{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SQAN6YQTLD2WJ5Q6IJ3CATJU5Q","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":"da65de1cd5baa9438b29f3a2120d6c9e8f09b68971e03046687a58f4a4377c0a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-24T05:59:30Z","title_canon_sha256":"1dd29828db2d7e7798f26025e41229d7c3aa924e52e4ffdea120585abaf5894a"},"schema_version":"1.0","source":{"id":"2607.22000","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22000","created_at":"2026-07-27T01:20:42Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22000v1","created_at":"2026-07-27T01:20:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22000","created_at":"2026-07-27T01:20:42Z"},{"alias_kind":"pith_short_12","alias_value":"SQAN6YQTLD2W","created_at":"2026-07-27T01:20:42Z"},{"alias_kind":"pith_short_16","alias_value":"SQAN6YQTLD2WJ5Q6","created_at":"2026-07-27T01:20:42Z"},{"alias_kind":"pith_short_8","alias_value":"SQAN6YQT","created_at":"2026-07-27T01:20:42Z"}],"graph_snapshots":[{"event_id":"sha256:1269a649010ac94f46438d62efc8a85872e74132938d6651c1cdf0cfa4daa3f7","target":"graph","created_at":"2026-07-27T01:20:42Z","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/2607.22000/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Joint Embedding Predictive Architectures (JEPA) have recently emerged as a paradigm for learning world models by predicting latent representations, offering a promising direction for self-supervised learning. While initial attempts have applied JEPA to the music domain, it remains unclear how such frameworks can naturally support the formation of a world model for music. In this work, we propose to learn a world model of piano sound using JEPA by framing music as an action-conditioned system: the audio is treated as the state, and the pianoroll as the instrument action. Given a current audio s","authors_text":"Kun Fang, Yann LeCun, Ziyu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-24T05:59:30Z","title":"Music-JEPA: Learning a World Model of Sound from Action"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22000","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":"sha256:0f1d7522fa992e7f9b54ca85bce9993da5cb35bb5ccf7a7887eb04ffd4444642","target":"record","created_at":"2026-07-27T01:20:42Z","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":"da65de1cd5baa9438b29f3a2120d6c9e8f09b68971e03046687a58f4a4377c0a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-24T05:59:30Z","title_canon_sha256":"1dd29828db2d7e7798f26025e41229d7c3aa924e52e4ffdea120585abaf5894a"},"schema_version":"1.0","source":{"id":"2607.22000","kind":"arxiv","version":1}},"canonical_sha256":"9400df621358f564f61e4276204d34ec0de4deaff8deb9977af2bffcf70d162c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9400df621358f564f61e4276204d34ec0de4deaff8deb9977af2bffcf70d162c","first_computed_at":"2026-07-27T01:20:42.528435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T01:20:42.528435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fu0kOCeUNEs6+GQ4kpWVU0rl/sSTtU4CzAdrn3lqlidJu+1Qr1Jbmnjg+axuoxCoAuxVNIKnD3I7khXqQT4+Ag==","signature_status":"signed_v1","signed_at":"2026-07-27T01:20:42.529354Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22000","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f1d7522fa992e7f9b54ca85bce9993da5cb35bb5ccf7a7887eb04ffd4444642","sha256:1269a649010ac94f46438d62efc8a85872e74132938d6651c1cdf0cfa4daa3f7"],"state_sha256":"ca17807daf2473faa867e13ec697826c2437c95abfdbd11f3d98dbbf1cc0497b"}