{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:I2BQMU3KISPFTYXGLUVD3I6UNA","short_pith_number":"pith:I2BQMU3K","canonical_record":{"source":{"id":"2605.15223","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-05-13T08:36:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"016d8cf3e9bf4775714ec4dfe96b4fa697b28c85419d43905541f25edbb63400","abstract_canon_sha256":"1f50dd57a15b5d7238e4e18cf9f1531ca50cc56d19ba9c00965abbec75636956"},"schema_version":"1.0"},"canonical_sha256":"468306536a449e59e2e65d2a3da3d4681ead69dac5497abdd06b400e522ceb91","source":{"kind":"arxiv","id":"2605.15223","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15223","created_at":"2026-05-20T00:00:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15223v1","created_at":"2026-05-20T00:00:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15223","created_at":"2026-05-20T00:00:47Z"},{"alias_kind":"pith_short_12","alias_value":"I2BQMU3KISPF","created_at":"2026-05-20T00:00:47Z"},{"alias_kind":"pith_short_16","alias_value":"I2BQMU3KISPFTYXG","created_at":"2026-05-20T00:00:47Z"},{"alias_kind":"pith_short_8","alias_value":"I2BQMU3K","created_at":"2026-05-20T00:00:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:I2BQMU3KISPFTYXGLUVD3I6UNA","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15223","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-05-13T08:36:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"016d8cf3e9bf4775714ec4dfe96b4fa697b28c85419d43905541f25edbb63400","abstract_canon_sha256":"1f50dd57a15b5d7238e4e18cf9f1531ca50cc56d19ba9c00965abbec75636956"},"schema_version":"1.0"},"canonical_sha256":"468306536a449e59e2e65d2a3da3d4681ead69dac5497abdd06b400e522ceb91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:47.094535Z","signature_b64":"1af3t5oTCXguGUs9hqOUI7I6zuiuTxVc1QnNQDcSf9pJ/dN6JCWEtI8ytgQtUxEC3CiXtUahDR68Uk2NFru+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"468306536a449e59e2e65d2a3da3d4681ead69dac5497abdd06b400e522ceb91","last_reissued_at":"2026-05-20T00:00:47.093443Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:47.093443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15223","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":"2026-05-20T00:00:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0aoihwXhJoeW+8e9wkmj3VIfvz8fVA3l/u/RpkEIXLlVqq/yAoU1EIoHSOs2jlO20K6HMfdJflLpFdiJXgN4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:18:14.580936Z"},"content_sha256":"1f852c00c4bbf9305787378b438fd1a80d98b93a4cc1b8a84dd43308c4565266","schema_version":"1.0","event_id":"sha256:1f852c00c4bbf9305787378b438fd1a80d98b93a4cc1b8a84dd43308c4565266"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:I2BQMU3KISPFTYXGLUVD3I6UNA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GenAI-Driven Approach to RISC-V Supply Chain Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LLM and VLM workflow turns unstructured RISC-V supply chain data into formal models for resilience analysis.","cross_cats":["cs.AI"],"primary_cat":"cs.AR","authors_text":"Alois Knoll, Andre Schamschurko, Nenad Petrovic, Yingjie Xu","submitted_at":"2026-05-13T08:36:57Z","abstract_excerpt":"This paper presents an LLM-empowered workflow for RISC-V supply chain analysis, integrating Vision-Language Models (VLMs) and Model-Driven Engineering (MDE) to enable comprehensive, multimodal data-driven insights. The proposed approach addresses the challenges of heterogeneous and unstructured supply chain data by leveraging LLMs for textual understanding and VLMs for extracting information from visual artifacts such as diagrams, tables, and scanned documents. These models collaboratively identify key entities and relationships, which are then organized into a knowledge graph representing sup"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The synergy between LLM- and VLM-based semantic understanding and MDE-based formal analysis supports both exploratory and systematic evaluation of supply chain resilience.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That LLMs and VLMs can reliably extract accurate key entities and relationships from heterogeneous, unstructured supply chain data including visual artifacts without significant errors or hallucinations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"An LLM- and VLM-powered workflow integrated with knowledge graphs and model-driven engineering is proposed for analyzing RISC-V semiconductor supply chain data and resilience.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LLM and VLM workflow turns unstructured RISC-V supply chain data into formal models for resilience analysis.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ffe309517cba9e3b05bf72c63a3a5ff550db61e58d339bae01dba0640e3ed468"},"source":{"id":"2605.15223","kind":"arxiv","version":1},"verdict":{"id":"01d42943-60bf-4098-ab8d-89a9b241b7b1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T17:54:13.545150Z","strongest_claim":"The synergy between LLM- and VLM-based semantic understanding and MDE-based formal analysis supports both exploratory and systematic evaluation of supply chain resilience.","one_line_summary":"An LLM- and VLM-powered workflow integrated with knowledge graphs and model-driven engineering is proposed for analyzing RISC-V semiconductor supply chain data and resilience.