{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7JHGNWMEYH5MUOX4NK37ME2ZTH","short_pith_number":"pith:7JHGNWME","canonical_record":{"source":{"id":"2605.17721","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T00:50:23Z","cross_cats_sorted":[],"title_canon_sha256":"844b992d5f99c159fcee93aaf09b8a383b20db22f0f4365b69b7274bc202854c","abstract_canon_sha256":"ae0bb3398c8e4d58bd1672119b639ce3244c9a16f87f9f2b63154c5c7d459eb3"},"schema_version":"1.0"},"canonical_sha256":"fa4e66d984c1faca3afc6ab7f6135999eff337b75ff4d05ec414765328fc0b03","source":{"kind":"arxiv","id":"2605.17721","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17721","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17721v1","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17721","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"7JHGNWMEYH5M","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"7JHGNWMEYH5MUOX4","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"7JHGNWME","created_at":"2026-05-20T00:04:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7JHGNWMEYH5MUOX4NK37ME2ZTH","target":"record","payload":{"canonical_record":{"source":{"id":"2605.17721","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T00:50:23Z","cross_cats_sorted":[],"title_canon_sha256":"844b992d5f99c159fcee93aaf09b8a383b20db22f0f4365b69b7274bc202854c","abstract_canon_sha256":"ae0bb3398c8e4d58bd1672119b639ce3244c9a16f87f9f2b63154c5c7d459eb3"},"schema_version":"1.0"},"canonical_sha256":"fa4e66d984c1faca3afc6ab7f6135999eff337b75ff4d05ec414765328fc0b03","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:54.753050Z","signature_b64":"q32ppDMuHjxr6bZKmPm37RSt5EFJA82MvP1mW+mJOXXxs9JvpiRZG3w9NQcJAjwxCwyYgJnqnq97o+ocTUQmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa4e66d984c1faca3afc6ab7f6135999eff337b75ff4d05ec414765328fc0b03","last_reissued_at":"2026-05-20T00:04:54.752182Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:54.752182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.17721","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":"2026-05-20T00:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fWNPMCNmGUvRz/DdF79ETBxGPLS6QyOSVtkEBisS/g0JZNM6K3DVqpqDIPkQM6WhqZZwWbuZn23kT18dReyuCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T14:58:39.105983Z"},"content_sha256":"6ab24bd91e658e29ab2e493473aa24d2a2b63f639fb161e4bedba8126a72159d","schema_version":"1.0","event_id":"sha256:6ab24bd91e658e29ab2e493473aa24d2a2b63f639fb161e4bedba8126a72159d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7JHGNWMEYH5MUOX4NK37ME2ZTH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EXG: Self-Evolving Agents with Experience Graphs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"EXG turns agent successes and failures into a connected graph for instant reuse across tasks.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hanchen Wang, Lu Qin, Siyuan Zhang, Wenjie Zhang, Ying Zhang, Yuxin Jin","submitted_at":"2026-05-18T00:50:23Z","abstract_excerpt":"Large language model (LLM)-based agents have demonstrated strong capabilities in complex reasoning and problem solving through multi-step interactions, yet most deployed agents remain behaviorally static, with knowledge acquired during execution rarely translating into systematic improvement over time. In response, a growing line of work on self-evolving agents explores how agents can improve through experience during deployment, but most existing approaches either rely on ad hoc reflection limited to single-task correction or adopt unstructured memory that accumulates fragmented experience wi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"EXG is the first experience graph designed for self-evolving agents, supporting both online, real-time graph growth during execution for immediate cross-task experience reuse, and offline reuse of a consolidated experience graph as an external memory module.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That successes and failures accumulated during agent execution can be effectively captured and related in a graph structure that enables immediate and transferable reuse without fragmentation or high overhead, as positioned against ad hoc reflection and unstructured memory in the abstract.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"EXG is an experience graph framework for self-evolving LLM agents that supports online real-time growth and offline reuse to enhance solution quality and efficiency on code generation and reasoning benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"EXG turns agent successes and failures into a connected graph for instant reuse across tasks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a95eda3b9c47fbce5b14300f7eb3f8d82c6a29cd0697419527365f42028c7a02"},"source":{"id":"2605.17721","kind":"arxiv","version":1},"verdict":{"id":"6eaeec59-e9f3-460f-846a-f85d31164ead","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T22:14:02.846903Z","strongest_claim":"EXG is the first experience graph designed for self-evolving agents, supporting both online, real-time graph growth during execution for immediate cross-task experience reuse, and offline reuse of a consolidated experience graph as an external memory module.","one_line_summary":"EXG is an experience graph framework for self-evolving LLM agents that supports online real-time growth and offline reuse to enhance solution quality and efficiency on code generation and reasoning benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That successes and failures accumulated during agent execution can be effectively captured and related in a graph structure that enables immediate and transferable reuse without fragmentation or high overhead, as positioned against ad hoc reflection and unstructured memory in the abstract.","pith_extraction_headline":"EXG turns agent successes and failures into a connected graph for instant reuse across tasks."