{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RFRSJ5YLLMIJLAMZFAPJE43BNM","short_pith_number":"pith:RFRSJ5YL","canonical_record":{"source":{"id":"2305.16355","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T04:16:07Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"bbbc8f4530482ee4a7ed90c8764467b8790d3a9d3a102881526d4cdb5d5655bd","abstract_canon_sha256":"a33eb1f75754eee664c50c5a05cfef2ea5b7c32e181ab55bcafee2f43fdb58d5"},"schema_version":"1.0"},"canonical_sha256":"896324f70b5b10958199281e9273616b3b1c9cba067746a5a493e96d395ec151","source":{"kind":"arxiv","id":"2305.16355","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16355","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16355v1","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16355","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"RFRSJ5YLLMIJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"RFRSJ5YLLMIJLAMZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"RFRSJ5YL","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RFRSJ5YLLMIJLAMZFAPJE43BNM","target":"record","payload":{"canonical_record":{"source":{"id":"2305.16355","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T04:16:07Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"bbbc8f4530482ee4a7ed90c8764467b8790d3a9d3a102881526d4cdb5d5655bd","abstract_canon_sha256":"a33eb1f75754eee664c50c5a05cfef2ea5b7c32e181ab55bcafee2f43fdb58d5"},"schema_version":"1.0"},"canonical_sha256":"896324f70b5b10958199281e9273616b3b1c9cba067746a5a493e96d395ec151","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:48.430747Z","signature_b64":"B/QM9uBoWogcXjnkmqhnXlQoQ3sxDA9hnLvh1Ust1Pyu1jRxeScz2UZLFfxOAU+CMA8FEljZD6rUdRtT+IO2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"896324f70b5b10958199281e9273616b3b1c9cba067746a5a493e96d395ec151","last_reissued_at":"2026-05-17T23:38:48.430132Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:48.430132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.16355","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":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jmo2A4GHz+6ohFEv61G+ZCFnxC3h9O7ZS8dKNMYkS3lLbDs3euO1yE5bMopS6tnsG3yCsIY07EVLqpdmYLj6Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T17:55:19.190393Z"},"content_sha256":"13145015a63ccb514df9877c9e9ec51db9bc78e85e429dd8030630398b3549ec","schema_version":"1.0","event_id":"sha256:13145015a63ccb514df9877c9e9ec51db9bc78e85e429dd8030630398b3549ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RFRSJ5YLLMIJLAMZFAPJE43BNM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PandaGPT: One Model To Instruction-Follow Them All","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A single model trained only on image-text pairs can follow instructions on video, audio, depth, and thermal inputs by composing their meanings in a shared embedding space.","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Deng Cai, Huayang Li, Jialu Xu, Tian Lan, Yan Wang, Yixuan Su","submitted_at":"2023-05-25T04:16:07Z","abstract_excerpt":"We present PandaGPT, an approach to emPower large lANguage moDels with visual and Auditory instruction-following capabilities. Our pilot experiments show that PandaGPT can perform complex tasks such as detailed image description generation, writing stories inspired by videos, and answering questions about audios. More interestingly, PandaGPT can take multimodal inputs simultaneously and compose their semantics naturally. For example, PandaGPT can connect how objects look in an image/video and how they sound in an audio. To do so, PandaGPT combines the multimodal encoders from ImageBind and the"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"PandaGPT displays emergent, i.e. zero-shot, cross-modal behaviors for data other than image and text (e.g., video, audio, depth, thermal, and IMU) and can take multimodal inputs simultaneously and compose their semantics naturally.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That ImageBind's embedding space is already semantically rich enough for the language model to compose meanings across modalities without any further alignment training on those modalities.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A single model trained only on image-text pairs gains instruction-following ability across images, video, and audio by routing all modalities through ImageBind's shared embedding space into Vicuna.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A single model trained only on image-text pairs can follow instructions on video, audio, depth, and thermal inputs by composing their meanings in a shared embedding space.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"925da561fe9ffe37f1187f7250a02b718a7486712ccb9d1f1189f9c333c3bc4e"},"source":{"id":"2305.16355","kind":"arxiv","version":1},"verdict":{"id":"5e0eb80b-0917-4302-b4b4-90bbb09d44c1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T08:58:06.902090Z","strongest_claim":"PandaGPT displays emergent, i.e. zero-shot, cross-modal behaviors for data other than image and text (e.g., video, audio, depth, thermal, and IMU) and can take multimodal inputs simultaneously and compose their semantics naturally.","one_line_summary":"A single model trained only on image-text pairs gains instruction-following ability across images, video, and audio by routing all modalities through ImageBind's shared embedding space into Vicuna.