{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5JXGLVLTETDTY7JWJ4BGQY4JKJ","short_pith_number":"pith:5JXGLVLT","canonical_record":{"source":{"id":"2312.08723","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-14T08:09:20Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"edff86845f1c4b2220acad700cd27251654a35c6c7cba7fac5de4c4d14b53242","abstract_canon_sha256":"afc438393a86f36314170bd5e9ed56cc9f55c0384455b209ad447b3d4f97d69e"},"schema_version":"1.0"},"canonical_sha256":"ea6e65d57324c73c7d364f0268638952503c837cb8abfa18040f0ae8e8538bcf","source":{"kind":"arxiv","id":"2312.08723","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08723","created_at":"2026-07-05T07:33:59Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08723v2","created_at":"2026-07-05T07:33:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08723","created_at":"2026-07-05T07:33:59Z"},{"alias_kind":"pith_short_12","alias_value":"5JXGLVLTETDT","created_at":"2026-07-05T07:33:59Z"},{"alias_kind":"pith_short_16","alias_value":"5JXGLVLTETDTY7JW","created_at":"2026-07-05T07:33:59Z"},{"alias_kind":"pith_short_8","alias_value":"5JXGLVLT","created_at":"2026-07-05T07:33:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5JXGLVLTETDTY7JWJ4BGQY4JKJ","target":"record","payload":{"canonical_record":{"source":{"id":"2312.08723","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-14T08:09:20Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"edff86845f1c4b2220acad700cd27251654a35c6c7cba7fac5de4c4d14b53242","abstract_canon_sha256":"afc438393a86f36314170bd5e9ed56cc9f55c0384455b209ad447b3d4f97d69e"},"schema_version":"1.0"},"canonical_sha256":"ea6e65d57324c73c7d364f0268638952503c837cb8abfa18040f0ae8e8538bcf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:59.321842Z","signature_b64":"apNKrXfa+Vt+LUMyBVtB71CjW3JAjHtbvRNVtm99rBdQ7mWtY8jk3K07xbQAMCJ1crcDcGxLUvgII5Qwfb8sBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea6e65d57324c73c7d364f0268638952503c837cb8abfa18040f0ae8e8538bcf","last_reissued_at":"2026-07-05T07:33:59.321358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:59.321358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.08723","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:33:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TBfmbc5DRYt4fC009D/5vtreZ+Ahx++yAGwst/ngUR7LnxZEK4yetmHM5LXdjpJOOiUYi+WlUFA9iZfmzFR/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T22:08:48.288745Z"},"content_sha256":"fc130a596a69552aee71af4e585517a8e22bdad92211c5f49e3a821bede604b2","schema_version":"1.0","event_id":"sha256:fc130a596a69552aee71af4e585517a8e22bdad92211c5f49e3a821bede604b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5JXGLVLTETDTY7JWJ4BGQY4JKJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StemGen: A music generation model that listens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Boris Kuznetsov, Duc Le, Furkan Yesiler, Janne Spijkervet, Jitong Chen, Ju-Chiang Wang, Julian D. Parker, Katerina Kosta, Matt Avent","submitted_at":"2023-12-14T08:09:20Z","abstract_excerpt":"End-to-end generation of musical audio using deep learning techniques has seen an explosion of activity recently. However, most models concentrate on generating fully mixed music in response to abstract conditioning information. In this work, we present an alternative paradigm for producing music generation models that can listen and respond to musical context. We describe how such a model can be constructed using a non-autoregressive, transformer-based model architecture and present a number of novel architectural and sampling improvements. We train the described architecture on both an open-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08723","kind":"arxiv","version":2},"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/2312.08723/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:33:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XdkgWoWj+tMfwzPJB5o9yrl7PnxvHjjeIKds+rhH8yPQa3PQ48TmWlf8OkUCB1RRYT1xmnyQmSXA7Rylo5baDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T22:08:48.290212Z"},"content_sha256":"e9ef35a007a0d22e2682288075a2e732f34b09dbdc1b255054223dd30bb64611","schema_version":"1.0","event_id":"sha256:e9ef35a007a0d22e2682288075a2e732f34b09dbdc1b255054223dd30bb64611"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5JXGLVLTETDTY7JWJ4BGQY4JKJ/bundle.json","state_url":"https://pith.science