{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ESR5ZBEMUI5ZKVCWR5UA3N7YSQ","short_pith_number":"pith:ESR5ZBEM","canonical_record":{"source":{"id":"2505.13211","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T14:58:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2a12493bd1c0e3529215d42d23f41bfeecef6662e6b88cf83d28362eaae5f67b","abstract_canon_sha256":"252ee3808b5c1e4d990797ee31c613f491bb3456842115351135abab295969d6"},"schema_version":"1.0"},"canonical_sha256":"24a3dc848ca23b9554568f680db7f8942cb64f40d42a6affd3c3b62293538bbe","source":{"kind":"arxiv","id":"2505.13211","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13211","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13211v1","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13211","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"ESR5ZBEMUI5Z","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"ESR5ZBEMUI5ZKVCW","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"ESR5ZBEM","created_at":"2026-07-05T11:05:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ESR5ZBEMUI5ZKVCWR5UA3N7YSQ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.13211","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T14:58:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2a12493bd1c0e3529215d42d23f41bfeecef6662e6b88cf83d28362eaae5f67b","abstract_canon_sha256":"252ee3808b5c1e4d990797ee31c613f491bb3456842115351135abab295969d6"},"schema_version":"1.0"},"canonical_sha256":"24a3dc848ca23b9554568f680db7f8942cb64f40d42a6affd3c3b62293538bbe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:26.901541Z","signature_b64":"2OBJYIkxxovkCPChQhDmK/hCvRQW5tCw4cvZ+AD2hkg+TRTDfG0Z/JrD9dN08SPws+XR//bqfomAzSNAUWL+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24a3dc848ca23b9554568f680db7f8942cb64f40d42a6affd3c3b62293538bbe","last_reissued_at":"2026-07-05T11:05:26.901031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:26.901031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.13211","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":"2026-07-05T11:05:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w7Z4pAZJpP2yA3DelZ7KCnEMNkzastRLpDGgo3B0fc2VM34YS7aJlwKQcAoN1OJj23BYXCdcrpqNrYdWNbyuAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:03:26.524404Z"},"content_sha256":"35bb815271239b18cac00c1f7a81dc573c026305fa0bd88b73d92ecbf03b7b3d","schema_version":"1.0","event_id":"sha256:35bb815271239b18cac00c1f7a81dc573c026305fa0bd88b73d92ecbf03b7b3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ESR5ZBEMUI5ZKVCWR5UA3N7YSQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MAGI-1: Autoregressive Video Generation at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MAGI-1 generates videos by autoregressively predicting fixed-length chunks of frames.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dai Shi, Guoli Su, Hansi Teng, Hanwen Sun, Hong Pan, Hongyu Jia, Jie Wang, Jiexin Sheng, Lei Sun, Lingzhi Li, Maolin Li, Min Cui, Mingqiu Tang, Ming Yan, Min Hu, Sand.ai, Shuai Han, Shucheng Yin, Siran Zhang, Tianning Zhang, Tingting Liu, Weifeng Luo, W.Q. Zhang, Xianping Yin, Xiaoyang Kang, Xiaoyu Yang, Xin Song, Xuan Hu, Yankai Zhang, Yuchen Sun, Yue Cao, Yunpeng Huang, Yuqiao Li, Yutong Lin, Yuxin Fang, Zewei Tao, Zheng Zhang, Zhongshu Wang, Zixun Liu","submitted_at":"2025-05-19T14:58:50Z","abstract_excerpt":"We present MAGI-1, a world model that generates videos by autoregressively predicting a sequence of video chunks, defined as fixed-length segments of consecutive frames. Trained to denoise per-chunk noise that increases monotonically over time, MAGI-1 enables causal temporal modeling and naturally supports streaming generation. It achieves strong performance on image-to-video (I2V) tasks conditioned on text instructions, providing high temporal consistency and scalability, which are made possible by several algorithmic innovations and a dedicated infrastructure stack. MAGI-1 facilitates contro"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MAGI-1 achieves strong performance on image-to-video tasks conditioned on text instructions, providing high temporal consistency and scalability, made possible by chunk-wise autoregressive prediction and supporting context lengths of up to 4 million tokens with a 24B parameter model.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That training to denoise per-chunk noise increasing monotonically over time is sufficient to produce causal temporal modeling and high consistency without additional mechanisms, post-processing, or architectural constraints.