{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EFZXCYE6I57UJIY7YFDOKGZL4C","short_pith_number":"pith:EFZXCYE6","canonical_record":{"source":{"id":"2605.13321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T10:34:47Z","cross_cats_sorted":[],"title_canon_sha256":"c391ac4816934ccd4ce5299da281b700b9587e174cac176ef908ee0b9f017a04","abstract_canon_sha256":"26470e9be5f60d4d5f443e741d5419a9f76a36ca2e7341506b6b445198079984"},"schema_version":"1.0"},"canonical_sha256":"217371609e477f44a31fc146e51b2be0a6827ee0b8a1393d0b86678cc40c99b5","source":{"kind":"arxiv","id":"2605.13321","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13321","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13321v1","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13321","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"pith_short_12","alias_value":"EFZXCYE6I57U","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"EFZXCYE6I57UJIY7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"EFZXCYE6","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EFZXCYE6I57UJIY7YFDOKGZL4C","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T10:34:47Z","cross_cats_sorted":[],"title_canon_sha256":"c391ac4816934ccd4ce5299da281b700b9587e174cac176ef908ee0b9f017a04","abstract_canon_sha256":"26470e9be5f60d4d5f443e741d5419a9f76a36ca2e7341506b6b445198079984"},"schema_version":"1.0"},"canonical_sha256":"217371609e477f44a31fc146e51b2be0a6827ee0b8a1393d0b86678cc40c99b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:48.671408Z","signature_b64":"mOr2lUifJaDlj5fam4d8vz/s0/4CjpGabWbfls3SjIOWC4tudsr6DEG7DU3gYWw3zHm8Lk/DLnGrPbKK2epNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"217371609e477f44a31fc146e51b2be0a6827ee0b8a1393d0b86678cc40c99b5","last_reissued_at":"2026-05-18T02:44:48.670968Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:48.670968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13321","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":"2026-05-18T02:44:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aAy67xggq5igGDRUpti3NRDLeObi3kKnsLWmgyLPNFnm0BFusveoSAWZU7nvBkUCHKw1lIUxzd5mij2zexq7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T13:44:43.008384Z"},"content_sha256":"9ccfb5df420cb081cca97bd6092753cdc9130eb9c580acc45775be9250648edc","schema_version":"1.0","event_id":"sha256:9ccfb5df420cb081cca97bd6092753cdc9130eb9c580acc45775be9250648edc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EFZXCYE6I57UJIY7YFDOKGZL4C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HCSG: Human-Centric Semantic-Geometric Reasoning for Vision-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"HCSG lets robots navigate dynamic spaces by predicting human movements and understanding their intentions through combined geometry and language models.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Haoang Li, Haoxuan Xu, Hesheng Wang, Huashuo Lei, Jin Wu, Lujia Wang, Tianfu Li, Wenbo Chen, Yi Liu, Yunfan Lou","submitted_at":"2026-05-13T10:34:47Z","abstract_excerpt":"VLN has achieved remarkable progress by scaling data and model capacity. However, the assumption of a static environment breaks down in real-world indoor scenarios, where robots inevitably encounter dynamic pedestrians. Existing human-aware approaches typically treat humans merely as moving obstacles based on implicit visual cues, lacking the explicit reasoning required to interpret human intentions or maintain social norms. To address this, we propose HCSG, the first human-centric framework for VLN. This framework provides a robust foundation for safe, socially intelligent navigation in dynam"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"HCSG is the first human-centric framework for VLN that synergizes geometric forecasting and semantic interpretation via VLM to achieve a 14% improvement in Success Rate and a 34% reduction in Collision Rate on the HA-VLNCE benchmark.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the unified Human Understanding Module can reliably predict human poses and trajectories while generating accurate natural-language descriptions of intentions, and that these representations can be effectively fused into the topological map for instruction-conditioned planning in unseen real-world dynamic scenes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"HCSG combines geometric forecasting of human pose and trajectory with VLM-generated semantic descriptions of intentions, fused into a topological map with a social distance loss, yielding 14% higher success rate and 34% lower collision rate on the HA-VLNCE benchmark.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"HCSG lets robots navigate dynamic spaces by predicting human movements and understanding their intentions through combined geometry and language models.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f4f84350fc091b0e7fbc46c0a156f7151f6dcefda156f9678b820162d7cba577"},"source":{"id":"2605.13321","kind":"arxiv","version":1},"verdict":{"id":"f6560fa2-b9a0-4c0d-ab9e-65eec281d6c6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:01:35.366623Z","strongest_claim":"HCSG is the first human-centric framework for VLN that synergizes geometric forecasting and semantic interpretation via VLM to achieve a 14% improvement in Success Rate and a 34% reduction in Collision Rate on the HA-VLNCE benchmark.","one_line_summary":"HCSG combines geometric forecasting of human pose and trajectory with VLM-generated semantic descriptions of intentions, fused into a topological map with a social distance loss, yielding 14% higher success rate and 34% lower collision rate on the HA-VLNCE benchmark.