{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CGL6YBG6NGXCHJGIOANGIK3KRR","short_pith_number":"pith:CGL6YBG6","canonical_record":{"source":{"id":"2301.11325","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-01-26T18:58:53Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"7c2475d75710d25a5c73f03e7d699808c15e975ce512e968c08b9d033fe34d11","abstract_canon_sha256":"0844c77bf8bfe220e9199d9d7000971c73d84e2b497b29348a69d9f0158b88ae"},"schema_version":"1.0"},"canonical_sha256":"1197ec04de69ae23a4c8701a642b6a8c660665412656c190eabf62162f8e7222","source":{"kind":"arxiv","id":"2301.11325","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.11325","created_at":"2026-07-05T05:36:12Z"},{"alias_kind":"arxiv_version","alias_value":"2301.11325v1","created_at":"2026-07-05T05:36:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11325","created_at":"2026-07-05T05:36:12Z"},{"alias_kind":"pith_short_12","alias_value":"CGL6YBG6NGXC","created_at":"2026-07-05T05:36:12Z"},{"alias_kind":"pith_short_16","alias_value":"CGL6YBG6NGXCHJGI","created_at":"2026-07-05T05:36:12Z"},{"alias_kind":"pith_short_8","alias_value":"CGL6YBG6","created_at":"2026-07-05T05:36:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CGL6YBG6NGXCHJGIOANGIK3KRR","target":"record","payload":{"canonical_record":{"source":{"id":"2301.11325","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-01-26T18:58:53Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"7c2475d75710d25a5c73f03e7d699808c15e975ce512e968c08b9d033fe34d11","abstract_canon_sha256":"0844c77bf8bfe220e9199d9d7000971c73d84e2b497b29348a69d9f0158b88ae"},"schema_version":"1.0"},"canonical_sha256":"1197ec04de69ae23a4c8701a642b6a8c660665412656c190eabf62162f8e7222","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:12.722624Z","signature_b64":"Xj+LBL+KTqc3U0VJrOo6hU25FzFLt2XIGyGaCFuLGUK6iYs+cHU5pauf5AEju/Yv76H+ui/rUZPCAj85pYZyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1197ec04de69ae23a4c8701a642b6a8c660665412656c190eabf62162f8e7222","last_reissued_at":"2026-07-05T05:36:12.722208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:12.722208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.11325","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":"2026-07-05T05:36:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tYGwkvI/HtInNjXFLyZyyQyuJ/IZSlH1Xw1tHh/ttZuuuwzGxNqnDRDSy2zBOG3ncKBfWwX/B1g0rSigEIjDBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:32:24.376162Z"},"content_sha256":"e0ce2be7bd44829f19e5e531412748de087c4a94565bb2eb3fa3cb3e4368bbd3","schema_version":"1.0","event_id":"sha256:e0ce2be7bd44829f19e5e531412748de087c4a94565bb2eb3fa3cb3e4368bbd3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CGL6YBG6NGXCHJGIOANGIK3KRR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MusicLM: Generating Music From Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MusicLM generates high-fidelity 24 kHz music from text that stays consistent for several minutes by using hierarchical sequence modeling.","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Adam Roberts, Andrea Agostinelli, Antoine Caillon, Aren Jansen, Christian Frank, Jesse Engel, Marco Tagliasacchi, Matt Sharifi, Mauro Verzetti, Neil Zeghidour, Qingqing Huang, Timo I. Denk, Zal\\'an Borsos","submitted_at":"2023-01-26T18:58:53Z","abstract_excerpt":"We introduce MusicLM, a model generating high-fidelity music from text descriptions such as \"a calming violin melody backed by a distorted guitar riff\". MusicLM casts the process of conditional music generation as a hierarchical sequence-to-sequence modeling task, and it generates music at 24 kHz that remains consistent over several minutes. Our experiments show that MusicLM outperforms previous systems both in audio quality and adherence to the text description. Moreover, we demonstrate that MusicLM can be conditioned on both text and a melody in that it can transform whistled and hummed melo"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MusicLM outperforms previous systems both in audio quality and adherence to the text description while generating 24 kHz music that remains consistent over several minutes.