{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LIEGPVP5NQZRLUA6WZVIJYXJDK","short_pith_number":"pith:LIEGPVP5","canonical_record":{"source":{"id":"2605.08330","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-08T17:36:13Z","cross_cats_sorted":[],"title_canon_sha256":"51c23789d9d1828a912b80c3c14c298a2266ad90cd5d6b26425a3ca691e522d1","abstract_canon_sha256":"d237b6aa94b036febbd876aaf77b7170fff794210de956b699fa115c7ba45dc2"},"schema_version":"1.0"},"canonical_sha256":"5a0867d5fd6c3315d01eb66a84e2e91a88567bc686e01bc7fff3bda65ee63840","source":{"kind":"arxiv","id":"2605.08330","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08330","created_at":"2026-06-30T01:17:39Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08330v1","created_at":"2026-06-30T01:17:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08330","created_at":"2026-06-30T01:17:39Z"},{"alias_kind":"pith_short_12","alias_value":"LIEGPVP5NQZR","created_at":"2026-06-30T01:17:39Z"},{"alias_kind":"pith_short_16","alias_value":"LIEGPVP5NQZRLUA6","created_at":"2026-06-30T01:17:39Z"},{"alias_kind":"pith_short_8","alias_value":"LIEGPVP5","created_at":"2026-06-30T01:17:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LIEGPVP5NQZRLUA6WZVIJYXJDK","target":"record","payload":{"canonical_record":{"source":{"id":"2605.08330","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-08T17:36:13Z","cross_cats_sorted":[],"title_canon_sha256":"51c23789d9d1828a912b80c3c14c298a2266ad90cd5d6b26425a3ca691e522d1","abstract_canon_sha256":"d237b6aa94b036febbd876aaf77b7170fff794210de956b699fa115c7ba45dc2"},"schema_version":"1.0"},"canonical_sha256":"5a0867d5fd6c3315d01eb66a84e2e91a88567bc686e01bc7fff3bda65ee63840","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:39.566982Z","signature_b64":"wScXlsvvShHjjZyGSxq3G2ZFBV9ollqaaV47Yvn7zZnSfJZblw7pOi6mdYzIU3anIygTvcpbWzizUX5nzwFjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a0867d5fd6c3315d01eb66a84e2e91a88567bc686e01bc7fff3bda65ee63840","last_reissued_at":"2026-06-30T01:17:39.566260Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:39.566260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.08330","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":"2026-06-30T01:17:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p7WSfEg0HxUadkdfthMUzn8om+GHIWqd1tI7X25NxJ3cWQI44r5SU3ExKqrOMaZoKPyByPX+4fYP5GV63RUfBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:29:14.378064Z"},"content_sha256":"e54f24d8ac49807d0511ec40f6f4765151662a3ca811ab6124994eed53ec9be3","schema_version":"1.0","event_id":"sha256:e54f24d8ac49807d0511ec40f6f4765151662a3ca811ab6124994eed53ec9be3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LIEGPVP5NQZRLUA6WZVIJYXJDK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Prompting with Dual LLM Modules for Robotic Task and Motion Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Dual LLM modules with hierarchical prompting achieve 86% success in robotic task and motion planning tests","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Antonio Galiza Cerdeira Gonzalez, Bipin Indurkhya, Karolina \\'Zr\\'obek, Pawe{\\l} Gajewski, Tessa Pulli","submitted_at":"2026-05-08T17:36:13Z","abstract_excerpt":"We present a hierarchical language-driven framework for robotic task and motion planning to improve natural, intuitive human-robot interaction in service and assistance scenarios. The proposed system employs two large language model (LLM) modules: a high-level planning agent and a low-level spatial reasoning sub-module. The primary agent processes natural language commands and generates action sequences using a ReAct-style prompt, interacting with tools for object perception and manipulation (e.g., pick, place, release). For precise spatial placement, such as interpreting \"place the mug next t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The system achieved an overall task success rate of 86% in 24 test scenarios, ranging from simple spatial commands to high-level instructions and infeasible requests.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that the high-level ReAct agent and low-level spatial sub-module will reliably interpret natural language and 3D geometry without hallucinations or integration failures in varied real-world conditions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A dual-LLM hierarchical framework for robotic task and motion planning, integrating object detection, achieves 86% success across 24 test scenarios ranging from simple spatial commands to infeasible requests.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Dual LLM modules with hierarchical prompting achieve 86% success in robotic task and motion planning tests","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2f56a2f06495f61fd4dfc92d86bde155ebc082ebaad67fe791c5a985b8c93649"},"source":{"id":"2605.08330","kind":"arxiv","version":1},"verdict":{"id":"87c61069-f487-46b1-a1a9-09406dfcfdba","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T01:17:18.584472Z","strongest_claim":"The system achieved an overall task success rate of 86% in 24 test scenarios, ranging from simple spatial commands to high-level instructions and infeasible requests.","one_line_summary":"A dual-LLM hierarchical framework for robotic task and motion planning, integrating object detection, achieves 86% success across 24 test scenarios ranging from simple spatial commands to infeasible requests.