{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:I3L53N3OMULTQN7UW3MSSQLWHR","short_pith_number":"pith:I3L53N3O","canonical_record":{"source":{"id":"2605.12838","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T00:16:05Z","cross_cats_sorted":[],"title_canon_sha256":"f49870feddfdbd2fdd9115e778f352c9479f70fbffb64642dbe8629348f14570","abstract_canon_sha256":"a85b9755fa54dc588f8291d9f9c1064c2a2a1130194b740e05d92bc27675ec8f"},"schema_version":"1.0"},"canonical_sha256":"46d7ddb76e65173837f4b6d92941763c58b9b682324925ff4c13a8824a795778","source":{"kind":"arxiv","id":"2605.12838","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12838","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12838v1","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12838","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"I3L53N3OMULT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"I3L53N3OMULTQN7U","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"I3L53N3O","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:I3L53N3OMULTQN7UW3MSSQLWHR","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12838","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T00:16:05Z","cross_cats_sorted":[],"title_canon_sha256":"f49870feddfdbd2fdd9115e778f352c9479f70fbffb64642dbe8629348f14570","abstract_canon_sha256":"a85b9755fa54dc588f8291d9f9c1064c2a2a1130194b740e05d92bc27675ec8f"},"schema_version":"1.0"},"canonical_sha256":"46d7ddb76e65173837f4b6d92941763c58b9b682324925ff4c13a8824a795778","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:12.003691Z","signature_b64":"r76rzlKq7VtRqg+Zr6ldEpmP8Sgt+yt4A0T0fYftwtAkOjHvjhFZ0AnV0ievQe39DZf1sOsa64rrvaRuvRnsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46d7ddb76e65173837f4b6d92941763c58b9b682324925ff4c13a8824a795778","last_reissued_at":"2026-05-18T03:09:12.002835Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:12.002835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12838","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":"2026-05-18T03:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ajzRMsvOMWFES7zZjLZZQyIrjMtGO2uBxnyWTwxNB9CPLofaW1eT7ypfBxltF9fqoMTGei/63h1sChodCH5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T04:24:20.927873Z"},"content_sha256":"8e1556d036126c6eff70a0cb8df6891c164716e31f544804442e141bc6ad7319","schema_version":"1.0","event_id":"sha256:8e1556d036126c6eff70a0cb8df6891c164716e31f544804442e141bc6ad7319"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:I3L53N3OMULTQN7UW3MSSQLWHR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Hidden Markov Models for Persistent Emotional State Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Sticky HDP-HMMs recover more interpretable persistent emotional regimes from multimodal valence-arousal trajectories than Gaussian HMM baselines.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anamika Ragu, Aneesh Jonelagadda","submitted_at":"2026-05-13T00:16:05Z","abstract_excerpt":"Tracking an interpretable emotional arc of a conversation via the sentiment of individual utterances processed as a whole is central to both understanding and guiding communication in applied, especially clinical, conversational contexts. Existing approaches to emotion recognition operate at the utterance level, obscuring the persistent phases that characterize real conversational dynamics. We propose a lightweight framework that models conversational emotion as a sequence of latent emotional regimes using sticky factorial HDP-HMMs over multimodal valence-arousal representations derived from s"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"the sticky HDP-HMM produces more interpretable regime sequences than the baseline Gaussian HMM at a fraction of the computational cost of LLM-based dialogue state tracking methods. In addition, Question-Answer experiments in a clinical dataset suggest that meaningful emotional phases can reliably be recovered from multimodal valence-arousal trajectories and used to improve the quality of LLM responses in unstable affective regimes via context augmentation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That valence-arousal representations extracted from simultaneous video, audio, and text inputs faithfully capture the underlying persistent emotional regimes, and that LLM-as-a-Judge plus geometric/temporal metrics provide a reliable proxy for interpretability and clinical usefulness.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Sticky factorial HDP-HMMs applied to multimodal valence-arousal trajectories identify interpretable persistent emotional regimes in conversations, outperforming Gaussian HMM baselines in consistency metrics and enabling context-augmented LLM responses.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Sticky HDP-HMMs recover more interpretable persistent emotional regimes from multimodal valence-arousal trajectories than Gaussian HMM baselines.