4JP3HDRE4GJEMCYVSBGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DG2MXG4JP3HDRE4GJEMCYVSBGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DG2MXG4JP3HDRE4GJEMCYVSBGF/action/storage_attestation","attest_author":"https://pith.science/pith/DG2MXG4JP3HDRE4GJEMCYVSBGF/action/author_attestation","sign_citation":"https://pith.science/pith/DG2MXG4JP3HDRE4GJEMCYVSBGF/action/citation_signature","submit_replication":"https://pith.science/pith/DG2MXG4JP3HDRE4GJEMCYVSBGF/action/replication_record"}},"created_at":"2026-07-05T07:56:11.642026+00:00","updated_at":"2026-07-05T07:56:11.642026+00:00"}