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that the high-level ReAct agent and low-level spatial sub-module will reliably interpret natural language and 3D geometry without hallucinations or integration failures in varied real-world conditions.","pith_extraction_headline":"Dual LLM modules with hierarchical prompting achieve 86% success in robotic task and motion planning tests"},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.08330/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T09:42:04.495795Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T04:42:15.984994Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T15:01:18.544733Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T11:16:28.640001Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"a83b48c319b1b19f5ef0139aba2b906b294316f085a0244b84706f588d76c9c8"},"references":{"count":29,"sample":[{"doi":"","year":2025,"title":"A survey of communicating robot learning during human-robot interaction","work_id":"a9190477-6287-4106-bd6b-907f931a914a","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Robots that use language","work_id":"035cf458-218e-41c0-9147-f42eff521ef0","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Tell me dave: Context- sensitive grounding of natural language to manipulation instructions","work_id":"6aa4812c-8b3e-4053-8833-42310ed167cc","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Robotic Control via Embodied Chain-of-Thought Reasoning","work_id":"bbe96698-686e-4b4a-9f7f-ed5054e61cca","ref_index":4,"cited_arxiv_id":"2407.08693","is_internal_anchor":true},{"doi":"","year":2024,"title":"Embodiedgpt: Vision-language pre-training via embodied chain of thought","work_id":"d49aec28-7f7b-49c9-8204-13e37a5e2fba","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":29,"snapshot_sha256":"75c51bc7a59b207e836a30953cd380e97326b0dd650645f7bac64d27b1d97b4b","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ebb29e4726dc609b04d11dd85c17236e97fcc61950e937628fd5cc5e03e2d555"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"87c61069-f487-46b1-a1a9-09406dfcfdba"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T01:17:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JkXwXL3L/SfvHc+eB9xIrYRWe57WmX7L4ApHzptJBkOkHVJsHjyCZ4IbmpQ7UAatogPpsgLivPw+Lf8cH8NjBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:29:14.379093Z"},"content_sha256":"85c23d7628631538f6df8d4dbf4a38a7c61a0785fac773be4bbcc47fc5c1d8ca","schema_version":"1.0","event_id":"sha256:85c23d7628631538f6df8d4dbf4a38a7c61a0785fac773be4bbcc47fc5c1d8ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LIEGPVP5NQZRLUA6WZVIJYXJDK/bundle.json","state_url":"https://pith.science/pith/LIEGPVP5NQZRLUA6WZVIJYXJDK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LIEGPVP5NQZRLUA6WZVIJYXJDK/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":"2026-08-04T14:29:14Z","links":{"resolver":"https://pith.science/pith/LIEGPVP5NQZRLUA6WZVIJYXJDK","bundle":"https://pith.science/pith/LIEGPVP5NQZRLUA6WZVIJYXJDK/bundle.json","state":"https://pith.science/pith/LIEGPVP5NQZRLUA6WZVIJYXJDK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LIEGPVP5NQZRLUA6WZVIJYXJDK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LIEGPVP5NQZRLUA6WZVIJYXJDK","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":"d237b6aa94b036febbd876aaf77b7170fff794210de956b699fa115c7ba45dc2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-08T17:36:13Z","title_canon_sha256":"51c23789d9d1828a912b80c3c14c298a2266ad90cd5d6b26425a3ca691e522d1"},"schema_version":"1.0","source":{"id":"2605.08330","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08330","created_at":"2026-06-30T01:17:39Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08330v1","created_at":"2026-06-30T01:17:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08330","created_at":"2026-06-30T01:17:39Z"},{"alias_kind":"pith_short_12","alias_value":"LIEGPVP5NQZR","created_at":"2026-06-30T01:17:39Z"},{"alias_kind":"pith_short_16","alias_value":"LIEGPVP5NQZRLUA6","created_at":"2026-06-30T01:17:39Z"},{"alias_kind":"pith_short_8","alias_value":"LIEGPVP5","created_at":"2026-06-30T01:17:39Z"}],"graph_snapshots":[{"event_id":"sha256:85c23d7628631538f6df8d4dbf4a38a7c61a0785fac773be4bbcc47fc5c1d8ca","target":"graph","created_at":"2026-06-30T01:17:39Z","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 system achieved an overall task success rate of 86% in 24 test scenarios, ranging from simple spatial commands to high-level instructions and infeasible requests."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the high-level ReAct agent and low-level spatial sub-module will reliably interpret natural language and 3D geometry without hallucinations or integration failures in varied real-world conditions."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A dual-LLM hierarchical framework for robotic task and motion planning, integrating object detection, achieves 86% success across 24 test scenarios ranging from simple spatial commands to infeasible requests."