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"79b5d516a482f0cdd6a4f4b166ce6c678545c99f7d43575d31f8da475536a1e6"},"source":{"id":"2605.12838","kind":"arxiv","version":1},"verdict":{"id":"e3ce0655-e0a7-4bf4-b941-19bbb8858f4b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:30:34.014354Z","strongest_claim":"the sticky HDP-HMM produces more interpretable regime sequences than the baseline Gaussian HMM at a fraction of the computational cost of LLM-based dialogue state tracking methods. In addition, Question-Answer experiments in a clinical dataset suggest that meaningful emotional phases can reliably be recovered from multimodal valence-arousal trajectories and used to improve the quality of LLM responses in unstable affective regimes via context augmentation.","one_line_summary":"Sticky factorial HDP-HMMs applied to multimodal valence-arousal trajectories identify interpretable persistent emotional regimes in conversations, outperforming Gaussian HMM baselines in consistency metrics and enabling context-augmented LLM responses.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That valence-arousal representations extracted from simultaneous video, audio, and text inputs faithfully capture the underlying persistent emotional regimes, and that LLM-as-a-Judge plus geometric/temporal metrics provide a reliable proxy for interpretability and clinical usefulness.","pith_extraction_headline":"Sticky HDP-HMMs recover more interpretable persistent emotional regimes from multimodal valence-arousal trajectories than Gaussian HMM baselines."},"references":{"count":21,"sample":[{"doi":"","year":2019,"title":"IEEE access , volume=","work_id":"c470310c-d0fe-4d22-92e6-9d811a829ed6","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"arXiv preprint arXiv:2206.07359 , year=","work_id":"45027496-b674-4a34-a106-af27c83f4c89","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1002/widm.1563","year":null,"title":"WIREs Data Mining and Knowledge Discovery , volume =","work_id":"3355e016-8135-413b-963b-23f56e8ea64d","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2006,"title":"and Bergeman, Cindy S","work_id":"eb80bb83-0f77-4d92-a7bb-45a34670aca6","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"arXiv preprint arXiv:2503.08857 , year=","work_id":"5a30a4c8-0e20-4855-9644-5869e0aad9f0","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":21,"snapshot_sha256":"b0e79a3b30cb845236e9b644584f0e96ba3c2ae9070c762183a4f7e086c8cd24","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0fac92dab62f8ee13694d3e0b78a40e08caed4ef52eda6e52c1732a1f556b36a"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"e3ce0655-e0a7-4bf4-b941-19bbb8858f4b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ul0n9+J+dR7mIogMMUv4WvlY1peyJ4DNF0wIwRkaxW0+mKwNZZ83VTUDccVtgj6RuBib7k5PudFNKe/nvKk5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T04:24:20.928733Z"},"content_sha256":"06635c700e5e6e2badaf45bfd990097343336a4f97bdbc522b7ee6b6f2e6d678","schema_version":"1.0","event_id":"sha256:06635c700e5e6e2badaf45bfd990097343336a4f97bdbc522b7ee6b6f2e6d678"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I3L53N3OMULTQN7UW3MSSQLWHR/bundle.json","state_url":"https://pith.science/pith/I3L53N3OMULTQN7UW3MSSQLWHR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I3L53N3OMULTQN7UW3MSSQLWHR/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":"2026-05-27T04:24:20Z","links":{"resolver":"https://pith.science/pith/I3L53N3OMULTQN7UW3MSSQLWHR","bundle":"https://pith.science/pith/I3L53N3OMULTQN7UW3MSSQLWHR/bundle.json","state":"https://pith.science/pith/I3L53N3OMULTQN7UW3MSSQLWHR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I3L53N3OMULTQN7UW3MSSQLWHR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:I3L53N3OMULTQN7UW3MSSQLWHR","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":"a85b9755fa54dc588f8291d9f9c1064c2a2a1130194b740e05d92bc27675ec8f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T00:16:05Z","title_canon_sha256":"f49870feddfdbd2fdd9115e778f352c9479f70fbffb64642dbe8629348f14570"},"schema_version":"1.0","source":{"id":"2605.12838","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12838","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12838v1","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12838","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"I3L53N3OMULT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"I3L53N3OMULTQN7U","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"I3L53N3O","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:06635c700e5e6e2badaf45bfd990097343336a4f97bdbc522b7ee6b6f2e6d678","target":"graph","created_at":"2026-05-18T03:09:12Z","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":"the sticky HDP-HMM produces more interpretable regime sequences than the baseline Gaussian HMM at a fraction of the computational cost of LLM-based dialogue state tracking methods. In addition, Question-Answer experiments in a clinical dataset suggest that meaningful emotional phases can reliably be recovered from multimodal valence-arousal trajectories and used to improve the quality of LLM responses in unstable affective regimes via context augmentation."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That valence-arousal representations extracted from simultaneous video, audio, and text inputs faithfully capture the underlying persistent emotional regimes, and that LLM-as-a-Judge plus geometric/temporal metrics provide a reliable proxy for interpretability and clinical usefulness."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Sticky factorial HDP-HMMs applied to multimodal valence-arousal trajectories identify interpretable persistent emotional regimes in conversations, outperforming Gaussian HMM baselines in consistency metrics and enabling context-augmented LLM responses."