{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SQAN6YQTLD2WJ5Q6IJ3CATJU5Q","short_pith_number":"pith:SQAN6YQT","schema_version":"1.0","canonical_sha256":"9400df621358f564f61e4276204d34ec0de4deaff8deb9977af2bffcf70d162c","source":{"kind":"arxiv","id":"2607.22000","version":1},"attestation_state":"computed","paper":{"title":"Music-JEPA: Learning a World Model of Sound from Action","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Kun Fang, Yann LeCun, Ziyu Wang","submitted_at":"2026-07-24T05:59:30Z","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"},"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":"2607.22000","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-24T05:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"1dd29828db2d7e7798f26025e41229d7c3aa924e52e4ffdea120585abaf5894a","abstract_canon_sha256":"da65de1cd5baa9438b29f3a2120d6c9e8f09b68971e03046687a58f4a4377c0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:20:42.529354Z","signature_b64":"Fu0kOCeUNEs6+GQ4kpWVU0rl/sSTtU4CzAdrn3lqlidJu+1Qr1Jbmnjg+axuoxCoAuxVNIKnD3I7khXqQT4+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9400df621358f564f61e4276204d34ec0de4deaff8deb9977af2bffcf70d162c","last_reissued_at":"2026-07-27T01:20:42.528435Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:20:42.528435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Music-JEPA: Learning a World Model of Sound from Action","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Kun Fang, Yann LeCun, Ziyu Wang","submitted_at":"2026-07-24T05:59:30Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22000","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/2607.22000/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":"2607.22000","created_at":"2026-07-27T01:20:42.528884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22000v1","created_at":"2026-07-27T01:20:42.528884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22000","created_at":"2026-07-27T01:20:42.528884+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQAN6YQTLD2W","created_at":"2026-07-27T01:20:42.528884+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQAN6YQTLD2WJ5Q6","created_at":"2026-07-27T01:20:42.528884+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQAN6YQT","created_at":"2026-07-27T01:20:42.528884+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/SQAN6YQTLD2WJ5Q6IJ3CATJU5Q","json":"https://pith.science/pith/SQAN6YQTLD2WJ5Q6IJ3CATJU5Q.json","graph_json":"https://pith.science/api/pith-number/SQAN6YQTLD2WJ5Q6IJ3CATJU5Q/graph.json","events_json":"https://pith.science/api/pith-number/SQAN6YQTLD2WJ5Q6IJ3CATJU5Q/events.json","paper":"https://pith.science/paper/SQAN6YQT"},"agent_actions":{"view_html":"https://pith.science/pith/SQAN6YQTLD2WJ5Q6IJ3CATJU5Q","download_json":"https://pith.science/pith/SQAN6YQTLD2WJ5Q6IJ3CATJU5Q.json","view_paper":"https://pith.science/paper/SQAN6YQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22000&json=true","fetch_graph":"https://pith.science/api/pith-number/SQAN6YQTLD2WJ5Q6IJ3CATJU5Q/graph.json","fetch_events":"https://pith.science/api/pith-number/SQAN6YQTLD2WJ5Q6IJ3CATJU5Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQAN6YQTLD2WJ5Q6IJ3CATJU5Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQAN6YQTLD2WJ5Q6IJ3CATJU5Q/action/storage_attestation","attest_author":"https://pith.science/pith/SQAN6YQTLD2WJ5Q6IJ3CATJU5Q/action/author_attestation","sign_citation":"https://pith.science/pith/SQAN6YQTLD2WJ5Q6IJ3CATJU5Q/action/citation_signature","submit_replication":"https://pith.science/pith/SQAN6YQTLD2WJ5Q6IJ3CATJU5Q/action/replication_record"}},"created_at":"2026-07-27T01:20:42.528884+00:00","updated_at":"2026-07-27T01:20:42.528884+00:00"}