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The hierarchical sequence-to-sequence modeling will continue to produce coherent long-form output when scaled beyond the training distribution of MusicCaps captions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MusicLM produces coherent multi-minute 24 kHz music from text prompts using hierarchical sequence-to-sequence modeling and outperforms prior systems in quality and text adherence.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MusicLM generates high-fidelity 24 kHz music from text that stays consistent for several minutes by using hierarchical sequence modeling.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9680d669e877542ed763b156d6c931d7b078f6c80e489bcebf5fd558f049a6c1"},"source":{"id":"2301.11325","kind":"arxiv","version":1},"verdict":{"id":"171ef051-669c-4e59-9767-9bbb09ad8927","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T14:23:19.958361Z","strongest_claim":"MusicLM outperforms previous systems both in audio quality and adherence to the text description while generating 24 kHz music that remains consistent over several minutes.","one_line_summary":"MusicLM produces coherent multi-minute 24 kHz music from text prompts using hierarchical sequence-to-sequence modeling and outperforms prior systems in quality and text adherence.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The hierarchical sequence-to-sequence modeling will continue to produce coherent long-form output when scaled beyond the training distribution of MusicCaps captions.","pith_extraction_headline":"MusicLM generates high-fidelity 24 kHz music from text that stays consistent for several minutes by using hierarchical sequence modeling."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2301.11325/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":16,"sample":[{"doi":"","year":null,"title":"YouTube-8M: A Large-Scale Video Classification Benchmark","work_id":"6b543bd8-75e8-4c53-9718-b4545e4bc424","ref_index":1,"cited_arxiv_id":"1609.08675","is_internal_anchor":false},{"doi":"","year":null,"title":"Audiolm: a language modeling approach to audio generation","work_id":"3a2aea1c-8117-4436-9100-0536aea3cf47","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2012,"title":"Brown, Dawn Song, Úlfar Er- lingsson, Alina Oprea, and Colin Raffel","work_id":"25b490c3-532b-40ec-b8ce-05fef84201d4","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Quantifying Memorization Across Neural Language Models","work_id":"35487ec1-b90b-4ace-95bd-1bce30064b2e","ref_index":4,"cited_arxiv_id":"2202.07646","is_internal_anchor":true},{"doi":"","year":null,"title":"LaMDA: Language Models for Dialog Applications","work_id":"1b66d0a5-f6ae-4332-8025-c662dc64b238","ref_index":5,"cited_arxiv_id":"2201.08239","is_internal_anchor":true}],"resolved_work":16,"snapshot_sha256":"3ed90c95953ecd7570ca56d4481f918dbd14a9ad8fccbec3ca9e0ad5665d6d56","internal_anchors":8},"formal_canon":{"evidence_count":1,"snapshot_sha256":"4ec12bd69cafa679d5687d74eb5191576824f51058ddd157259db6d6342cf4e1"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"171ef051-669c-4e59-9767-9bbb09ad8927"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:36:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4t6fKQkxf/bzW40vV8w6nUyWKfWNP/d2RwI7tQ/kJ9e4dztdyj6DK5tmeC09rrscFTl5H3qIM8TqawdJwYUUBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:32:24.376979Z"},"content_sha256":"efc0b9328c3457f0b40f690ab1cb71f787a38558d5108bf9dfdb5bf6c70c52c0","schema_version":"1.0","event_id":"sha256:efc0b9328c3457f0b40f690ab1cb71f787a38558d5108bf9dfdb5bf6c70c52c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CGL6