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the unified Human Understanding Module can reliably predict human poses and trajectories while generating accurate natural-language descriptions of intentions, and that these representations can be effectively fused into the topological map for instruction-conditioned planning in unseen real-world dynamic scenes.","pith_extraction_headline":"HCSG lets robots navigate dynamic spaces by predicting human movements and understanding their intentions through combined geometry and language models."},"references":{"count":58,"sample":[{"doi":"","year":2023,"title":"BEVBert: Multimodal map pre-training for language-guided navigation,","work_id":"88d30bb1-d8f5-4fde-8da0-78cddc631c93","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"ETPNav: Evolving topological planning for vision-language navigation in continuous environments,","work_id":"2e1d906c-19d7-4030-943e-934e587c2896","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments,","work_id":"90aa608c-7f36-418a-88f7-72435cc81af8","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Room-Across- Room: Multilingual Vision-and-Language Navigation with Dense Spa- tiotemporal Grounding,","work_id":"d191ec7b-9065-40c8-acbe-de8b03a7e7dc","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Beyond the Nav-Graph: Vision-and-language navigation in continuous environ- ments,","work_id":"8bf4b5e7-ac84-47c5-bc08-05aa41c57447","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":58,"snapshot_sha256":"5ac2d3a56207b5b7b356479c7e02fd9cf68e7c7d63e654d144c097ab530ba461","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d4d57c700a1f09d8921590fc2ee521af96539f430536ec2f2839bcd587b21723"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"f6560fa2-b9a0-4c0d-ab9e-65eec281d6c6"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1qJz6B73iVSiiBCNVQinXTpohzmBGAD+JfBDldPYTdCIEqIvQrz+l5EynQvfWEOgJgJo9Oe0tqVIrPsn307ABw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T13:44:43.008936Z"},"content_sha256":"303d95f666c35544b18294dda645b062152d2e15ab98675fdd7a1980a7782e38","schema_version":"1.0","event_id":"sha256:303d95f666c35544b18294dda645b062152d2e15ab98675fdd7a1980a7782e38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EFZXCYE6I57UJIY7YFDOKGZL4C/bundle.json","state_url":"https://pith.science/pith/EFZXCYE6I57UJIY7YFDOKGZL4C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EFZXCYE6I57UJIY7YFDOKGZL4C/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":"2026-06-02T13:44:43Z","links":{"resolver":"https://pith.science/pith/EFZXCYE6I57UJIY7YFDOKGZL4C","bundle":"https://pith.science/pith/EFZXCYE6I57UJIY7YFDOKGZL4C/bundle.json","state":"https://pith.science/pith/EFZXCYE6I57UJIY7YFDOKGZL4C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EFZXCYE6I57UJIY7YFDOKGZL4C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EFZXCYE6I57UJIY7YFDOKGZL4C","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":"26470e9be5f60d4d5f443e741d5419a9f76a36ca2e7341506b6b445198079984","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T10:34:47Z","title_canon_sha256":"c391ac4816934ccd4ce5299da281b700b9587e174cac176ef908ee0b9f017a04"},"schema_version":"1.0","source":{"id":"2605.13321","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13321","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13321v1","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13321","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"pith_short_12","alias_value":"EFZXCYE6I57U","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"EFZXCYE6I57UJIY7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"EFZXCYE6","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:303d95f666c35544b18294dda645b062152d2e15ab98675fdd7a1980a7782e38","target":"graph","created_at":"2026-05-18T02:44:48Z","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":"HCSG is the first human-centric framework for VLN that synergizes geometric forecasting and semantic interpretation via VLM to achieve a 14% improvement in Success Rate and a 34% reduction in Collision Rate on the HA-VLNCE benchmark."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the unified Human Understanding Module can reliably predict human poses and trajectories while generating accurate natural-language descriptions of intentions, and that these representations can be effectively fused into the topological map for instruction-conditioned planning in unseen real-world dynamic scenes."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"HCSG combines geometric forecasting of human pose and trajectory with VLM-generated semantic descriptions of intentions, fused into a topological map with a social distance loss, yielding 14% higher success rate and 34% lower collision rate on the HA-VLNCE benchmark."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"HCSG lets robots navigate dynamic spaces by predicting human movements and understanding their intentions through combined geometry and language models."