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That ImageBind's embedding space is already semantically rich enough for the language model to compose meanings across modalities without any further alignment training on those modalities.","pith_extraction_headline":"A single model trained only on image-text pairs can follow instructions on video, audio, depth, and thermal inputs by composing their meanings in a shared embedding space."},"references":{"count":32,"sample":[{"doi":"","year":2022,"title":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. 2022. Flamingo: a visual language model","work_id":"99c9825d-d8aa-4d56-9301-b5cac88e2bb4","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Jean-Baptiste Alayrac, Adria Recasens, Rosalia Schneider, Relja Arandjelovi´c, Jason Rama- puram, Jeffrey De Fauw, Lucas Smaira, Sander Dieleman, and Andrew Zisserman. 2020. Self-supervised multimodal","work_id":"f80752c3-199b-4209-a52f-91a90fb91770","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot lear","work_id":"0ee6a9fc-348e-411b-945a-c5820c50b0b1","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Gonzalez, Ion Stoica, and Eric P","work_id":"eb89ea20-08e6-4a9e-9f97-6330cab3e994","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the N","work_id":"62467c4c-275a-48fb-a48c-2d95503573e0","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":32,"snapshot_sha256":"9348f680c6e4af2af79bde822d07cb39360040d5299e0413d722c64c593c6c5f","internal_anchors":8},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b65acc071b63869295fd48ec3472d576acaea9f112fd4298df924112f4d67867"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"5e0eb80b-0917-4302-b4b4-90bbb09d44c1"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HVjPIcZPf1/NO8xARGNweN1rK10jtsPFqMqCLYcfc+dqu1/NzizBzddODkWqTEIuxog5x9AksbKqdsgyw79aCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T17:55:19.190993Z"},"content_sha256":"6c8835162464772be5a4546aed6b22e2bee199cb266d87fca1b166befd835d4f","schema_version":"1.0","event_id":"sha256:6c8835162464772be5a4546aed6b22e2bee199cb266d87fca1b166befd835d4f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RFRSJ5YLLMIJLAMZFAPJE43BNM/bundle.json","state_url":"https://pith.science/pith/RFRSJ5YLLMIJLAMZFAPJE43BNM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RFRSJ5YLLMIJLAMZFAPJE43BNM/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":"2026-05-20T17:55:19Z","links":{"resolver":"https://pith.science/pith/RFRSJ5YLLMIJLAMZFAPJE43BNM","bundle":"https://pith.science/pith/RFRSJ5YLLMIJLAMZFAPJE43BNM/bundle.json","state":"https://pith.science/pith/RFRSJ5YLLMIJLAMZFAPJE43BNM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RFRSJ5YLLMIJLAMZFAPJE43BNM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RFRSJ5YLLMIJLAMZFAPJE43BNM","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":"a33eb1f75754eee664c50c5a05cfef2ea5b7c32e181ab55bcafee2f43fdb58d5","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T04:16:07Z","title_canon_sha256":"bbbc8f4530482ee4a7ed90c8764467b8790d3a9d3a102881526d4cdb5d5655bd"},"schema_version":"1.0","source":{"id":"2305.16355","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16355","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16355v1","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16355","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"RFRSJ5YLLMIJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"RFRSJ5YLLMIJLAMZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"RFRSJ5YL","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:6c8835162464772be5a4546aed6b22e2bee199cb266d87fca1b166befd835d4f","target":"graph","created_at":"2026-05-17T23:38:48Z","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":"PandaGPT displays emergent, i.e. zero-shot, cross-modal behaviors for data other than image and text (e.g., video, audio, depth, thermal, and IMU) and can take multimodal inputs simultaneously and compose their semantics naturally."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That ImageBind's embedding space is already semantically rich enough for the language model to compose meanings across modalities without any further alignment training on those modalities."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A single model trained only on image-text pairs gains instruction-following ability across images, video, and audio by routing all modalities through ImageBind's shared embedding space into Vicuna."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A single model trained only on image-text pairs can follow instructions on video, audio, depth, and thermal inputs by composing their meanings in a shared embedding space."