YBG6NGXCHJGIOANGIK3KRR/bundle.json","state_url":"https://pith.science/pith/CGL6YBG6NGXCHJGIOANGIK3KRR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CGL6YBG6NGXCHJGIOANGIK3KRR/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":"2026-08-18T15:32:24Z","links":{"resolver":"https://pith.science/pith/CGL6YBG6NGXCHJGIOANGIK3KRR","bundle":"https://pith.science/pith/CGL6YBG6NGXCHJGIOANGIK3KRR/bundle.json","state":"https://pith.science/pith/CGL6YBG6NGXCHJGIOANGIK3KRR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CGL6YBG6NGXCHJGIOANGIK3KRR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CGL6YBG6NGXCHJGIOANGIK3KRR","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":"0844c77bf8bfe220e9199d9d7000971c73d84e2b497b29348a69d9f0158b88ae","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-01-26T18:58:53Z","title_canon_sha256":"7c2475d75710d25a5c73f03e7d699808c15e975ce512e968c08b9d033fe34d11"},"schema_version":"1.0","source":{"id":"2301.11325","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.11325","created_at":"2026-07-05T05:36:12Z"},{"alias_kind":"arxiv_version","alias_value":"2301.11325v1","created_at":"2026-07-05T05:36:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11325","created_at":"2026-07-05T05:36:12Z"},{"alias_kind":"pith_short_12","alias_value":"CGL6YBG6NGXC","created_at":"2026-07-05T05:36:12Z"},{"alias_kind":"pith_short_16","alias_value":"CGL6YBG6NGXCHJGI","created_at":"2026-07-05T05:36:12Z"},{"alias_kind":"pith_short_8","alias_value":"CGL6YBG6","created_at":"2026-07-05T05:36:12Z"}],"graph_snapshots":[{"event_id":"sha256:efc0b9328c3457f0b40f690ab1cb71f787a38558d5108bf9dfdb5bf6c70c52c0","target":"graph","created_at":"2026-07-05T05:36:12Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"MusicLM outperforms previous systems both in audio quality and adherence to the text description while generating 24 kHz music that remains consistent over several minutes."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The hierarchical sequence-to-sequence modeling will continue to produce coherent long-form output when scaled beyond the training distribution of MusicCaps captions."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MusicLM produces coherent multi-minute 24 kHz music from text prompts using hierarchical sequence-to-sequence modeling and outperforms prior systems in quality and text adherence."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MusicLM generates high-fidelity 24 kHz music from text that stays consistent for several minutes by using hierarchical sequence modeling."}],"snapshot_sha256":"9680d669e877542ed763b156d6c931d7b078f6c80e489bcebf5fd558f049a6c1"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"4ec12bd69cafa679d5687d74eb5191576824f51058ddd157259db6d6342cf4e1"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2301.11325/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce MusicLM, a model generating high-fidelity music from text descriptions such as \"a calming violin melody backed by a distorted guitar riff\". MusicLM casts the process of conditional music generation as a hierarchical sequence-to-sequence modeling task, and it generates music at 24 kHz that remains consistent over several minutes. Our experiments show that MusicLM outperforms previous systems both in audio quality and adherence to the text description. Moreover, we demonstrate that MusicLM can be conditioned on both text and a melody in that it can transform whistled and hummed melo","authors_text":"Adam Roberts, Andrea Agostinelli, Antoine Caillon, Aren Jansen, Christian Frank, Jesse Engel, Marco Tagliasacchi, Matt Sharifi, Mauro Verzetti, Neil Zeghidour, Qingqing Huang, Timo I. Denk, Zal\\'an Borsos","cross_cats":["cs.LG","eess.AS"],"headline":"MusicLM generates high-fidelity 24 kHz music from text that stays consistent for several minutes by using hierarchical sequence modeling.