{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:C5U7Q2NXSADYKNZ37J4SFNG66V","short_pith_number":"pith:C5U7Q2NX","canonical_record":{"source":{"id":"2502.08939","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-13T03:40:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8eb81445f32f2ec3713dccbbac5b9ff126ca86bc1d0f7c36a0561f9eb37e1cba","abstract_canon_sha256":"9bea2592e308c39f5e8edaf33ecf28b49ada3528fe593e07df2326a1c6b10010"},"schema_version":"1.0"},"canonical_sha256":"1769f869b7900785373bfa7922b4def542dae4cc3c92feae21911ff1b02d6d2d","source":{"kind":"arxiv","id":"2502.08939","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08939","created_at":"2026-07-05T10:13:50Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08939v1","created_at":"2026-07-05T10:13:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08939","created_at":"2026-07-05T10:13:50Z"},{"alias_kind":"pith_short_12","alias_value":"C5U7Q2NXSADY","created_at":"2026-07-05T10:13:50Z"},{"alias_kind":"pith_short_16","alias_value":"C5U7Q2NXSADYKNZ3","created_at":"2026-07-05T10:13:50Z"},{"alias_kind":"pith_short_8","alias_value":"C5U7Q2NX","created_at":"2026-07-05T10:13:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:C5U7Q2NXSADYKNZ37J4SFNG66V","target":"record","payload":{"canonical_record":{"source":{"id":"2502.08939","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-13T03:40:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8eb81445f32f2ec3713dccbbac5b9ff126ca86bc1d0f7c36a0561f9eb37e1cba","abstract_canon_sha256":"9bea2592e308c39f5e8edaf33ecf28b49ada3528fe593e07df2326a1c6b10010"},"schema_version":"1.0"},"canonical_sha256":"1769f869b7900785373bfa7922b4def542dae4cc3c92feae21911ff1b02d6d2d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:50.053430Z","signature_b64":"VXJk6hOpmBWR9vYxqpOAFUnF84SZKopeWu0y4IZPyPFvvnLVYJJGmg5QYNKBj0rnP2+qfmzyT89xDKM0GbjTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1769f869b7900785373bfa7922b4def542dae4cc3c92feae21911ff1b02d6d2d","last_reissued_at":"2026-07-05T10:13:50.052926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:50.052926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.08939","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":"2026-07-05T10:13:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vNJCZhFSUv2NR40irFT2rEL9n/KW10CkuWA9oIEStknTAMOfAKI63BKBTdBJr+BTqPCcWDZW2WS/RZEgxMUoDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:42:56.403035Z"},"content_sha256":"4a4f7b780678d670d9518fd0e3fa89bf0171847b53cdeab6fad11e41f9183195","schema_version":"1.0","event_id":"sha256:4a4f7b780678d670d9518fd0e3fa89bf0171847b53cdeab6fad11e41f9183195"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:C5U7Q2NXSADYKNZ37J4SFNG66V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TokenSynth: A Token-based Neural Synthesizer for Instrument Cloning and Text-to-Instrument","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Haesun Joung, Junghyun Koo, Kyogu Lee, Kyungsu Kim, Sungho Lee","submitted_at":"2025-02-13T03:40:30Z","abstract_excerpt":"Recent advancements in neural audio codecs have enabled the use of tokenized audio representations in various audio generation tasks, such as text-to-speech, text-to-audio, and text-to-music generation. Leveraging this approach, we propose TokenSynth, a novel neural synthesizer that utilizes a decoder-only transformer to generate desired audio tokens from MIDI tokens and CLAP (Contrastive Language-Audio Pretraining) embedding, which has timbre-related information. Our model is capable of performing instrument cloning, text-to-instrument synthesis, and text-guided timbre manipulation without an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08939","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/2502.08939/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":"2026-07-05T10:13:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3SlxwLMoFyKrViclqKWgJhp1+OYjZS/AxUBEVjuwZuvZiLALLVUegKPARWPLXzTbNHQQnIQRaE9Y9G34zG56BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T22:42:56.403586Z"},"content_sha256":"cd34449025e7dc15a63373264bde19f07e83ac830a344f9dbfb4ab9bc503b42f","schema_version":"1.0","event_id":"sha256:cd34449025e7dc15a63373264bde19f07e83ac830a344f9dbfb4ab9bc503b42f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C5U7Q2NXSADYKNZ37J4SFNG66V/bundle.json","state_url":"https