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MAGI-1 is a 24B-parameter autoregressive video world model that predicts denoised frame chunks sequentially with increasing noise to enable causal, scalable, streaming generation up to 4M token contexts.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MAGI-1 generates videos by autoregressively predicting fixed-length chunks of frames.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"af59b1a8a89cd5f27c413399b2efa785201e39af1afd56b14466760289fa6017"},"source":{"id":"2505.13211","kind":"arxiv","version":1},"verdict":{"id":"0583df12-90a9-4312-8daf-8bb8d321a03a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T20:24:41.013969Z","strongest_claim":"MAGI-1 achieves strong performance on image-to-video tasks conditioned on text instructions, providing high temporal consistency and scalability, made possible by chunk-wise autoregressive prediction and supporting context lengths of up to 4 million tokens with a 24B parameter model.","one_line_summary":"MAGI-1 is a 24B-parameter autoregressive video world model that predicts denoised frame chunks sequentially with increasing noise to enable causal, scalable, streaming generation up to 4M token contexts.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That training to denoise per-chunk noise increasing monotonically over time is sufficient to produce causal temporal modeling and high consistency without additional mechanisms, post-processing, or architectural constraints.","pith_extraction_headline":"MAGI-1 generates videos by autoregressively predicting fixed-length chunks of frames."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.13211/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":52,"sample":[{"doi":"","year":null,"title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","work_id":"b73ad5b2-e553-4c71-b0c9-67e67ba7b158","ref_index":1,"cited_arxiv_id":"2305.13245","is_internal_anchor":true},{"doi":"","year":null,"title":"Building Normalizing Flows with Stochastic Interpolants","work_id":"83654cbd-832b-4269-bec9-26faa87ececd","ref_index":2,"cited_arxiv_id":"2209.15571","is_internal_anchor":true},{"doi":"","year":null,"title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","work_id":"27ed795c-abbe-4de1-9a7a-2ecf39c354f3","ref_index":3,"cited_arxiv_id":"2406.03520","is_internal_anchor":true},{"doi":"","year":2024,"title":"Lumiere: A space-time diffusion model for video generation","work_id":"a2fb0e21-137b-4726-bbff-2f163dcc0a8b","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","work_id":"4f68eada-27e3-437a-a2fe-6e4ca524d0d3","ref_index":5,"cited_arxiv_id":"2311.15127","is_internal_anchor":true}],"resolved_work":52,"snapshot_sha256":"0a1731ff2b9116de3ca7a735a6fac1482fd3a64dd87f7686aea36b95c3155072","internal_anchors":35},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9d350f34e7e560e3bb8f74b981eedaf52a8606f484b47ceda6b01050626facbf"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"0583df12-90a9-4312-8daf-8bb8d321a03a"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:05:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gp0XfU+Az1jakuHnJvarDx79YEmuZtoKk6Jmn7DAuibcBJUq0M3J7Zn2HmsN2Rf5Ki/rMcIiYwJyYBOtUx9DAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:03:26.524972Z"},"content_sha256":"8c360248665572ed185b85adb10ebeb7781c3b682ee36fa081d7fb7fe7df309c","schema_version":"1.0","event_id":"sha256:8c360248665572ed185b85adb10ebeb7781c3b682ee36fa081d7fb7fe7df309c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ESR5ZBEMUI5ZKVCWR5UA3N7YSQ/bundle.json","state_url":"https://pith.science/pith/ESR5ZBEMUI5ZKVCWR5UA3N7YSQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ESR5ZBEMUI5ZKVCWR5UA3N7YSQ/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":"2026-08-06T01:03:26Z","links":{"resolver":"https://pith.science/pith/ESR5ZBEMUI5ZKVCWR5UA3N7YSQ","bundle":"https://pith.science/pith/ESR5ZBEMUI5ZKVCWR5UA3N7YSQ/bundle.json","state":"https://pith.science/pith/ESR5ZBEMUI5ZKVCWR5UA3N7YSQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ESR5ZBEMUI5ZKVCWR5UA3N7YSQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ESR5ZBEMUI5ZKVCWR5UA3N7YSQ","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":"252ee3808b5c1e4d990797ee31c613f491bb3456842115351135abab295969d6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