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17721/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T22:31:19.378207Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T22:20:57.052636Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"shingle_duplication","ran_at":"2026-05-19T21:49:43.466689Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T21:49:43.296092Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.500082Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T21:21:57.418662Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.401990Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d2ec0e0fd6c563033c9644a79d36847c319fe0539fda8a4156306b113c039074"},"references":{"count":56,"sample":[{"doi":"","year":2025,"title":"MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems","work_id":"eaff38e0-7f83-4800-aa64-f8687ace2302","ref_index":1,"cited_arxiv_id":"2510.17281","is_internal_anchor":true},{"doi":"","year":2025,"title":"FLEX: Continuous agent evolution via forward learning from experience","work_id":"20c70353-cdc5-4bb5-806a-59181ff4fbdf","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution","work_id":"e1808e0d-921b-46dd-b221-96110080aa71","ref_index":3,"cited_arxiv_id":"2512.10696","is_internal_anchor":true},{"doi":"","year":2021,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","ref_index":4,"cited_arxiv_id":"2107.03374","is_internal_anchor":true},{"doi":"","year":null,"title":"Jizhan Fang, Xinle Deng, Haoming Xu, Ziyan Jiang, Yuqi Tang, Ziwen Xu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Huajun Chen, and Ningyu Zhang","work_id":"27b895a0-0661-4820-b6da-406212444530","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":56,"snapshot_sha256":"7d2273352019d635d4e3d85a4ae213b9ffc8d116a0dab4655f555f46d1545a24","internal_anchors":19},"formal_canon":{"evidence_count":2,"snapshot_sha256":"a3e372c84bb742fc9ee2486bfa5ed6ac65f4fb9db2f14d20072aba82e4f103e9"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"6eaeec59-e9f3-460f-846a-f85d31164ead"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BeWZx2JZnOAs5PZ87w1GrsGIhCcfaDIqnfEYQnhkdPfh9hg3rBgJeFyO6O42V4UPAqvlqnjKbdxlKTNtAyOfBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T14:58:39.106631Z"},"content_sha256":"4c952fba71e49d1d2cac1a25a1a6d785423299be4a50d6f19183fa1d8c315530","schema_version":"1.0","event_id":"sha256:4c952fba71e49d1d2cac1a25a1a6d785423299be4a50d6f19183fa1d8c315530"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7JHGNWMEYH5MUOX4NK37ME2ZTH/bundle.json","state_url":"https://pith.science/pith/7JHGNWMEYH5MUOX4NK37ME2ZTH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7JHGNWMEYH5MUOX4NK37ME2ZTH/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":"2026-05-21T14:58:39Z","links":{"resolver":"https://pith.science/pith/7JHGNWMEYH5MUOX4NK37ME2ZTH","bundle":"https://pith.science/pith/7JHGNWMEYH5MUOX4NK37ME2ZTH/bundle.json","state":"https://pith.science/pith/7JHGNWMEYH5MUOX4NK37ME2ZTH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7JHGNWMEYH5MUOX4NK37ME2ZTH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7JHGNWMEYH5MUOX4NK37ME2ZTH","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":"ae0bb3398c8e4d58bd1672119b639ce3244c9a16f87f9f2b63154c5c7d459eb3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T00:50:23Z","title_canon_sha256":"844b992d5f99c159fcee93aaf09b8a383b20db22f0f4365b69b7274bc202854c"},"schema_version":"1.0","source":{"id":"2605.17721","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17721","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17721v1","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17721","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"7JHGNWMEYH5M","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"7JHGNWMEYH5MUOX4","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"7JHGNWME","created_at":"2026-05-20T00:04:54Z"}],"graph_snapshots":[{"event_id":"sha256:4c952fba71e49d1d2cac1a25a1a6d785423299be4a50d6f19183fa1d8c315530","target":"graph","created_at":"2026-05-20T00:04:54Z","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":"EXG is the first experience graph designed for self-evolving agents, supporting both online, real-time graph growth during execution for immediate cross-task experience reuse, and offline reuse of a consolidated experience graph as an external memory module."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That successes and failures accumulated during agent execution can be effectively captured and related in a graph structure that enables immediate and transferable reuse without fragmentation or high overhead, as positioned against ad hoc reflection and unstructured memory in the abstract."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"EXG is an experience graph framework for self-evolving LLM agents that supports online real-time growth and offline reuse to enhance solution quality and efficiency on code generation and reasoning benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"EXG turns agent successes and failures into a connected graph for instant reuse across tasks."