{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:77CWFXTVI3EJRWRNSBE7GCRZQD","short_pith_number":"pith:77CWFXTV","canonical_record":{"source":{"id":"2605.16726","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T00:28:59Z","cross_cats_sorted":[],"title_canon_sha256":"b970e7064f8320dd982bf9fa052702e42ab35b5fa701c9d055cca72f32c72309","abstract_canon_sha256":"6c27b79cc89b971998ae8d6b5983b4405bcb61a7dac2e2dc18b11cf612006c0a"},"schema_version":"1.0"},"canonical_sha256":"ffc562de7546c898da2d9049f30a3980d1de148704e0f267fc47433d70cdeac4","source":{"kind":"arxiv","id":"2605.16726","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16726","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16726v1","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16726","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"pith_short_12","alias_value":"77CWFXTVI3EJ","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"pith_short_16","alias_value":"77CWFXTVI3EJRWRN","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"pith_short_8","alias_value":"77CWFXTV","created_at":"2026-05-20T00:02:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:77CWFXTVI3EJRWRNSBE7GCRZQD","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16726","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T00:28:59Z","cross_cats_sorted":[],"title_canon_sha256":"b970e7064f8320dd982bf9fa052702e42ab35b5fa701c9d055cca72f32c72309","abstract_canon_sha256":"6c27b79cc89b971998ae8d6b5983b4405bcb61a7dac2e2dc18b11cf612006c0a"},"schema_version":"1.0"},"canonical_sha256":"ffc562de7546c898da2d9049f30a3980d1de148704e0f267fc47433d70cdeac4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:38.627585Z","signature_b64":"/jdug+cQACpFGylQX0TG7xGCXlgNv+XaqASG9nuvzVDpGpxd7xi3CFfAFe+b3PRYch7w9l63AHUHbG4i36aODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffc562de7546c898da2d9049f30a3980d1de148704e0f267fc47433d70cdeac4","last_reissued_at":"2026-05-20T00:02:38.626729Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:38.626729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16726","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":"2026-05-20T00:02:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8NpEbf0ZonjDWjGHdA++6ZBCxzpHBj6pyC2ommnKpL4ZgqEAop9zcYReuHH9i2z8BYyMv4Ean7f/ULUDUtEsAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:46:00.431630Z"},"content_sha256":"2c331033aa61805b65d5676525771c13d6a833cab0a22bb9709258923f9d7afd","schema_version":"1.0","event_id":"sha256:2c331033aa61805b65d5676525771c13d6a833cab0a22bb9709258923f9d7afd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:77CWFXTVI3EJRWRNSBE7GCRZQD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Global-Local Graph Attention Network for Traffic Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"GLGAT lets traffic nodes share a global attention matrix while each gets its own local one to model distinct behaviors.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Tianchi Zhang","submitted_at":"2026-05-16T00:28:59Z","abstract_excerpt":"Traffic forecasting is a significant part of intelligent transportation systems. One of the critical challenges of traffic forecasting is to find spatio-temporal correlations. In recent years, graph convolutional networks and graph attention networks have replaced traditional statistical models to predict future traffic. However, it is complicated for both of them to allow vertices to have far different characters. To address this, we propose the Global-Local Graph Attention Network (GLGAT) with pairwise encoding and the event-based adjacency matrix. The GLGAT allows vertices to have a global "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on two real-world traffic datasets show that GLGAT can effectively capture spatio-temporal correlations and has competitive performance against other state-of-the-art baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The premise that traffic vertices have sufficiently different characters to justify separate global and per-vertex local attention matrices, and that an event-based adjacency matrix will reliably encode the relevant spatio-temporal dependencies without introducing bias.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GLGAT uses global-local graph attention with pairwise encoding and event-based adjacency to capture spatio-temporal traffic correlations and reports competitive results on two real-world datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"GLGAT lets traffic nodes share a global attention matrix while each gets its own local one to model distinct behaviors.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d6fc71a732465e6854554b53c362e86a782622b6145007645fb77312a58b8b03"},"source":{"id":"2605.16726","kind":"arxiv","version":1},"verdict":{"id":"cf94adc9-08d2-487a-acb0-1a0a05bd3c9a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T21:39:05.552647Z","strongest_claim":"Experiments on two real-world traffic datasets show that GLGAT can effectively capture spatio-temporal correlations and has competitive performance against other state-of-the-art baselines.","one_line_summary":"GLGAT uses global-local graph attention with pairwise encoding and event-based adjacency to capture spatio-temporal traffic correlations and reports competitive results on two real-world datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The premise that traffic vertices have sufficiently different characters to justify separate global and per-vertex local attention matrices, and that an event-based adjacency matrix will reliably encode the relevant spatio-temporal dependencies without introducing bias.","pith_extraction_headline":"GLGAT lets traffic nodes share a global attention matrix while each gets its own local one to model distinct behaviors."