{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VQBYAW5ALV6XF6WIYUYBIZKO5R","short_pith_number":"pith:VQBYAW5A","canonical_record":{"source":{"id":"2605.16716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T00:01:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c941abc9879edb168c4ecce86a628b9baa3de91ef7268649d876e03dde1053bd","abstract_canon_sha256":"8a7609e0d0ec8f464314d08bda316e7f85971cb4b352f29f3b11655349af9923"},"schema_version":"1.0"},"canonical_sha256":"ac03805ba05d7d72fac8c53014654eec5d214a3d9dec9d5481c96d385e240c62","source":{"kind":"arxiv","id":"2605.16716","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16716","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16716v1","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16716","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"pith_short_12","alias_value":"VQBYAW5ALV6X","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"pith_short_16","alias_value":"VQBYAW5ALV6XF6WI","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"pith_short_8","alias_value":"VQBYAW5A","created_at":"2026-05-20T00:02:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VQBYAW5ALV6XF6WIYUYBIZKO5R","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T00:01:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c941abc9879edb168c4ecce86a628b9baa3de91ef7268649d876e03dde1053bd","abstract_canon_sha256":"8a7609e0d0ec8f464314d08bda316e7f85971cb4b352f29f3b11655349af9923"},"schema_version":"1.0"},"canonical_sha256":"ac03805ba05d7d72fac8c53014654eec5d214a3d9dec9d5481c96d385e240c62","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:38.117024Z","signature_b64":"aeBLoGgjIsiB4Fb0OfuAkelZCJoogLWyDMZIxOBPB93NOMn1VbtFNI9Mbiw5kTtwlPR3KpErTdMbmT9nqWRmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac03805ba05d7d72fac8c53014654eec5d214a3d9dec9d5481c96d385e240c62","last_reissued_at":"2026-05-20T00:02:38.116117Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:38.116117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16716","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":"nhELdT626cBGKIBzjs8BpVsz5NJb0MffTQsxHpZNvNvTxXJYWrv4U48gUlJsyWZa8ESqvwkMGGQQFYeOKYmXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T08:32:48.434668Z"},"content_sha256":"d377879c20b9a37d097eb53fb9f3ac22011f928e47b33eb8f00b2abb1e1a0f23","schema_version":"1.0","event_id":"sha256:d377879c20b9a37d097eb53fb9f3ac22011f928e47b33eb8f00b2abb1e1a0f23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VQBYAW5ALV6XF6WIYUYBIZKO5R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MAVEN A Multi-Agent Framework for Multicultural Text-to-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Multi-agent refinement of text prompts raises cultural fidelity in generated videos.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Oana Ignat, Parth Bhalerao, Shuowei Li, Yuming Zhao","submitted_at":"2026-05-16T00:01:18Z","abstract_excerpt":"Text-to-video (T2V) generation has rapidly progressed in visual fidelity, yet its ability to faithfully represent multiple cultures within a single prompt remains underexplored. We introduce MAVEN, a multi-agent prompt refinement framework designed to improve cultural fidelity in both mono-cultural and cross-cultural T2V generation. MAVEN decomposes prompts into person, action, and location dimensions, handled by specialized agents operating in parallel or sequentially. To support systematic evaluation, we contribute a new benchmark of 243 culturally grounded prompts and 972 corresponding vide"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Multi-agent refinement, particularly parallel specialization, significantly improves cultural relevance while preserving visual quality and temporal consistency.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That decomposing prompts into person, action, and location dimensions and assigning them to specialized agents will reliably increase cultural fidelity without introducing new inconsistencies or biases that the chosen metrics fail to detect.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MAVEN is a multi-agent prompt refinement framework that improves cultural fidelity in text-to-video generation, demonstrated on a new benchmark of 243 prompts and 972 videos across Chinese, American, and Romanian cultures.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multi-agent refinement of text prompts raises cultural fidelity in generated videos.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8b44a3462c06aaa92142228183016397d0c35870a36ff3c0dbe00deff2b3821f"},"source":{"id":"2605.16716","kind":"arxiv","version":1},"verdict":{"id":"4e8ac0c1-b9bf-406a-a9a4-3f5cd522fa6a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T21:55:16.376385Z","strongest_claim":"Multi-agent refinement, particularly parallel specialization, significantly improves cultural relevance while preserving visual quality and temporal consistency.","one_line_summary":"MAVEN is a multi-agent prompt refinement framework that improves cultural fidelity in text-to-video generation, demonstrated on a new benchmark of 243 prompts and 972 videos across Chinese, American, and Romanian cultures.