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-01-26T18:58:53Z","title":"MusicLM: Generating Music From Text"},"references":{"count":16,"internal_anchors":8,"resolved_work":16,"sample":[{"cited_arxiv_id":"1609.08675","doi":"","is_internal_anchor":false,"ref_index":1,"title":"YouTube-8M: A Large-Scale Video Classification Benchmark","work_id":"6b543bd8-75e8-4c53-9718-b4545e4bc424","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Audiolm: a language modeling approach to audio generation","work_id":"3a2aea1c-8117-4436-9100-0536aea3cf47","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Brown, Dawn Song, Úlfar Er- lingsson, Alina Oprea, and Colin Raffel","work_id":"25b490c3-532b-40ec-b8ce-05fef84201d4","year":2012},{"cited_arxiv_id":"2202.07646","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Quantifying Memorization Across Neural Language Models","work_id":"35487ec1-b90b-4ace-95bd-1bce30064b2e","year":null},{"cited_arxiv_id":"2201.08239","doi":"","is_internal_anchor":true,"ref_index":5,"title":"LaMDA: Language Models for Dialog Applications","work_id":"1b66d0a5-f6ae-4332-8025-c662dc64b238","year":null}],"snapshot_sha256":"3ed90c95953ecd7570ca56d4481f918dbd14a9ad8fccbec3ca9e0ad5665d6d56"},"source":{"id":"2301.11325","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-13T14:23:19.958361Z","id":"171ef051-669c-4e59-9767-9bbb09ad8927","model_set":{"reader":"grok-4.3"},"one_line_summary":"MusicLM produces coherent multi-minute 24 kHz music from text prompts using hierarchical sequence-to-sequence modeling and outperforms prior systems in quality and text adherence.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MusicLM generates high-fidelity 24 kHz music from text that stays consistent for several minutes by using hierarchical sequence modeling.","strongest_claim":"MusicLM outperforms previous systems both in audio quality and adherence to the text description while generating 24 kHz music that remains consistent over several minutes.","weakest_assumption":"The hierarchical sequence-to-sequence modeling will continue to produce coherent long-form output when scaled beyond the training distribution of MusicCaps captions."}},"verdict_id":"171ef051-669c-4e59-9767-9bbb09ad8927"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e0ce2be7bd44829f19e5e531412748de087c4a94565bb2eb3fa3cb3e4368bbd3","target":"record","created_at":"2026-07-05T05:36:12Z","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":"0844c77bf8bfe220e9199d9d7000971c73d84e2b497b29348a69d9f0158b88ae","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-01-26T18:58:53Z","title_canon_sha256":"7c2475d75710d25a5c73f03e7d699808c15e975ce512e968c08b9d033fe34d11"},"schema_version":"1.0","source":{"id":"2301.11325","kind":"arxiv","version":1}},"canonical_sha256":"1197ec04de69ae23a4c8701a642b6a8c660665412656c190eabf62162f8e7222","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1197ec04de69ae23a4c8701a642b6a8c660665412656c190eabf62162f8e7222","first_computed_at":"2026-07-05T05:36:12.722208Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:36:12.722208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xj+LBL+KTqc3U0VJrOo6hU25FzFLt2XIGyGaCFuLGUK6iYs+cHU5pauf5AEju/Yv76H+ui/rUZPCAj85pYZyAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:36:12.722624Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.11325","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0ce2be7bd44829f19e5e531412748de087c4a94565bb2eb3fa3cb3e4368bbd3","sha256:efc0b9328c3457f0b40f690ab1cb71f787a38558d5108bf9dfdb5bf6c70c52c0"],"state_sha256":"69a23aaed535278c60d6187308bd1c5cfa91afb766ceb722d14d33dfa0895441"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jFtwSuzwVUkv4AJ/zo6cRPfidiE2sQY5Iy7PGnYjImyMVr1XZfjQlrIdGr17ayO67VN4IW0gWAGCxk3/U+JyDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T15:32:24.382661Z","bundle_sha256":"7705f408845cf56e18228f6f111ea1248a40eec5929ec34a26677b2b4c6b435c"}}