{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VR23ILULWJIPBGP7OY2R4RGZJ7","short_pith_number":"pith:VR23ILUL","canonical_record":{"source":{"id":"2605.21433","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-20T17:23:58Z","cross_cats_sorted":[],"title_canon_sha256":"5051cbc42262984f8d6f1cb4a7dcbacde5866f4aadc282a14502631bfa83419a","abstract_canon_sha256":"46657ab6bcd462a789065e22c28e552ab24cbaec625e53c66a514ae39836e469"},"schema_version":"1.0"},"canonical_sha256":"ac75b42e8bb250f099ff76351e44d94fcf2803668e9ffbd67485ebc58e6269d6","source":{"kind":"arxiv","id":"2605.21433","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21433","created_at":"2026-05-21T02:05:34Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21433v1","created_at":"2026-05-21T02:05:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21433","created_at":"2026-05-21T02:05:34Z"},{"alias_kind":"pith_short_12","alias_value":"VR23ILULWJIP","created_at":"2026-05-21T02:05:34Z"},{"alias_kind":"pith_short_16","alias_value":"VR23ILULWJIPBGP7","created_at":"2026-05-21T02:05:34Z"},{"alias_kind":"pith_short_8","alias_value":"VR23ILUL","created_at":"2026-05-21T02:05:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VR23ILULWJIPBGP7OY2R4RGZJ7","target":"record","payload":{"canonical_record":{"source":{"id":"2605.21433","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-20T17:23:58Z","cross_cats_sorted":[],"title_canon_sha256":"5051cbc42262984f8d6f1cb4a7dcbacde5866f4aadc282a14502631bfa83419a","abstract_canon_sha256":"46657ab6bcd462a789065e22c28e552ab24cbaec625e53c66a514ae39836e469"},"schema_version":"1.0"},"canonical_sha256":"ac75b42e8bb250f099ff76351e44d94fcf2803668e9ffbd67485ebc58e6269d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:34.529679Z","signature_b64":"XcJOntqNYtV1vuAtliEebEE36Y1c5bkp6JRtGKW6qQjRmwjO/b+dNhWCVz4p16XJ2xrgl2OuSvWdPhlARI8KCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac75b42e8bb250f099ff76351e44d94fcf2803668e9ffbd67485ebc58e6269d6","last_reissued_at":"2026-05-21T02:05:34.529040Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:34.529040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.21433","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T02:05:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Kfzyzff9QOazVuVofgoDekjSGZr0nWXRGcM+eLAG4V5vo20cOzTPcbuDzzZOYuIULOL1qPPRQ4eZAq78/87Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:21:07.708821Z"},"content_sha256":"0bdb54dcfae4bd4cff5cd150ea8077bd96410ebffb26bd30e1d14b7ae8793fc7","schema_version":"1.0","event_id":"sha256:0bdb54dcfae4bd4cff5cd150ea8077bd96410ebffb26bd30e1d14b7ae8793fc7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VR23ILULWJIPBGP7OY2R4RGZJ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Instrumental Text-to-Music Generation with Auxiliary Conditioning Branches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Junyoung Koh","submitted_at":"2026-05-20T17:23:58Z","abstract_excerpt":"Text-to-music generation has advanced rapidly, with modern autoregressive and diffusion-based models producing convincing music from natural-language prompts. However, much of this progress relies on large-scale training data and external pretraining, making it difficult to isolate which design choices remain effective when data and pretraining are controlled. We study this setting using a Diffusion Transformer backbone with lyric and timbre conditioning, adapted to an instrumental-only text-to-music task in which the auxiliary lyric and timbre branches receive only degenerate conditioning sig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21433","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/2605.21433/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":"2026-05-21T02:05:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bwL7Ze1OEtBl2y9xzNmajmlOWyu3xyBMXObyH0SywcqjIJI/Y9w1IZ8gMLTW2cs+b6rmilnrfHo++GyfZZyVAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:21:07.709551Z"},"content_sha256":"6b60f51ec2a7a4915062af4e57c51ee05217c755ad9dbaf953adb7f884268c2b","schema_version":"1.0","event_id":"sha256:6b60f51ec2a7a4915062af4e57c51ee05217c755ad9dbaf953adb7f884268c2b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VR23ILULWJIPBGP7OY2R4RGZJ7/bundle.json","state_url":"https://pith.science/pith/VR23