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That LLMs and VLMs can reliably extract accurate key entities and relationships from heterogeneous, unstructured supply chain data including visual artifacts without significant errors or hallucinations.","pith_extraction_headline":"LLM and VLM workflow turns unstructured RISC-V supply chain data into formal models for resilience analysis."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15223/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T20:01:57.095311Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T18:01:24.746509Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T18:01:18.627909Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.834812Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"66d0867ff8c0169e1f5a565364c8ff69a896cbe05d88b6fdf27c9bf5dd994d57"},"references":{"count":31,"sample":[{"doi":"","year":2025,"title":"In: 2025 8th International Conference on Electronics, Materials Engineering & Nano- Technology (IEMENTech)","work_id":"b13b549e-c81c-45b6-b0a7-bec411ac8bb3","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"White paper (2025), https://riscv.org/wp-content/uploads/2025/04/ RISC-V AIOpportunitiesChallenges 042825.pdf, accessed: 2026-04-25","work_id":"ba481ba7-3f74-49c7-9b3f-10734142d819","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"In: 2023 12th Mediterranean Conference on Embedded Computing (MECO)","work_id":"85eb6bac-0a8c-483f-b774-b0e9c6cd1fe8","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"RISC-V Functional Safety for Autonomous Automotive Systems: An Analytical Framework and Research Roadmap for ML-Assisted Certification","work_id":"aa379260-5d46-422e-bf54-7eb2a3b5e4bb","ref_index":4,"cited_arxiv_id":"2604.17391","is_internal_anchor":true},{"doi":"","year":2025,"title":"In: 2025 2nd International Generative AI and Com- putational Language Modelling Conference (GACLM)","work_id":"203c3fd3-6b56-4de4-b1b4-05e2e6edb839","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":31,"snapshot_sha256":"cfe9215c5b7b470c7e76fa157680e2cf0c85db53fd80403e794ffce739d14584","internal_anchors":1},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"01d42943-60bf-4098-ab8d-89a9b241b7b1"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"myrDXyaPDpDP4Dp33grOBFquko33Wvo9ByyYOU7u5LTpuvAVPjEwd+05zoMdcz4flzEhfKdHpk5GriKQhCsWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:18:14.582079Z"},"content_sha256":"04fa7de6f949bdfe28b55a8cd3195ca91d80ebf51168fd45443f98bf86d743fb","schema_version":"1.0","event_id":"sha256:04fa7de6f949bdfe28b55a8cd3195ca91d80ebf51168fd45443f98bf86d743fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I2BQMU3KISPFTYXGLUVD3I6UNA/bundle.json","state_url":"https://pith.science/pith/I2BQMU3KISPFTYXGLUVD3I6UNA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I2BQMU3KISPFTYXGLUVD3I6UNA/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":"2026-05-26T11:18:14Z","links":{"resolver":"https://pith.science/pith/I2BQMU3KISPFTYXGLUVD3I6UNA","bundle":"https://pith.science/pith/I2BQMU3KISPFTYXGLUVD3I6UNA/bundle.json","state":"https://pith.science/pith/I2BQMU3KISPFTYXGLUVD3I6UNA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I2BQMU3KISPFTYXGLUVD3I6UNA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:I2BQMU3KISPFTYXGLUVD3I6UNA","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":"1f50dd57a15b5d7238e4e18cf9f1531ca50cc56d19ba9c00965abbec75636956","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-05-13T08:36:57Z","title_canon_sha256":"016d8cf3e9bf4775714ec4dfe96b4fa697b28c85419d43905541f25edbb63400"},"schema_version":"1.0","source":{"id":"2605.15223","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15223","created_at":"2026-05-20T00:00:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15223v1","created_at":"2026-05-20T00:00:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15223","created_at":"2026-05-20T00:00:47Z"},{"alias_kind":"pith_short_12","alias_value":"I2BQMU3KISPF","created_at":"2026-05-20T00:00:47Z"},{"alias_kind":"pith_short_16","alias_value":"I2BQMU3KISPFTYXG","created_at":"2026-05-20T00:00:47Z"},{"alias_kind":"pith_short_8","alias_value":"I2BQMU3K","created_at":"2026-05-20T00:00:47Z"}],"graph_snapshots":[{"event_id":"sha256:04fa7de6f949bdfe28b55a8cd3195ca91d80ebf51168fd45443f98bf86d743fb","target":"graph","created_at":"2026-05-20T00:00:47Z","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 synergy between LLM- and VLM-based semantic understanding and MDE-based formal analysis supports both exploratory and systematic evaluation of supply chain resilience."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That LLMs and VLMs can reliably extract accurate key entities and relationships from heterogeneous, unstructured supply chain data including visual artifacts without significant errors or hallucinations."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"An LLM- and VLM-powered workflow integrated with knowledge graphs and model-driven engineering is proposed for analyzing RISC-V semiconductor supply chain data and resilience."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"LLM and VLM workflow turns unstructured RISC-V supply chain data into formal models for resilience analysis."