{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YADD6DH56JIEV3SSFFPJ26FN75","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"06cfa777c5b3610e745b962f7c634717c38e7c482bc259339a48dd2d0f556c2c","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-27T13:53:53Z","title_canon_sha256":"c433b17203102885121492b7b913ae0148b74d275f80a01ffa445971d5252fb3"},"schema_version":"1.0","source":{"id":"2311.15830","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.15830","created_at":"2026-07-05T07:32:25Z"},{"alias_kind":"arxiv_version","alias_value":"2311.15830v3","created_at":"2026-07-05T07:32:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15830","created_at":"2026-07-05T07:32:25Z"},{"alias_kind":"pith_short_12","alias_value":"YADD6DH56JIE","created_at":"2026-07-05T07:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"YADD6DH56JIEV3SS","created_at":"2026-07-05T07:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"YADD6DH5","created_at":"2026-07-05T07:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:d6f6f0feaea3b212b9341604b80dc65f9e25438bfaed56997bf2a42d53287285","target":"graph","created_at":"2026-07-05T07:32:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.15830/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Junshi Huang, Mingyuan Fan, Zhengcong Fei","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-27T13:53:53Z","title":"A-JEPA: Joint-Embedding Predictive Architecture Can Listen"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15830","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cc67313328d1e8a21f1d4313ce054edf457de0735d4066e8f70f61b3289d845c","target":"record","created_at":"2026-07-05T07:32:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"06cfa777c5b3610e745b962f7c634717c38e7c482bc259339a48dd2d0f556c2c","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-27T13:53:53Z","title_canon_sha256":"c433b17203102885121492b7b913ae0148b74d275f80a01ffa445971d5252fb3"},"schema_version":"1.0","source":{"id":"2311.15830","kind":"arxiv","version":3}},"canonical_sha256":"c0063f0cfdf2504aee52295e9d78adff7b4b6a610f6faa5f05cd5375482d5112","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0063f0cfdf2504aee52295e9d78adff7b4b6a610f6faa5f05cd5375482d5112","first_computed_at":"2026-07-05T07:32:25.153336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:32:25.153336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zLlCQJ5ppQcHP3N0dK96ktgtkYJPTsZALe/ioj41lleQtTnwO8NcWlTla7V7irkRvKE2042aOSAEvf2vUpfBDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:32:25.153868Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.15830","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc67313328d1e8a21f1d4313ce054edf457de0735d4066e8f70f61b3289d845c","sha256:d6f6f0feaea3b212b9341604b80dc65f9e25438bfaed56997bf2a42d53287285"],"state_sha256":"b6dfa7d133b3f89bbb6bdaff1029c145aecc13bddb70eead733b40ed29367313"}