{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:46IE6STPY3MTZ7PHKRAVZDNUMZ","short_pith_number":"pith:46IE6STP","schema_version":"1.0","canonical_sha256":"e7904f4a6fc6d93cfde754415c8db46659527807018f02f0e2689eec5a1ddee0","source":{"kind":"arxiv","id":"2408.02514","version":1},"attestation_state":"computed","paper":{"title":"Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alain Riou, Ga\\\"etan Hadjeres, Geoffroy Peeters, Michael Anslow, Stefan Lattner","submitted_at":"2024-08-05T14:34:40Z","abstract_excerpt":"This paper explores the automated process of determining stem compatibility by identifying audio recordings of single instruments that blend well with a given musical context. To tackle this challenge, we present Stem-JEPA, a novel Joint-Embedding Predictive Architecture (JEPA) trained on a multi-track dataset using a self-supervised learning approach.\n  Our model comprises two networks: an encoder and a predictor, which are jointly trained to predict the embeddings of compatible stems from the embeddings of a given context, typically a mix of several instruments. Training a model in this mann"},"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":"2408.02514","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-05T14:34:40Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"a26966256a2bfb330edf5459f783a734b6dd02bfa227ffedcb0339f39f7ca495","abstract_canon_sha256":"124b52c5989ee3f6dc1287826b89f1471843d36e3e8b8ba6115116ffc0f379e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:13.865437Z","signature_b64":"ByRMVqq5oE9fd1/jvdPD2b6i5ZasAKym9vAK5ADuZe6iMqqs+z+IzuVlDyjYJj2RKks7BohQIOWeNDDTkqjzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7904f4a6fc6d93cfde754415c8db46659527807018f02f0e2689eec5a1ddee0","last_reissued_at":"2026-07-05T08:52:13.864904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:13.864904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alain Riou, Ga\\\"etan Hadjeres, Geoffroy Peeters, Michael Anslow, Stefan Lattner","submitted_at":"2024-08-05T14:34:40Z","abstract_excerpt":"This paper explores the automated process of determining stem compatibility by identifying audio recordings of single instruments that blend well with a given musical context. To tackle this challenge, we present Stem-JEPA, a novel Joint-Embedding Predictive Architecture (JEPA) trained on a multi-track dataset using a self-supervised learning approach.\n  Our model comprises two networks: an encoder and a predictor, which are jointly trained to predict the embeddings of compatible stems from the embeddings of a given context, typically a mix of several instruments. Training a model in this mann"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02514","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/2408.02514/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":"2408.02514","created_at":"2026-07-05T08:52:13.864961+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02514v1","created_at":"2026-07-05T08:52:13.864961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02514","created_at":"2026-07-05T08:52:13.864961+00:00"},{"alias_kind":"pith_short_12","alias_value":"46IE6STPY3MT","created_at":"2026-07-05T08:52:13.864961+00:00"},{"alias_kind":"pith_short_16","alias_value":"46IE6STPY3MTZ7PH","created_at":"2026-07-05T08:52:13.864961+00:00"},{"alias_kind":"pith_short_8","alias_value":"46IE6STP","created_at":"2026-07-05T08:52:13.864961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02915","citing_title":"Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/46IE6STPY3MTZ7PHKRAVZDNUMZ","json":"https://pith.science/pith/46IE6STPY3MTZ7PHKRAVZDNUMZ.json","graph_json":"https://pith.science/api/pith-number/46IE6STPY3MTZ7PHKRAVZDNUMZ/graph.json","events_json":"https://pith.science/api/pith-number/46IE6STPY3MTZ7PHKRAVZDNUMZ/events.json","paper":"https://pith.science/paper/46IE6STP"},"agent_actions":{"view_html":"https://pith.science/pith/46IE6STPY3MTZ7PHKRAVZDNUMZ","download_json":"https://pith.science/pith/46IE6STPY3MTZ7PHKRAVZDNUMZ.json","view_paper":"https://pith.science/paper/46IE6STP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02514&json=true","fetch_graph":"https://pith.science/api/pith-number/46IE6STPY3MTZ7PHKRAVZDNUMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/46IE6STPY3MTZ7PHKRAVZDNUMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46IE6STPY3MTZ7PHKRAVZDNUMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46IE6STPY3MTZ7PHKRAVZDNUMZ/action/storage_attestation","attest_author":"https://pith.science/pith/46IE6STPY3MTZ7PHKRAVZDNUMZ/action/author_attestation","sign_citation":"https://pith.science/pith/46IE6STPY3MTZ7PHKRAVZDNUMZ/action/citation_signature","submit_replication":"https://pith.science/pith/46IE6STPY3MTZ7PHKRAVZDNUMZ/action/replication_record"}},"created_at":"2026-07-05T08:52:13.864961+00:00","updated_at":"2026-07-05T08:52:13.864961+00:00"}