{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YADD6DH56JIEV3SSFFPJ26FN75","short_pith_number":"pith:YADD6DH5","schema_version":"1.0","canonical_sha256":"c0063f0cfdf2504aee52295e9d78adff7b4b6a610f6faa5f05cd5375482d5112","source":{"kind":"arxiv","id":"2311.15830","version":3},"attestation_state":"computed","paper":{"title":"A-JEPA: Joint-Embedding Predictive Architecture Can Listen","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Junshi Huang, Mingyuan Fan, Zhengcong Fei","submitted_at":"2023-11-27T13:53:53Z","abstract_excerpt":"This paper presents that the masked-modeling principle driving the success of large foundational vision models can be effectively applied to audio by making predictions in a latent space. We introduce Audio-based Joint-Embedding Predictive Architecture (A-JEPA), a simple extension method for self-supervised learning from the audio spectrum. Following the design of I-JEPA, our A-JEPA encodes visible audio spectrogram patches with a curriculum masking strategy via context encoder, and predicts the representations of regions sampled at well-designed locations. The target representations of those "},"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":"2311.15830","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-27T13:53:53Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"c433b17203102885121492b7b913ae0148b74d275f80a01ffa445971d5252fb3","abstract_canon_sha256":"06cfa777c5b3610e745b962f7c634717c38e7c482bc259339a48dd2d0f556c2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:25.153868Z","signature_b64":"zLlCQJ5ppQcHP3N0dK96ktgtkYJPTsZALe/ioj41lleQtTnwO8NcWlTla7V7irkRvKE2042aOSAEvf2vUpfBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0063f0cfdf2504aee52295e9d78adff7b4b6a610f6faa5f05cd5375482d5112","last_reissued_at":"2026-07-05T07:32:25.153336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:25.153336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A-JEPA: Joint-Embedding Predictive Architecture Can Listen","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Junshi Huang, Mingyuan Fan, Zhengcong Fei","submitted_at":"2023-11-27T13:53:53Z","abstract_excerpt":"This paper presents that the masked-modeling principle driving the success of large foundational vision models can be effectively applied to audio by making predictions in a latent space. We introduce Audio-based Joint-Embedding Predictive Architecture (A-JEPA), a simple extension method for self-supervised learning from the audio spectrum. Following the design of I-JEPA, our A-JEPA encodes visible audio spectrogram patches with a curriculum masking strategy via context encoder, and predicts the representations of regions sampled at well-designed locations. The target representations of those "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15830","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/2311.15830/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":"2311.15830","created_at":"2026-07-05T07:32:25.153395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.15830v3","created_at":"2026-07-05T07:32:25.153395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15830","created_at":"2026-07-05T07:32:25.153395+00:00"},{"alias_kind":"pith_short_12","alias_value":"YADD6DH56JIE","created_at":"2026-07-05T07:32:25.153395+00:00"},{"alias_kind":"pith_short_16","alias_value":"YADD6DH56JIEV3SS","created_at":"2026-07-05T07:32:25.153395+00:00"},{"alias_kind":"pith_short_8","alias_value":"YADD6DH5","created_at":"2026-07-05T07:32:25.153395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25713","citing_title":"Frequency-Aware Self-Supervised Music Representation Learning","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25225","citing_title":"MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20781","citing_title":"World Action Models: A Survey","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00052","citing_title":"AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06582","citing_title":"PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25713","citing_title":"Frequency-Aware Self-Supervised Music Representation Learning","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13684","citing_title":"Recurrent Video Masked Autoencoders","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14231","citing_title":"AudioMosaic: Contrastive Masked Audio Representation Learning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06582","citing_title":"PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05586","citing_title":"AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16086","citing_title":"Stylistic-STORM (ST-STORM) : Perceiving the Semantic Nature of Appearance","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YADD6DH56JIEV3SSFFPJ26FN75","json":"https://pith.science/pith/YADD6DH56JIEV3SSFFPJ26FN75.json","graph_json":"https://pith.science/api/pith-number/YADD6DH56JIEV3SSFFPJ26FN75/graph.json","events_json":"https://pith.science/api/pith-number/YADD6DH56JIEV3SSFFPJ26FN75/events.json","paper":"https://pith.science/paper/YADD6DH5"},"agent_actions":{"view_html":"https://pith.science/pith/YADD6DH56JIEV3SSFFPJ26FN75","download_json":"https://pith.science/pith/YADD6DH56JIEV3SSFFPJ26FN75.json","view_paper":"https://pith.science/paper/YADD6DH5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.15830&json=true","fetch_graph":"https://pith.science/api/pith-number/YADD6DH56JIEV3SSFFPJ26FN75/graph.json","fetch_events":"https://pith.science/api/pith-number/YADD6DH56JIEV3SSFFPJ26FN75/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YADD6DH56JIEV3SSFFPJ26FN75/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YADD6DH56JIEV3SSFFPJ26FN75/action/storage_attestation","attest_author":"https://pith.science/pith/YADD6DH56JIEV3SSFFPJ26FN75/action/author_attestation","sign_citation":"https://pith.science/pith/YADD6DH56JIEV3SSFFPJ26FN75/action/citation_signature","submit_replication":"https://pith.science/pith/YADD6DH56JIEV3SSFFPJ26FN75/action/replication_record"}},"created_at":"2026-07-05T07:32:25.153395+00:00","updated_at":"2026-07-05T07:32:25.153395+00:00"}