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16726/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T22:01:23.088632Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T21:51:05.314135Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.347082Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.472405Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"96087c1422aa660a333721b69df4868e4db611151c9b60bbf46f6656d556e6f2"},"references":{"count":19,"sample":[{"doi":"","year":2021,"title":"page 1–17, Jul 2021","work_id":"2f55f036-eeed-42a0-a508-dad74ca2565e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Ross Girshick. Fast r-cnn. InProceedings of the IEEE inter- national conference on computer vision, pages 1440–1448,","work_id":"0fbe78b2-1adc-41ba-81e6-17509f12a5ef","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Gaussian Error Linear Units (GELUs)","work_id":"0466fd22-03a1-4a61-af0a-a900e77bb023","ref_index":3,"cited_arxiv_id":"1606.08415","is_internal_anchor":true},{"doi":"","year":null,"title":"arXiv preprint arXiv:2101.11174 , year=","work_id":"efe8dd9b-b9ec-4c2c-bc6f-7e05eb541027","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Vasantha Kumar and Lelitha Vanajakshi","work_id":"2ee94aba-dd76-4826-801e-de763f5b117f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":19,"snapshot_sha256":"08e6e34e02cfb6f35ebc5e0da746e24f3dafcea3ee96feacd63a5e70977b4756","internal_anchors":4},"formal_canon":{"evidence_count":1,"snapshot_sha256":"c436ccf6bd3e0d5666c922d994f69b72f37b6474cb33adcd052b448ff17f295b"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"cf94adc9-08d2-487a-acb0-1a0a05bd3c9a"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ma9W5Wvoh+9x+h1+4u7IZuYrzCviRrOMQsKcLkvnTuLhMIjoa9j8hOaBLnqSsH8NzxrcMtjlbgx0p8Q04C+aCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:46:00.432892Z"},"content_sha256":"e9060446c1bfee4ee70a8e990720ed66ad8b2d4f2f7f1336602f9d8bc29acab1","schema_version":"1.0","event_id":"sha256:e9060446c1bfee4ee70a8e990720ed66ad8b2d4f2f7f1336602f9d8bc29acab1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/77CWFXTVI3EJRWRNSBE7GCRZQD/bundle.json","state_url":"https://pith.science/pith/77CWFXTVI3EJRWRNSBE7GCRZQD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/77CWFXTVI3EJRWRNSBE7GCRZQD/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":"2026-05-31T07:46:00Z","links":{"resolver":"https://pith.science/pith/77CWFXTVI3EJRWRNSBE7GCRZQD","bundle":"https://pith.science/pith/77CWFXTVI3EJRWRNSBE7GCRZQD/bundle.json","state":"https://pith.science/pith/77CWFXTVI3EJRWRNSBE7GCRZQD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/77CWFXTVI3EJRWRNSBE7GCRZQD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:77CWFXTVI3EJRWRNSBE7GCRZQD","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":"6c27b79cc89b971998ae8d6b5983b4405bcb61a7dac2e2dc18b11cf612006c0a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T00:28:59Z","title_canon_sha256":"b970e7064f8320dd982bf9fa052702e42ab35b5fa701c9d055cca72f32c72309"},"schema_version":"1.0","source":{"id":"2605.16726","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16726","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16726v1","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16726","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"pith_short_12","alias_value":"77CWFXTVI3EJ","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"pith_short_16","alias_value":"77CWFXTVI3EJRWRN","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"pith_short_8","alias_value":"77CWFXTV","created_at":"2026-05-20T00:02:38Z"}],"graph_snapshots":[{"event_id":"sha256:e9060446c1bfee4ee70a8e990720ed66ad8b2d4f2f7f1336602f9d8bc29acab1","target":"graph","created_at":"2026-05-20T00:02:38Z","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":"Experiments on two real-world traffic datasets show that GLGAT can effectively capture spatio-temporal correlations and has competitive performance against other state-of-the-art baselines."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The premise that traffic vertices have sufficiently different characters to justify separate global and per-vertex local attention matrices, and that an event-based adjacency matrix will reliably encode the relevant spatio-temporal dependencies without introducing bias."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"GLGAT uses global-local graph attention with pairwise encoding and event-based adjacency to capture spatio-temporal traffic correlations and reports competitive results on two real-world datasets."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"GLGAT lets traffic nodes share a global attention matrix while each gets its own local one to model distinct behaviors."