/pith/5JXGLVLTETDTY7JWJ4BGQY4JKJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5JXGLVLTETDTY7JWJ4BGQY4JKJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-13T22:08:48Z","links":{"resolver":"https://pith.science/pith/5JXGLVLTETDTY7JWJ4BGQY4JKJ","bundle":"https://pith.science/pith/5JXGLVLTETDTY7JWJ4BGQY4JKJ/bundle.json","state":"https://pith.science/pith/5JXGLVLTETDTY7JWJ4BGQY4JKJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5JXGLVLTETDTY7JWJ4BGQY4JKJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5JXGLVLTETDTY7JWJ4BGQY4JKJ","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":"afc438393a86f36314170bd5e9ed56cc9f55c0384455b209ad447b3d4f97d69e","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-14T08:09:20Z","title_canon_sha256":"edff86845f1c4b2220acad700cd27251654a35c6c7cba7fac5de4c4d14b53242"},"schema_version":"1.0","source":{"id":"2312.08723","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08723","created_at":"2026-07-05T07:33:59Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08723v2","created_at":"2026-07-05T07:33:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08723","created_at":"2026-07-05T07:33:59Z"},{"alias_kind":"pith_short_12","alias_value":"5JXGLVLTETDT","created_at":"2026-07-05T07:33:59Z"},{"alias_kind":"pith_short_16","alias_value":"5JXGLVLTETDTY7JW","created_at":"2026-07-05T07:33:59Z"},{"alias_kind":"pith_short_8","alias_value":"5JXGLVLT","created_at":"2026-07-05T07:33:59Z"}],"graph_snapshots":[{"event_id":"sha256:e9ef35a007a0d22e2682288075a2e732f34b09dbdc1b255054223dd30bb64611","target":"graph","created_at":"2026-07-05T07:33:59Z","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/2312.08723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end generation of musical audio using deep learning techniques has seen an explosion of activity recently. However, most models concentrate on generating fully mixed music in response to abstract conditioning information. In this work, we present an alternative paradigm for producing music generation models that can listen and respond to musical context. We describe how such a model can be constructed using a non-autoregressive, transformer-based model architecture and present a number of novel architectural and sampling improvements. We train the described architecture on both an open-","authors_text":"Boris Kuznetsov, Duc Le, Furkan Yesiler, Janne Spijkervet, Jitong Chen, Ju-Chiang Wang, Julian D. Parker, Katerina Kosta, Matt Avent","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-14T08:09:20Z","title":"StemGen: A music generation model that listens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08723","kind":"arxiv","version":2},"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:fc130a596a69552aee71af4e585517a8e22bdad92211c5f49e3a821bede604b2","target":"record","created_at":"2026-07-05T07:33:59Z","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":"afc438393a86f36314170bd5e9ed56cc9f55c0384455b209ad447b3d4f97d69e","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-14T08:09:20Z","title_canon_sha256":"edff86845f1c4b2220acad700cd27251654a35c6c7cba7fac5de4c4d14b53242"},"schema_version":"1.0","source":{"id":"2312.08723","kind":"arxiv","version":2}},"canonical_sha256":"ea6e65d57324c73c7d364f0268638952503c837cb8abfa18040f0ae8e8538bcf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea6e65d57324c73c7d364f0268638952503c837cb8abfa18040f0ae8e8538bcf","first_computed_at":"2026-07-05T07:33:59.321358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:33:59.321358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"apNKrXfa+Vt+LUMyBVtB71CjW3JAjHtbvRNVtm99rBdQ7mWtY8jk3K07xbQAMCJ1crcDcGxLUvgII5Qwfb8sBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:33:59.321842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.08723","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc130a596a69552aee71af4e585517a8e22bdad92211c5f49e3a821bede604b2","sha256:e9ef35a007a0d22e2682288075a2e732f34b09dbdc1b255054223dd30bb64611"],"state_sha256":"aa1931f720b986a19a1939c8a48133150c00d60d5ad80323112707d4ef6282f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S5d61BWD5u5bhvSguQeeucDN6Yc4VpzNm3XwxjZF8RInMHoQIFUuCZX57aNqS+JcKRvf/s8ywPAP/hdBhRTsAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T22:08:48.301341Z","bundle_sha256":"c8692c73e8e96f839d3c4f31a5aa5a746a355e336beeeaf8b90cd3a88818d3be"}}