}],"snapshot_sha256":"f4f84350fc091b0e7fbc46c0a156f7151f6dcefda156f9678b820162d7cba577"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d4d57c700a1f09d8921590fc2ee521af96539f430536ec2f2839bcd587b21723"},"paper":{"abstract_excerpt":"VLN has achieved remarkable progress by scaling data and model capacity. However, the assumption of a static environment breaks down in real-world indoor scenarios, where robots inevitably encounter dynamic pedestrians. Existing human-aware approaches typically treat humans merely as moving obstacles based on implicit visual cues, lacking the explicit reasoning required to interpret human intentions or maintain social norms. To address this, we propose HCSG, the first human-centric framework for VLN. This framework provides a robust foundation for safe, socially intelligent navigation in dynam","authors_text":"Haoang Li, Haoxuan Xu, Hesheng Wang, Huashuo Lei, Jin Wu, Lujia Wang, Tianfu Li, Wenbo Chen, Yi Liu, Yunfan Lou","cross_cats":[],"headline":"HCSG lets robots navigate dynamic spaces by predicting human movements and understanding their intentions through combined geometry and language models.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T10:34:47Z","title":"HCSG: Human-Centric Semantic-Geometric Reasoning for Vision-Language Navigation"},"references":{"count":58,"internal_anchors":1,"resolved_work":58,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"BEVBert: Multimodal map pre-training for language-guided navigation,","work_id":"88d30bb1-d8f5-4fde-8da0-78cddc631c93","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"ETPNav: Evolving topological planning for vision-language navigation in continuous environments,","work_id":"2e1d906c-19d7-4030-943e-934e587c2896","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments,","work_id":"90aa608c-7f36-418a-88f7-72435cc81af8","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Room-Across- Room: Multilingual Vision-and-Language Navigation with Dense Spa- tiotemporal Grounding,","work_id":"d191ec7b-9065-40c8-acbe-de8b03a7e7dc","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Beyond the Nav-Graph: Vision-and-language navigation in continuous environ- ments,","work_id":"8bf4b5e7-ac84-47c5-bc08-05aa41c57447","year":2020}],"snapshot_sha256":"5ac2d3a56207b5b7b356479c7e02fd9cf68e7c7d63e654d144c097ab530ba461"},"source":{"id":"2605.13321","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T18:01:35.366623Z","id":"f6560fa2-b9a0-4c0d-ab9e-65eec281d6c6","model_set":{"reader":"grok-4.3"},"one_line_summary":"HCSG combines geometric forecasting of human pose and trajectory with VLM-generated semantic descriptions of intentions, fused into a topological map with a social distance loss, yielding 14% higher success rate and 34% lower collision rate on the HA-VLNCE benchmark.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"HCSG lets robots navigate dynamic spaces by predicting human movements and understanding their intentions through combined geometry and language models.","strongest_claim":"HCSG is the first human-centric framework for VLN that synergizes geometric forecasting and semantic interpretation via VLM to achieve a 14% improvement in Success Rate and a 34% reduction in Collision Rate on the HA-VLNCE benchmark.","weakest_assumption":"That the unified Human Understanding Module can reliably predict human poses and trajectories while generating accurate natural-language descriptions of intentions, and that these representations can be effectively fused into the topological map for instruction-conditioned planning in unseen real-world dynamic scenes."}},"verdict_id":"f6560fa2-b9a0-4c0d-ab9e-65eec281d6c6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9ccfb5df420cb081cca97bd6092753cdc9130eb9c580acc45775be9250648edc","target":"record","created_at":"2026-05-18T02:44:48Z","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":"26470e9be5f60d4d5f443e741d5419a9f76a36ca2e7341506b6b445198079984","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T10:34:47Z","title_canon_sha256":"c391ac4816934ccd4ce5299da281b700b9587e174cac176ef908ee0b9f017a04"},"schema_version":"1.0","source":{"id":"2605.13321","kind":"arxiv","version":1}},"canonical_sha256":"217371609e477f44a31fc146e51b2be0a6827ee0b8a1393d0b86678cc40c99b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"217371609e477f44a31fc146e51b2be0a6827ee0b8a1393d0b86678cc40c99b5","first_computed_at":"2026-05-18T02:44:48.670968Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:48.670968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mOr2lUifJaDlj5fam4d8vz/s0/4CjpGabWbfls3SjIOWC4tudsr6DEG7DU3gYWw3zHm8Lk/DLnGrPbKK2epNDA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:48.671408Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13321","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ccfb5df420cb081cca97bd6092753cdc9130eb9c580acc45775be9250648edc","sha256:303d95f666c35544b18294dda645b062152d2e15ab98675fdd7a1980a7782e38"],"state_sha256":"b19293562d4c94fc011acddcb0ed87f678a95440c59d60173bc28398bb0bdab8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yb5mvSp4Hnz1I3nbKJEcocU2FmTRvoGM3xde3q4eZ3RpUx7Wr6wvIpnnUe3HWZXwmb+GC8DQtXTwHsgyVrDiAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T13:44:43.011448Z","bundle_sha256":"9db7d5ec3257de2c516f2d14008f98d47a1d794b31cf607856006d6ae1ab22cd"}}