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Sticky HDP-HMMs recover more interpretable persistent emotional regimes from multimodal valence-arousal trajectories than Gaussian HMM baselines."}],"snapshot_sha256":"79b5d516a482f0cdd6a4f4b166ce6c678545c99f7d43575d31f8da475536a1e6"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0fac92dab62f8ee13694d3e0b78a40e08caed4ef52eda6e52c1732a1f556b36a"},"paper":{"abstract_excerpt":"Tracking an interpretable emotional arc of a conversation via the sentiment of individual utterances processed as a whole is central to both understanding and guiding communication in applied, especially clinical, conversational contexts. Existing approaches to emotion recognition operate at the utterance level, obscuring the persistent phases that characterize real conversational dynamics. We propose a lightweight framework that models conversational emotion as a sequence of latent emotional regimes using sticky factorial HDP-HMMs over multimodal valence-arousal representations derived from s","authors_text":"Anamika Ragu, Aneesh Jonelagadda","cross_cats":[],"headline":"Sticky HDP-HMMs recover more interpretable persistent emotional regimes from multimodal valence-arousal trajectories than Gaussian HMM baselines.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T00:16:05Z","title":"Multimodal Hidden Markov Models for Persistent Emotional State Tracking"},"references":{"count":21,"internal_anchors":0,"resolved_work":21,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"IEEE access , volume=","work_id":"c470310c-d0fe-4d22-92e6-9d811a829ed6","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"arXiv preprint arXiv:2206.07359 , year=","work_id":"45027496-b674-4a34-a106-af27c83f4c89","year":null},{"cited_arxiv_id":"","doi":"10.1002/widm.1563","is_internal_anchor":false,"ref_index":3,"title":"WIREs Data Mining and Knowledge Discovery , volume =","work_id":"3355e016-8135-413b-963b-23f56e8ea64d","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"and Bergeman, Cindy S","work_id":"eb80bb83-0f77-4d92-a7bb-45a34670aca6","year":2006},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"arXiv preprint arXiv:2503.08857 , year=","work_id":"5a30a4c8-0e20-4855-9644-5869e0aad9f0","year":null}],"snapshot_sha256":"b0e79a3b30cb845236e9b644584f0e96ba3c2ae9070c762183a4f7e086c8cd24"},"source":{"id":"2605.12838","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:30:34.014354Z","id":"e3ce0655-e0a7-4bf4-b941-19bbb8858f4b","model_set":{"reader":"grok-4.3"},"one_line_summary":"Sticky factorial HDP-HMMs applied to multimodal valence-arousal trajectories identify interpretable persistent emotional regimes in conversations, outperforming Gaussian HMM baselines in consistency metrics and enabling context-augmented LLM responses.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Sticky HDP-HMMs recover more interpretable persistent emotional regimes from multimodal valence-arousal trajectories than Gaussian HMM baselines.","strongest_claim":"the sticky HDP-HMM produces more interpretable regime sequences than the baseline Gaussian HMM at a fraction of the computational cost of LLM-based dialogue state tracking methods. In addition, Question-Answer experiments in a clinical dataset suggest that meaningful emotional phases can reliably be recovered from multimodal valence-arousal trajectories and used to improve the quality of LLM responses in unstable affective regimes via context augmentation.","weakest_assumption":"That valence-arousal representations extracted from simultaneous video, audio, and text inputs faithfully capture the underlying persistent emotional regimes, and that LLM-as-a-Judge plus geometric/temporal metrics provide a reliable proxy for interpretability and clinical usefulness."}},"verdict_id":"e3ce0655-e0a7-4bf4-b941-19bbb8858f4b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8e1556d036126c6eff70a0cb8df6891c164716e31f544804442e141bc6ad7319","target":"record","created_at":"2026-05-18T03:09:12Z","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":"a85b9755fa54dc588f8291d9f9c1064c2a2a1130194b740e05d92bc27675ec8f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T00:16:05Z","title_canon_sha256":"f49870feddfdbd2fdd9115e778f352c9479f70fbffb64642dbe8629348f14570"},"schema_version":"1.0","source":{"id":"2605.12838","kind":"arxiv","version":1}},"canonical_sha256":"46d7ddb76e65173837f4b6d92941763c58b9b682324925ff4c13a8824a795778","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46d7ddb76e65173837f4b6d92941763c58b9b682324925ff4c13a8824a795778","first_computed_at":"2026-05-18T03:09:12.002835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:12.002835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r76rzlKq7VtRqg+Zr6ldEpmP8Sgt+yt4A0T0fYftwtAkOjHvjhFZ0AnV0ievQe39DZf1sOsa64rrvaRuvRnsDg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:12.003691Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12838","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e1556d036126c6eff70a0cb8df6891c164716e31f544804442e141bc6ad7319","sha256:06635c700e5e6e2badaf45bfd990097343336a4f97bdbc522b7ee6b6f2e6d678"],"state_sha256":"e340c1a3265c10a32642a9277dc895106807b4a72c04dcce08aeb0c8bc46067c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9/WHc7jQ89i+MIWBYXrseetqJD2kZQBvO2vrFchOdGIIaU00IJDBFx6eijldg3hKSpDSh61unPK7kQ8bmFkODw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T04:24:20.933107Z","bundle_sha256":"fb6914d3ac354555e82d4e488470197fe749a24723826e99324d72e9afa761c1"}}