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That decomposing prompts into person, action, and location dimensions and assigning them to specialized agents will reliably increase cultural fidelity without introducing new inconsistencies or biases that the chosen metrics fail to detect.","pith_extraction_headline":"Multi-agent refinement of text prompts raises cultural fidelity in generated videos."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16716/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T22:01:23.116692Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T22:01:03.023129Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.354562Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.478640Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"1260a16813101ca09f5ed913569266eb1711a4c234de918bc56dbc5c21468d1d"},"references":{"count":21,"sample":[{"doi":"","year":2025,"title":"SimCityNet: Quanti- fying Geo-Cultural bias in AI-generated urban videos through interpretable scene embeddings. SSRN. Ac- cessed 2025-10-10. Yubin Chen, Xuyang Guo, Zhenmei Shi, Zhao Song, and Jiahao","work_id":"daa363c3-35e9-4b6e-a694-89c4856d9ab5","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Google DeepMind","work_id":"8dbb4c54-6562-4bd1-9af7-79df43942e6d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","ref_index":3,"cited_arxiv_id":"2407.21783","is_internal_anchor":true},{"doi":"","year":null,"title":"Storyagent: Customized storytelling video generation via multi-agent collaboration","work_id":"d989b19d-4134-4b76-a09f-cc1e4b0e579e","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Sam Ade Jacobs, Masahiro Tanaka, Chengming Zhang, Minjia Zhang, Shuaiwen Leon Song, Samyam Rajbhandari, and Yuxiong He","work_id":"edd66998-17b7-45c3-b89b-4ddbbc9f3a96","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":21,"snapshot_sha256":"8851461f36b646ea7c1df81e13e8dfaf958f2cb8bcdcf7374580ec073a29fc40","internal_anchors":2},"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":"4e8ac0c1-b9bf-406a-a9a4-3f5cd522fa6a"},"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":"1ZNLYQdYmzW9J8Qd4IrwBwXRfg5beT+YYLQoIPskPzzH3vyP1GXqMmjiEG7dBdTQKvOKbuVwu56LrDEnKhqPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T08:32:48.435732Z"},"content_sha256":"4e5a27021eef1df5e8f21394b2a4742bb62cba1ad552fae3bc9c270178f7c29a","schema_version":"1.0","event_id":"sha256:4e5a27021eef1df5e8f21394b2a4742bb62cba1ad552fae3bc9c270178f7c29a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VQBYAW5ALV6XF6WIYUYBIZKO5R/bundle.json","state_url":"https://pith.science/pith/VQBYAW5ALV6XF6WIYUYBIZKO5R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VQBYAW5ALV6XF6WIYUYBIZKO5R/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":"2026-05-27T08:32:48Z","links":{"resolver":"https://pith.science/pith/VQBYAW5ALV6XF6WIYUYBIZKO5R","bundle":"https://pith.science/pith/VQBYAW5ALV6XF6WIYUYBIZKO5R/bundle.json","state":"https://pith.science/pith/VQBYAW5ALV6XF6WIYUYBIZKO5R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VQBYAW5ALV6XF6WIYUYBIZKO5R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VQBYAW5ALV6XF6WIYUYBIZKO5R","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":"8a7609e0d0ec8f464314d08bda316e7f85971cb4b352f29f3b11655349af9923","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T00:01:18Z","title_canon_sha256":"c941abc9879edb168c4ecce86a628b9baa3de91ef7268649d876e03dde1053bd"},"schema_version":"1.0","source":{"id":"2605.16716","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16716","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16716v1","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16716","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"pith_short_12","alias_value":"VQBYAW5ALV6X","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"pith_short_16","alias_value":"VQBYAW5ALV6XF6WI","created_at":"2026-05-20T00:02:38Z"},{"alias_kind":"pith_short_8","alias_value":"VQBYAW5A","created_at":"2026-05-20T00:02:38Z"}],"graph_snapshots":[{"event_id":"sha256:4e5a27021eef1df5e8f21394b2a4742bb62cba1ad552fae3bc9c270178f7c29a","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":"Multi-agent refinement, particularly parallel specialization, significantly improves cultural relevance while preserving visual quality and temporal consistency."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That decomposing prompts into person, action, and location dimensions and assigning them to specialized agents will reliably increase cultural fidelity without introducing new inconsistencies or biases that the chosen metrics fail to detect."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MAVEN is a multi-agent prompt refinement framework that improves cultural fidelity in text-to-video generation, demonstrated on a new benchmark of 243 prompts and 972 videos across Chinese, American, and Romanian cultures."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Multi-agent refinement of text prompts raises cultural fidelity in generated videos."