ILULWJIPBGP7OY2R4RGZJ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VR23ILULWJIPBGP7OY2R4RGZJ7/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":"2026-05-26T01:21:07Z","links":{"resolver":"https://pith.science/pith/VR23ILULWJIPBGP7OY2R4RGZJ7","bundle":"https://pith.science/pith/VR23ILULWJIPBGP7OY2R4RGZJ7/bundle.json","state":"https://pith.science/pith/VR23ILULWJIPBGP7OY2R4RGZJ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VR23ILULWJIPBGP7OY2R4RGZJ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VR23ILULWJIPBGP7OY2R4RGZJ7","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":"46657ab6bcd462a789065e22c28e552ab24cbaec625e53c66a514ae39836e469","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-20T17:23:58Z","title_canon_sha256":"5051cbc42262984f8d6f1cb4a7dcbacde5866f4aadc282a14502631bfa83419a"},"schema_version":"1.0","source":{"id":"2605.21433","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21433","created_at":"2026-05-21T02:05:34Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21433v1","created_at":"2026-05-21T02:05:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21433","created_at":"2026-05-21T02:05:34Z"},{"alias_kind":"pith_short_12","alias_value":"VR23ILULWJIP","created_at":"2026-05-21T02:05:34Z"},{"alias_kind":"pith_short_16","alias_value":"VR23ILULWJIPBGP7","created_at":"2026-05-21T02:05:34Z"},{"alias_kind":"pith_short_8","alias_value":"VR23ILUL","created_at":"2026-05-21T02:05:34Z"}],"graph_snapshots":[{"event_id":"sha256:6b60f51ec2a7a4915062af4e57c51ee05217c755ad9dbaf953adb7f884268c2b","target":"graph","created_at":"2026-05-21T02:05:34Z","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/2605.21433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-music generation has advanced rapidly, with modern autoregressive and diffusion-based models producing convincing music from natural-language prompts. However, much of this progress relies on large-scale training data and external pretraining, making it difficult to isolate which design choices remain effective when data and pretraining are controlled. We study this setting using a Diffusion Transformer backbone with lyric and timbre conditioning, adapted to an instrumental-only text-to-music task in which the auxiliary lyric and timbre branches receive only degenerate conditioning sig","authors_text":"Junyoung Koh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-20T17:23:58Z","title":"Instrumental Text-to-Music Generation with Auxiliary Conditioning Branches"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21433","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":"sha256:0bdb54dcfae4bd4cff5cd150ea8077bd96410ebffb26bd30e1d14b7ae8793fc7","target":"record","created_at":"2026-05-21T02:05:34Z","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":"46657ab6bcd462a789065e22c28e552ab24cbaec625e53c66a514ae39836e469","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-20T17:23:58Z","title_canon_sha256":"5051cbc42262984f8d6f1cb4a7dcbacde5866f4aadc282a14502631bfa83419a"},"schema_version":"1.0","source":{"id":"2605.21433","kind":"arxiv","version":1}},"canonical_sha256":"ac75b42e8bb250f099ff76351e44d94fcf2803668e9ffbd67485ebc58e6269d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac75b42e8bb250f099ff76351e44d94fcf2803668e9ffbd67485ebc58e6269d6","first_computed_at":"2026-05-21T02:05:34.529040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T02:05:34.529040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XcJOntqNYtV1vuAtliEebEE36Y1c5bkp6JRtGKW6qQjRmwjO/b+dNhWCVz4p16XJ2xrgl2OuSvWdPhlARI8KCA==","signature_status":"signed_v1","signed_at":"2026-05-21T02:05:34.529679Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21433","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bdb54dcfae4bd4cff5cd150ea8077bd96410ebffb26bd30e1d14b7ae8793fc7","sha256:6b60f51ec2a7a4915062af4e57c51ee05217c755ad9dbaf953adb7f884268c2b"],"state_sha256":"57cab1af56383ea7695bc0800bf5a9e2ce3d0e2f7de2b09ae016fc391a58add9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qw3dNZmBhf8LV2/CXZIlEx7vbk+BGqs8Xoz2Niuqg6da0bWfTdbYzskUm+IHRXE/LnZbDu2NQGQJ7bJZtBSRCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T01:21:07.713470Z","bundle_sha256":"53845390deb0e723af703ca3d8d4a72448f76dc568fb0994b41f36839c6eb839"}}