{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A2ZU5K2TGDRMSFB5LWMIX6TXUJ","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":"a43f2a91c31acface75d3f371bee55c15cdb67a422055dc40abd5a2884ac8975","cross_cats_sorted":["cs.AI","cs.LG","eess.AS","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-25T08:38:27Z","title_canon_sha256":"e4594f6a56d95835967af77fb0979ff02598b9d8abf9514fea4523c8f4299e9d"},"schema_version":"1.0","source":{"id":"2507.02915","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02915","created_at":"2026-07-05T11:31:48Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02915v1","created_at":"2026-07-05T11:31:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02915","created_at":"2026-07-05T11:31:48Z"},{"alias_kind":"pith_short_12","alias_value":"A2ZU5K2TGDRM","created_at":"2026-07-05T11:31:48Z"},{"alias_kind":"pith_short_16","alias_value":"A2ZU5K2TGDRMSFB5","created_at":"2026-07-05T11:31:48Z"},{"alias_kind":"pith_short_8","alias_value":"A2ZU5K2T","created_at":"2026-07-05T11:31:48Z"}],"graph_snapshots":[{"event_id":"sha256:39be198c77f64f3cc818190e9f630a72108555643fe9b81041357a3d0e47ba75","target":"graph","created_at":"2026-07-05T11:31:48Z","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/2507.02915/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building on the Joint-Embedding Predictive Architecture (JEPA) paradigm, a recent self-supervised learning framework that predicts latent representations of masked regions in high-level feature spaces, we propose Audio-JEPA (Audio Joint-Embedding Predictive Architecture), tailored specifically for audio data. Audio-JEPA uses a simple Vision Transformer backbone to predict latent representations of masked spectrogram patches rather than reconstructing raw audio. We pre-train on unlabeled AudioSet clips (10s, 32kHz) with random patch masking on mel-spectrograms. We evaluate on the X-ARES suite c","authors_text":"Emmanouil Benetos (QMUL), Etienne Labb\\'e (IRIT-SAMoVA), Ludovic Tuncay (IRIT-SAMoVA), Thomas Pellegrini (IRIT-SAMoVA)","cross_cats":["cs.AI","cs.LG","eess.AS","eess.SP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-25T08:38:27Z","title":"Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02915","kind":"arxiv","version":1},"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":"sha256:9619d4a18febc8c9218c15a1fc0f7dfc9e821c155399c86609af1d63567e9a4f","target":"record","created_at":"2026-07-05T11:31:48Z","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":"a43f2a91c31acface75d3f371bee55c15cdb67a422055dc40abd5a2884ac8975","cross_cats_sorted":["cs.AI","cs.LG","eess.AS","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-25T08:38:27Z","title_canon_sha256":"e4594f6a56d95835967af77fb0979ff02598b9d8abf9514fea4523c8f4299e9d"},"schema_version":"1.0","source":{"id":"2507.02915","kind":"arxiv","version":1}},"canonical_sha256":"06b34eab5330e2c9143d5d988bfa77a251d80f87e8a8edc781716df3380ef8de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06b34eab5330e2c9143d5d988bfa77a251d80f87e8a8edc781716df3380ef8de","first_computed_at":"2026-07-05T11:31:48.641916Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:48.641916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AoDSzSAf77IvQ5/gKzeLPD36aRqwxCfyW8bkl9HrupJAcBgI1oYGLq8aUwhU3Q/6Envm0qqjBf7MYlKz1oOiCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:48.642541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02915","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9619d4a18febc8c9218c15a1fc0f7dfc9e821c155399c86609af1d63567e9a4f","sha256:39be198c77f64f3cc818190e9f630a72108555643fe9b81041357a3d0e47ba75"],"state_sha256":"6ca856a5717581ad4001aa3cfb074cc2102b06e617dcd285c5eea8a0251a45b4"}