}],"snapshot_sha256":"d6fc71a732465e6854554b53c362e86a782622b6145007645fb77312a58b8b03"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"c436ccf6bd3e0d5666c922d994f69b72f37b6474cb33adcd052b448ff17f295b"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T22:01:23.088632Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T21:51:05.314135Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.347082Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.472405Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16726/integrity.json","findings":[],"snapshot_sha256":"96087c1422aa660a333721b69df4868e4db611151c9b60bbf46f6656d556e6f2","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traffic forecasting is a significant part of intelligent transportation systems. One of the critical challenges of traffic forecasting is to find spatio-temporal correlations. In recent years, graph convolutional networks and graph attention networks have replaced traditional statistical models to predict future traffic. However, it is complicated for both of them to allow vertices to have far different characters. To address this, we propose the Global-Local Graph Attention Network (GLGAT) with pairwise encoding and the event-based adjacency matrix. The GLGAT allows vertices to have a global ","authors_text":"Tianchi Zhang","cross_cats":[],"headline":"GLGAT lets traffic nodes share a global attention matrix while each gets its own local one to model distinct behaviors.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T00:28:59Z","title":"A Global-Local Graph Attention Network for Traffic Forecasting"},"references":{"count":19,"internal_anchors":4,"resolved_work":19,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"page 1–17, Jul 2021","work_id":"2f55f036-eeed-42a0-a508-dad74ca2565e","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Ross Girshick. Fast r-cnn. InProceedings of the IEEE inter- national conference on computer vision, pages 1440–1448,","work_id":"0fbe78b2-1adc-41ba-81e6-17509f12a5ef","year":null},{"cited_arxiv_id":"1606.08415","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Gaussian Error Linear Units (GELUs)","work_id":"0466fd22-03a1-4a61-af0a-a900e77bb023","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"arXiv preprint arXiv:2101.11174 , year=","work_id":"efe8dd9b-b9ec-4c2c-bc6f-7e05eb541027","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Vasantha Kumar and Lelitha Vanajakshi","work_id":"2ee94aba-dd76-4826-801e-de763f5b117f","year":null}],"snapshot_sha256":"08e6e34e02cfb6f35ebc5e0da746e24f3dafcea3ee96feacd63a5e70977b4756"},"source":{"id":"2605.16726","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T21:39:05.552647Z","id":"cf94adc9-08d2-487a-acb0-1a0a05bd3c9a","model_set":{"reader":"grok-4.3"},"one_line_summary":"GLGAT uses global-local graph attention with pairwise encoding and event-based adjacency to capture spatio-temporal traffic correlations and reports competitive results on two real-world datasets.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"GLGAT lets traffic nodes share a global attention matrix while each gets its own local one to model distinct behaviors.","strongest_claim":"Experiments on two real-world traffic datasets show that GLGAT can effectively capture spatio-temporal correlations and has competitive performance against other state-of-the-art baselines.","weakest_assumption":"The premise that traffic vertices have sufficiently different characters to justify separate global and per-vertex local attention matrices, and that an event-based adjacency matrix will reliably encode the relevant spatio-temporal dependencies without introducing bias."}},"verdict_id":"cf94adc9-08d2-487a-acb0-1a0a05bd3c9a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2c331033aa61805b65d5676525771c13d6a833cab0a22bb9709258923f9d7afd","target":"record","created_at":"2026-05-20T00:02:38Z","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":"6c27b79cc89b971998ae8d6b5983b4405bcb61a7dac2e2dc18b11cf612006c0a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T00:28:59Z","title_canon_sha256":"b970e7064f8320dd982bf9fa052702e42ab35b5fa701c9d055cca72f32c72309"},"schema_version":"1.0","source":{"id":"2605.16726","kind":"arxiv","version":1}},"canonical_sha256":"ffc562de7546c898da2d9049f30a3980d1de148704e0f267fc47433d70cdeac4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffc562de7546c898da2d9049f30a3980d1de148704e0f267fc47433d70cdeac4","first_computed_at":"2026-05-20T00:02:38.626729Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:38.626729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/jdug+cQACpFGylQX0TG7xGCXlgNv+XaqASG9nuvzVDpGpxd7xi3CFfAFe+b3PRYch7w9l63AHUHbG4i36aODA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:38.627585Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16726","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c331033aa61805b65d5676525771c13d6a833cab0a22bb9709258923f9d7afd","sha256:e9060446c1bfee4ee70a8e990720ed66ad8b2d4f2f7f1336602f9d8bc29acab1"],"state_sha256":"72262ad7fe78f03238fc5a680cbe8f081831a50fdd0a693eed79d5a6a4f4f123"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qsw4r2m74ddfhq8yU03e/k8Dmbv29eMfB3SlJunytsrrhOPrM5cA6v5Rfa/gwrb0EJVO0GHx6iA4BmMXHF6aCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T07:46:00.437662Z","bundle_sha256":"9c66eb119e43a872774e3a85b7539c804ecab2e2c7dafe6f6f650d5ba7080833"}}