}],"snapshot_sha256":"ffe309517cba9e3b05bf72c63a3a5ff550db61e58d339bae01dba0640e3ed468"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T20:01:57.095311Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T18:01:24.746509Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T18:01:18.627909Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.834812Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15223/integrity.json","findings":[],"snapshot_sha256":"66d0867ff8c0169e1f5a565364c8ff69a896cbe05d88b6fdf27c9bf5dd994d57","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents an LLM-empowered workflow for RISC-V supply chain analysis, integrating Vision-Language Models (VLMs) and Model-Driven Engineering (MDE) to enable comprehensive, multimodal data-driven insights. The proposed approach addresses the challenges of heterogeneous and unstructured supply chain data by leveraging LLMs for textual understanding and VLMs for extracting information from visual artifacts such as diagrams, tables, and scanned documents. These models collaboratively identify key entities and relationships, which are then organized into a knowledge graph representing sup","authors_text":"Alois Knoll, Andre Schamschurko, Nenad Petrovic, Yingjie Xu","cross_cats":["cs.AI"],"headline":"LLM and VLM workflow turns unstructured RISC-V supply chain data into formal models for resilience analysis.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-05-13T08:36:57Z","title":"GenAI-Driven Approach to RISC-V Supply Chain Exploration"},"references":{"count":31,"internal_anchors":1,"resolved_work":31,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"In: 2025 8th International Conference on Electronics, Materials Engineering & Nano- Technology (IEMENTech)","work_id":"b13b549e-c81c-45b6-b0a7-bec411ac8bb3","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"White paper (2025), https://riscv.org/wp-content/uploads/2025/04/ RISC-V AIOpportunitiesChallenges 042825.pdf, accessed: 2026-04-25","work_id":"ba481ba7-3f74-49c7-9b3f-10734142d819","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"In: 2023 12th Mediterranean Conference on Embedded Computing (MECO)","work_id":"85eb6bac-0a8c-483f-b774-b0e9c6cd1fe8","year":2023},{"cited_arxiv_id":"2604.17391","doi":"","is_internal_anchor":true,"ref_index":4,"title":"RISC-V Functional Safety for Autonomous Automotive Systems: An Analytical Framework and Research Roadmap for ML-Assisted Certification","work_id":"aa379260-5d46-422e-bf54-7eb2a3b5e4bb","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"In: 2025 2nd International Generative AI and Com- putational Language Modelling Conference (GACLM)","work_id":"203c3fd3-6b56-4de4-b1b4-05e2e6edb839","year":2025}],"snapshot_sha256":"cfe9215c5b7b470c7e76fa157680e2cf0c85db53fd80403e794ffce739d14584"},"source":{"id":"2605.15223","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T17:54:13.545150Z","id":"01d42943-60bf-4098-ab8d-89a9b241b7b1","model_set":{"reader":"grok-4.3"},"one_line_summary":"An LLM- and VLM-powered workflow integrated with knowledge graphs and model-driven engineering is proposed for analyzing RISC-V semiconductor supply chain data and resilience.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"LLM and VLM workflow turns unstructured RISC-V supply chain data into formal models for resilience analysis.","strongest_claim":"The synergy between LLM- and VLM-based semantic understanding and MDE-based formal analysis supports both exploratory and systematic evaluation of supply chain resilience.","weakest_assumption":"That LLMs and VLMs can reliably extract accurate key entities and relationships from heterogeneous, unstructured supply chain data including visual artifacts without significant errors or hallucinations."}},"verdict_id":"01d42943-60bf-4098-ab8d-89a9b241b7b1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1f852c00c4bbf9305787378b438fd1a80d98b93a4cc1b8a84dd43308c4565266","target":"record","created_at":"2026-05-20T00:00:47Z","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":"1f50dd57a15b5d7238e4e18cf9f1531ca50cc56d19ba9c00965abbec75636956","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-05-13T08:36:57Z","title_canon_sha256":"016d8cf3e9bf4775714ec4dfe96b4fa697b28c85419d43905541f25edbb63400"},"schema_version":"1.0","source":{"id":"2605.15223","kind":"arxiv","version":1}},"canonical_sha256":"468306536a449e59e2e65d2a3da3d4681ead69dac5497abdd06b400e522ceb91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"468306536a449e59e2e65d2a3da3d4681ead69dac5497abdd06b400e522ceb91","first_computed_at":"2026-05-20T00:00:47.093443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:47.093443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1af3t5oTCXguGUs9hqOUI7I6zuiuTxVc1QnNQDcSf9pJ/dN6JCWEtI8ytgQtUxEC3CiXtUahDR68Uk2NFru+Bg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:47.094535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15223","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f852c00c4bbf9305787378b438fd1a80d98b93a4cc1b8a84dd43308c4565266","sha256:04fa7de6f949bdfe28b55a8cd3195ca91d80ebf51168fd45443f98bf86d743fb"],"state_sha256":"76a206300a5e47a544f311039f1eb432a510f59d7a209b52b99423e3539e31a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jxRY+cfW63Cda00nnniTL5bRVxISFQSdJuq3x+Cb9gGf7yVQUPhG3WA4nDBv/rdM3J6nc/UI1IMEEiGmG4CTCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T11:18:14.586426Z","bundle_sha256":"75f5078a81aede49dee13ba05f33a8d9c7b7d6c4731f2568dfb1d75461185c19"}}