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Dual LLM modules with hierarchical prompting achieve 86% success in robotic task and motion planning tests"}],"snapshot_sha256":"2f56a2f06495f61fd4dfc92d86bde155ebc082ebaad67fe791c5a985b8c93649"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ebb29e4726dc609b04d11dd85c17236e97fcc61950e937628fd5cc5e03e2d555"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T09:42:04.495795Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T04:42:15.984994Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T15:01:18.544733Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T11:16:28.640001Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.08330/integrity.json","findings":[],"snapshot_sha256":"a83b48c319b1b19f5ef0139aba2b906b294316f085a0244b84706f588d76c9c8","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a hierarchical language-driven framework for robotic task and motion planning to improve natural, intuitive human-robot interaction in service and assistance scenarios. The proposed system employs two large language model (LLM) modules: a high-level planning agent and a low-level spatial reasoning sub-module. The primary agent processes natural language commands and generates action sequences using a ReAct-style prompt, interacting with tools for object perception and manipulation (e.g., pick, place, release). For precise spatial placement, such as interpreting \"place the mug next t","authors_text":"Antonio Galiza Cerdeira Gonzalez, Bipin Indurkhya, Karolina \\'Zr\\'obek, Pawe{\\l} Gajewski, Tessa Pulli","cross_cats":[],"headline":"Dual LLM modules with hierarchical prompting achieve 86% success in robotic task and motion planning tests","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-08T17:36:13Z","title":"Hierarchical Prompting with Dual LLM Modules for Robotic Task and Motion Planning"},"references":{"count":29,"internal_anchors":4,"resolved_work":29,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"A survey of communicating robot learning during human-robot interaction","work_id":"a9190477-6287-4106-bd6b-907f931a914a","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Robots that use language","work_id":"035cf458-218e-41c0-9147-f42eff521ef0","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Tell me dave: Context- sensitive grounding of natural language to manipulation instructions","work_id":"6aa4812c-8b3e-4053-8833-42310ed167cc","year":2016},{"cited_arxiv_id":"2407.08693","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Robotic Control via Embodied Chain-of-Thought Reasoning","work_id":"bbe96698-686e-4b4a-9f7f-ed5054e61cca","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Embodiedgpt: Vision-language pre-training via embodied chain of thought","work_id":"d49aec28-7f7b-49c9-8204-13e37a5e2fba","year":2024}],"snapshot_sha256":"75c51bc7a59b207e836a30953cd380e97326b0dd650645f7bac64d27b1d97b4b"},"source":{"id":"2605.08330","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-12T01:17:18.584472Z","id":"87c61069-f487-46b1-a1a9-09406dfcfdba","model_set":{"reader":"grok-4.3"},"one_line_summary":"A dual-LLM hierarchical framework for robotic task and motion planning, integrating object detection, achieves 86% success across 24 test scenarios ranging from simple spatial commands to infeasible requests.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Dual LLM modules with hierarchical prompting achieve 86% success in robotic task and motion planning tests","strongest_claim":"The system achieved an overall task success rate of 86% in 24 test scenarios, ranging from simple spatial commands to high-level instructions and infeasible requests.","weakest_assumption":"The assumption that the high-level ReAct agent and low-level spatial sub-module will reliably interpret natural language and 3D geometry without hallucinations or integration failures in varied real-world conditions."}},"verdict_id":"87c61069-f487-46b1-a1a9-09406dfcfdba"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e54f24d8ac49807d0511ec40f6f4765151662a3ca811ab6124994eed53ec9be3","target":"record","created_at":"2026-06-30T01:17:39Z","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":"d237b6aa94b036febbd876aaf77b7170fff794210de956b699fa115c7ba45dc2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-08T17:36:13Z","title_canon_sha256":"51c23789d9d1828a912b80c3c14c298a2266ad90cd5d6b26425a3ca691e522d1"},"schema_version":"1.0","source":{"id":"2605.08330","kind":"arxiv","version":1}},"canonical_sha256":"5a0867d5fd6c3315d01eb66a84e2e91a88567bc686e01bc7fff3bda65ee63840","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a0867d5fd6c3315d01eb66a84e2e91a88567bc686e01bc7fff3bda65ee63840","first_computed_at":"2026-06-30T01:17:39.566260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:17:39.566260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wScXlsvvShHjjZyGSxq3G2ZFBV9ollqaaV47Yvn7zZnSfJZblw7pOi6mdYzIU3anIygTvcpbWzizUX5nzwFjDA==","signature_status":"signed_v1","signed_at":"2026-06-30T01:17:39.566982Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.08330","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e54f24d8ac49807d0511ec40f6f4765151662a3ca811ab6124994eed53ec9be3","sha256:85c23d7628631538f6df8d4dbf4a38a7c61a0785fac773be4bbcc47fc5c1d8ca"],"state_sha256":"f8f75d92ca8a3c344605a620c39e1d468f2f5b6d8873bb53e447a0d5513e803b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zbL8Hf6jo3Y99s9YAgAdc0s3oQ5QzHKpeJGgDgnxtH1Aicy0XTlgmTswetIjT7SDX96alvcYfOxNoZs6oqXBCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T14:29:14.420363Z","bundle_sha256":"157b5ec3119b5d84995b4abdf43069435fd7f0c3b5d6bf9b1ffe160b384e497b"}}