://pith.science/pith/C5U7Q2NXSADYKNZ37J4SFNG66V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C5U7Q2NXSADYKNZ37J4SFNG66V/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":"2026-08-18T22:42:56Z","links":{"resolver":"https://pith.science/pith/C5U7Q2NXSADYKNZ37J4SFNG66V","bundle":"https://pith.science/pith/C5U7Q2NXSADYKNZ37J4SFNG66V/bundle.json","state":"https://pith.science/pith/C5U7Q2NXSADYKNZ37J4SFNG66V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C5U7Q2NXSADYKNZ37J4SFNG66V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C5U7Q2NXSADYKNZ37J4SFNG66V","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":"9bea2592e308c39f5e8edaf33ecf28b49ada3528fe593e07df2326a1c6b10010","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-13T03:40:30Z","title_canon_sha256":"8eb81445f32f2ec3713dccbbac5b9ff126ca86bc1d0f7c36a0561f9eb37e1cba"},"schema_version":"1.0","source":{"id":"2502.08939","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08939","created_at":"2026-07-05T10:13:50Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08939v1","created_at":"2026-07-05T10:13:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08939","created_at":"2026-07-05T10:13:50Z"},{"alias_kind":"pith_short_12","alias_value":"C5U7Q2NXSADY","created_at":"2026-07-05T10:13:50Z"},{"alias_kind":"pith_short_16","alias_value":"C5U7Q2NXSADYKNZ3","created_at":"2026-07-05T10:13:50Z"},{"alias_kind":"pith_short_8","alias_value":"C5U7Q2NX","created_at":"2026-07-05T10:13:50Z"}],"graph_snapshots":[{"event_id":"sha256:cd34449025e7dc15a63373264bde19f07e83ac830a344f9dbfb4ab9bc503b42f","target":"graph","created_at":"2026-07-05T10:13:50Z","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/2502.08939/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in neural audio codecs have enabled the use of tokenized audio representations in various audio generation tasks, such as text-to-speech, text-to-audio, and text-to-music generation. Leveraging this approach, we propose TokenSynth, a novel neural synthesizer that utilizes a decoder-only transformer to generate desired audio tokens from MIDI tokens and CLAP (Contrastive Language-Audio Pretraining) embedding, which has timbre-related information. Our model is capable of performing instrument cloning, text-to-instrument synthesis, and text-guided timbre manipulation without an","authors_text":"Haesun Joung, Junghyun Koo, Kyogu Lee, Kyungsu Kim, Sungho Lee","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-13T03:40:30Z","title":"TokenSynth: A Token-based Neural Synthesizer for Instrument Cloning and Text-to-Instrument"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08939","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":"sha256:4a4f7b780678d670d9518fd0e3fa89bf0171847b53cdeab6fad11e41f9183195","target":"record","created_at":"2026-07-05T10:13:50Z","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":"9bea2592e308c39f5e8edaf33ecf28b49ada3528fe593e07df2326a1c6b10010","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-13T03:40:30Z","title_canon_sha256":"8eb81445f32f2ec3713dccbbac5b9ff126ca86bc1d0f7c36a0561f9eb37e1cba"},"schema_version":"1.0","source":{"id":"2502.08939","kind":"arxiv","version":1}},"canonical_sha256":"1769f869b7900785373bfa7922b4def542dae4cc3c92feae21911ff1b02d6d2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1769f869b7900785373bfa7922b4def542dae4cc3c92feae21911ff1b02d6d2d","first_computed_at":"2026-07-05T10:13:50.052926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:50.052926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VXJk6hOpmBWR9vYxqpOAFUnF84SZKopeWu0y4IZPyPFvvnLVYJJGmg5QYNKBj0rnP2+qfmzyT89xDKM0GbjTBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:50.053430Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08939","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a4f7b780678d670d9518fd0e3fa89bf0171847b53cdeab6fad11e41f9183195","sha256:cd34449025e7dc15a63373264bde19f07e83ac830a344f9dbfb4ab9bc503b42f"],"state_sha256":"96dea49f5090c35edae104539cf66c69c04e4d2745e4daef3796b0f325848d75"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T6XxFvkPTTbTY9f2/q9AATDi/P8IDNhT68VpqaKCV0g1f5Ixid4//akXSD1Ofiif8wnSEvmF09XOSCHGIvKlDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T22:42:56.408701Z","bundle_sha256":"016632796be8f5ad4c52012bbbf0193669b4b1841c9090b1b604686235d9a6a7"}}