}],"snapshot_sha256":"a95eda3b9c47fbce5b14300f7eb3f8d82c6a29cd0697419527365f42028c7a02"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"a3e372c84bb742fc9ee2486bfa5ed6ac65f4fb9db2f14d20072aba82e4f103e9"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T22:31:19.378207Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T22:20:57.052636Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"shingle_duplication","ran_at":"2026-05-19T21:49:43.466689Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T21:49:43.296092Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.500082Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T21:21:57.418662Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.401990Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.17721/integrity.json","findings":[],"snapshot_sha256":"d2ec0e0fd6c563033c9644a79d36847c319fe0539fda8a4156306b113c039074","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM)-based agents have demonstrated strong capabilities in complex reasoning and problem solving through multi-step interactions, yet most deployed agents remain behaviorally static, with knowledge acquired during execution rarely translating into systematic improvement over time. In response, a growing line of work on self-evolving agents explores how agents can improve through experience during deployment, but most existing approaches either rely on ad hoc reflection limited to single-task correction or adopt unstructured memory that accumulates fragmented experience wi","authors_text":"Hanchen Wang, Lu Qin, Siyuan Zhang, Wenjie Zhang, Ying Zhang, Yuxin Jin","cross_cats":[],"headline":"EXG turns agent successes and failures into a connected graph for instant reuse across tasks.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T00:50:23Z","title":"EXG: Self-Evolving Agents with Experience Graphs"},"references":{"count":56,"internal_anchors":19,"resolved_work":56,"sample":[{"cited_arxiv_id":"2510.17281","doi":"","is_internal_anchor":true,"ref_index":1,"title":"MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems","work_id":"eaff38e0-7f83-4800-aa64-f8687ace2302","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"FLEX: Continuous agent evolution via forward learning from experience","work_id":"20c70353-cdc5-4bb5-806a-59181ff4fbdf","year":2025},{"cited_arxiv_id":"2512.10696","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution","work_id":"e1808e0d-921b-46dd-b221-96110080aa71","year":2025},{"cited_arxiv_id":"2107.03374","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Jizhan Fang, Xinle Deng, Haoming Xu, Ziyan Jiang, Yuqi Tang, Ziwen Xu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Huajun Chen, and Ningyu Zhang","work_id":"27b895a0-0661-4820-b6da-406212444530","year":null}],"snapshot_sha256":"7d2273352019d635d4e3d85a4ae213b9ffc8d116a0dab4655f555f46d1545a24"},"source":{"id":"2605.17721","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T22:14:02.846903Z","id":"6eaeec59-e9f3-460f-846a-f85d31164ead","model_set":{"reader":"grok-4.3"},"one_line_summary":"EXG is an experience graph framework for self-evolving LLM agents that supports online real-time growth and offline reuse to enhance solution quality and efficiency on code generation and reasoning benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"EXG turns agent successes and failures into a connected graph for instant reuse across tasks.","strongest_claim":"EXG is the first experience graph designed for self-evolving agents, supporting both online, real-time graph growth during execution for immediate cross-task experience reuse, and offline reuse of a consolidated experience graph as an external memory module.","weakest_assumption":"That successes and failures accumulated during agent execution can be effectively captured and related in a graph structure that enables immediate and transferable reuse without fragmentation or high overhead, as positioned against ad hoc reflection and unstructured memory in the abstract."}},"verdict_id":"6eaeec59-e9f3-460f-846a-f85d31164ead"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6ab24bd91e658e29ab2e493473aa24d2a2b63f639fb161e4bedba8126a72159d","target":"record","created_at":"2026-05-20T00:04:54Z","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":"ae0bb3398c8e4d58bd1672119b639ce3244c9a16f87f9f2b63154c5c7d459eb3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T00:50:23Z","title_canon_sha256":"844b992d5f99c159fcee93aaf09b8a383b20db22f0f4365b69b7274bc202854c"},"schema_version":"1.0","source":{"id":"2605.17721","kind":"arxiv","version":1}},"canonical_sha256":"fa4e66d984c1faca3afc6ab7f6135999eff337b75ff4d05ec414765328fc0b03","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa4e66d984c1faca3afc6ab7f6135999eff337b75ff4d05ec414765328fc0b03","first_computed_at":"2026-05-20T00:04:54.752182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:54.752182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q32ppDMuHjxr6bZKmPm37RSt5EFJA82MvP1mW+mJOXXxs9JvpiRZG3w9NQcJAjwxCwyYgJnqnq97o+ocTUQmBA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:54.753050Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17721","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ab24bd91e658e29ab2e493473aa24d2a2b63f639fb161e4bedba8126a72159d","sha256:4c952fba71e49d1d2cac1a25a1a6d785423299be4a50d6f19183fa1d8c315530"],"state_sha256":"7ae85c3b36849c40448f944492ef56cf7dae81fb3babbe8ab5f0efbe79b437bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Tq9qZPO1j6qu06E9Nf/dLYbs+R0IYdX57it/5hkBtG8wdNmxY9le9r4AsnZcEjbn2VtE66AVfEMPSURknNEDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T14:58:39.112760Z","bundle_sha256":"5f4ea97481e634e43ac75f35faff4dfa46ead5b7147352ff4d2c451c89469625"}}