}],"snapshot_sha256":"8b44a3462c06aaa92142228183016397d0c35870a36ff3c0dbe00deff2b3821f"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T22:01:23.116692Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T22:01:03.023129Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.354562Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.478640Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16716/integrity.json","findings":[],"snapshot_sha256":"1260a16813101ca09f5ed913569266eb1711a4c234de918bc56dbc5c21468d1d","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-video (T2V) generation has rapidly progressed in visual fidelity, yet its ability to faithfully represent multiple cultures within a single prompt remains underexplored. We introduce MAVEN, a multi-agent prompt refinement framework designed to improve cultural fidelity in both mono-cultural and cross-cultural T2V generation. MAVEN decomposes prompts into person, action, and location dimensions, handled by specialized agents operating in parallel or sequentially. To support systematic evaluation, we contribute a new benchmark of 243 culturally grounded prompts and 972 corresponding vide","authors_text":"Oana Ignat, Parth Bhalerao, Shuowei Li, Yuming Zhao","cross_cats":["cs.AI"],"headline":"Multi-agent refinement of text prompts raises cultural fidelity in generated videos.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T00:01:18Z","title":"MAVEN A Multi-Agent Framework for Multicultural Text-to-Video Generation"},"references":{"count":21,"internal_anchors":2,"resolved_work":21,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"SimCityNet: Quanti- fying Geo-Cultural bias in AI-generated urban videos through interpretable scene embeddings. SSRN. Ac- cessed 2025-10-10. Yubin Chen, Xuyang Guo, Zhenmei Shi, Zhao Song, and Jiahao","work_id":"daa363c3-35e9-4b6e-a694-89c4856d9ab5","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Google DeepMind","work_id":"8dbb4c54-6562-4bd1-9af7-79df43942e6d","year":null},{"cited_arxiv_id":"2407.21783","doi":"","is_internal_anchor":true,"ref_index":3,"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Storyagent: Customized storytelling video generation via multi-agent collaboration","work_id":"d989b19d-4134-4b76-a09f-cc1e4b0e579e","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Sam Ade Jacobs, Masahiro Tanaka, Chengming Zhang, Minjia Zhang, Shuaiwen Leon Song, Samyam Rajbhandari, and Yuxiong He","work_id":"edd66998-17b7-45c3-b89b-4ddbbc9f3a96","year":null}],"snapshot_sha256":"8851461f36b646ea7c1df81e13e8dfaf958f2cb8bcdcf7374580ec073a29fc40"},"source":{"id":"2605.16716","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T21:55:16.376385Z","id":"4e8ac0c1-b9bf-406a-a9a4-3f5cd522fa6a","model_set":{"reader":"grok-4.3"},"one_line_summary":"MAVEN is a multi-agent prompt refinement framework that improves cultural fidelity in text-to-video generation, demonstrated on a new benchmark of 243 prompts and 972 videos across Chinese, American, and Romanian cultures.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Multi-agent refinement of text prompts raises cultural fidelity in generated videos.","strongest_claim":"Multi-agent refinement, particularly parallel specialization, significantly improves cultural relevance while preserving visual quality and temporal consistency.","weakest_assumption":"That decomposing prompts into person, action, and location dimensions and assigning them to specialized agents will reliably increase cultural fidelity without introducing new inconsistencies or biases that the chosen metrics fail to detect."}},"verdict_id":"4e8ac0c1-b9bf-406a-a9a4-3f5cd522fa6a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d377879c20b9a37d097eb53fb9f3ac22011f928e47b33eb8f00b2abb1e1a0f23","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":"8a7609e0d0ec8f464314d08bda316e7f85971cb4b352f29f3b11655349af9923","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T00:01:18Z","title_canon_sha256":"c941abc9879edb168c4ecce86a628b9baa3de91ef7268649d876e03dde1053bd"},"schema_version":"1.0","source":{"id":"2605.16716","kind":"arxiv","version":1}},"canonical_sha256":"ac03805ba05d7d72fac8c53014654eec5d214a3d9dec9d5481c96d385e240c62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac03805ba05d7d72fac8c53014654eec5d214a3d9dec9d5481c96d385e240c62","first_computed_at":"2026-05-20T00:02:38.116117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:38.116117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aeBLoGgjIsiB4Fb0OfuAkelZCJoogLWyDMZIxOBPB93NOMn1VbtFNI9Mbiw5kTtwlPR3KpErTdMbmT9nqWRmBg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:38.117024Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16716","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d377879c20b9a37d097eb53fb9f3ac22011f928e47b33eb8f00b2abb1e1a0f23","sha256:4e5a27021eef1df5e8f21394b2a4742bb62cba1ad552fae3bc9c270178f7c29a"],"state_sha256":"cbd90105a65cc4dba5e1fb25741b6dd24a836fa26ef9cabd691d35a29375f0bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xKrKSYlaZybrWhQ5PDtHghQV3Py/0V8TPdPvpMJlxa4OFJuR/7PegZzVNGa2P/d+kjoQm20PoVkkXH3Lq+LlAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T08:32:48.440310Z","bundle_sha256":"446395f4d706b44c5676e86757dd0bb4e71302decfe7d7d1388e79453eec41d4"}}