}],"snapshot_sha256":"925da561fe9ffe37f1187f7250a02b718a7486712ccb9d1f1189f9c333c3bc4e"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b65acc071b63869295fd48ec3472d576acaea9f112fd4298df924112f4d67867"},"paper":{"abstract_excerpt":"We present PandaGPT, an approach to emPower large lANguage moDels with visual and Auditory instruction-following capabilities. Our pilot experiments show that PandaGPT can perform complex tasks such as detailed image description generation, writing stories inspired by videos, and answering questions about audios. More interestingly, PandaGPT can take multimodal inputs simultaneously and compose their semantics naturally. For example, PandaGPT can connect how objects look in an image/video and how they sound in an audio. To do so, PandaGPT combines the multimodal encoders from ImageBind and the","authors_text":"Deng Cai, Huayang Li, Jialu Xu, Tian Lan, Yan Wang, Yixuan Su","cross_cats":["cs.CV"],"headline":"A single model trained only on image-text pairs can follow instructions on video, audio, depth, and thermal inputs by composing their meanings in a shared embedding space.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T04:16:07Z","title":"PandaGPT: One Model To Instruction-Follow Them All"},"references":{"count":32,"internal_anchors":8,"resolved_work":32,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. 2022. Flamingo: a visual language model","work_id":"99c9825d-d8aa-4d56-9301-b5cac88e2bb4","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Jean-Baptiste Alayrac, Adria Recasens, Rosalia Schneider, Relja Arandjelovi´c, Jason Rama- puram, Jeffrey De Fauw, Lucas Smaira, Sander Dieleman, and Andrew Zisserman. 2020. Self-supervised multimodal","work_id":"f80752c3-199b-4209-a52f-91a90fb91770","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot lear","work_id":"0ee6a9fc-348e-411b-945a-c5820c50b0b1","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Gonzalez, Ion Stoica, and Eric P","work_id":"eb89ea20-08e6-4a9e-9f97-6330cab3e994","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the N","work_id":"62467c4c-275a-48fb-a48c-2d95503573e0","year":2019}],"snapshot_sha256":"9348f680c6e4af2af79bde822d07cb39360040d5299e0413d722c64c593c6c5f"},"source":{"id":"2305.16355","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-16T08:58:06.902090Z","id":"5e0eb80b-0917-4302-b4b4-90bbb09d44c1","model_set":{"reader":"grok-4.3"},"one_line_summary":"A single model trained only on image-text pairs gains instruction-following ability across images, video, and audio by routing all modalities through ImageBind's shared embedding space into Vicuna.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A single model trained only on image-text pairs can follow instructions on video, audio, depth, and thermal inputs by composing their meanings in a shared embedding space.","strongest_claim":"PandaGPT displays emergent, i.e. zero-shot, cross-modal behaviors for data other than image and text (e.g., video, audio, depth, thermal, and IMU) and can take multimodal inputs simultaneously and compose their semantics naturally.","weakest_assumption":"That ImageBind's embedding space is already semantically rich enough for the language model to compose meanings across modalities without any further alignment training on those modalities."}},"verdict_id":"5e0eb80b-0917-4302-b4b4-90bbb09d44c1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:13145015a63ccb514df9877c9e9ec51db9bc78e85e429dd8030630398b3549ec","target":"record","created_at":"2026-05-17T23:38:48Z","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":"a33eb1f75754eee664c50c5a05cfef2ea5b7c32e181ab55bcafee2f43fdb58d5","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T04:16:07Z","title_canon_sha256":"bbbc8f4530482ee4a7ed90c8764467b8790d3a9d3a102881526d4cdb5d5655bd"},"schema_version":"1.0","source":{"id":"2305.16355","kind":"arxiv","version":1}},"canonical_sha256":"896324f70b5b10958199281e9273616b3b1c9cba067746a5a493e96d395ec151","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"896324f70b5b10958199281e9273616b3b1c9cba067746a5a493e96d395ec151","first_computed_at":"2026-05-17T23:38:48.430132Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:48.430132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B/QM9uBoWogcXjnkmqhnXlQoQ3sxDA9hnLvh1Ust1Pyu1jRxeScz2UZLFfxOAU+CMA8FEljZD6rUdRtT+IO2DA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:48.430747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.16355","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13145015a63ccb514df9877c9e9ec51db9bc78e85e429dd8030630398b3549ec","sha256:6c8835162464772be5a4546aed6b22e2bee199cb266d87fca1b166befd835d4f"],"state_sha256":"ea1966f819c8a8e642ff1ba17065c2bdb5df34cc983fd39bfbf7840a8fb1e650"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qL5/GNTQgd7EoIPgHU3t6Yu6Vzj0WppGenGNyO7TYqhHa8cEzQLVeX4d+xwGpNFELDSqIs4f7Xa1HiA2DcYTCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T17:55:19.193931Z","bundle_sha256":"69d64b26f59c3c7326d287ef29834058b025288740e853517d90c34a171dd866"}}