T14:58:50Z","title_canon_sha256":"2a12493bd1c0e3529215d42d23f41bfeecef6662e6b88cf83d28362eaae5f67b"},"schema_version":"1.0","source":{"id":"2505.13211","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13211","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13211v1","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13211","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"ESR5ZBEMUI5Z","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"ESR5ZBEMUI5ZKVCW","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"ESR5ZBEM","created_at":"2026-07-05T11:05:26Z"}],"graph_snapshots":[{"event_id":"sha256:8c360248665572ed185b85adb10ebeb7781c3b682ee36fa081d7fb7fe7df309c","target":"graph","created_at":"2026-07-05T11:05:26Z","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":"MAGI-1 achieves strong performance on image-to-video tasks conditioned on text instructions, providing high temporal consistency and scalability, made possible by chunk-wise autoregressive prediction and supporting context lengths of up to 4 million tokens with a 24B parameter model."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That training to denoise per-chunk noise increasing monotonically over time is sufficient to produce causal temporal modeling and high consistency without additional mechanisms, post-processing, or architectural constraints."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MAGI-1 is a 24B-parameter autoregressive video world model that predicts denoised frame chunks sequentially with increasing noise to enable causal, scalable, streaming generation up to 4M token contexts."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MAGI-1 generates videos by autoregressively predicting fixed-length chunks of frames."}],"snapshot_sha256":"af59b1a8a89cd5f27c413399b2efa785201e39af1afd56b14466760289fa6017"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9d350f34e7e560e3bb8f74b981eedaf52a8606f484b47ceda6b01050626facbf"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.13211/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present MAGI-1, a world model that generates videos by autoregressively predicting a sequence of video chunks, defined as fixed-length segments of consecutive frames. Trained to denoise per-chunk noise that increases monotonically over time, MAGI-1 enables causal temporal modeling and naturally supports streaming generation. It achieves strong performance on image-to-video (I2V) tasks conditioned on text instructions, providing high temporal consistency and scalability, which are made possible by several algorithmic innovations and a dedicated infrastructure stack. MAGI-1 facilitates contro","authors_text":"Dai Shi, Guoli Su, Hansi Teng, Hanwen Sun, Hong Pan, Hongyu Jia, Jie Wang, Jiexin Sheng, Lei Sun, Lingzhi Li, Maolin Li, Min Cui, Mingqiu Tang, Ming Yan, Min Hu, Sand.ai, Shuai Han, Shucheng Yin, Siran Zhang, Tianning Zhang, Tingting Liu, Weifeng Luo, W.Q. Zhang, Xianping Yin, Xiaoyang Kang, Xiaoyu Yang, Xin Song, Xuan Hu, Yankai Zhang, Yuchen Sun, Yue Cao, Yunpeng Huang, Yuqiao Li, Yutong Lin, Yuxin Fang, Zewei Tao, Zheng Zhang, Zhongshu Wang, Zixun Liu","cross_cats":["cs.AI"],"headline":"MAGI-1 generates videos by autoregressively predicting fixed-length chunks of frames.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T14:58:50Z","title":"MAGI-1: Autoregressive Video Generation at Scale"},"references":{"count":52,"internal_anchors":35,"resolved_work":52,"sample":[{"cited_arxiv_id":"2305.13245","doi":"","is_internal_anchor":true,"ref_index":1,"title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","work_id":"b73ad5b2-e553-4c71-b0c9-67e67ba7b158","year":null},{"cited_arxiv_id":"2209.15571","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Building Normalizing Flows with Stochastic Interpolants","work_id":"83654cbd-832b-4269-bec9-26faa87ececd","year":null},{"cited_arxiv_id":"2406.03520","doi":"","is_internal_anchor":true,"ref_index":3,"title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","work_id":"27ed795c-abbe-4de1-9a7a-2ecf39c354f3","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Lumiere: A space-time diffusion model for video generation","work_id":"a2fb0e21-137b-4726-bbff-2f163dcc0a8b","year":2024},{"cited_arxiv_id":"2311.15127","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","work_id":"4f68eada-27e3-437a-a2fe-6e4ca524d0d3","year":null}],"snapshot_sha256":"0a1731ff2b9116de3ca7a735a6fac1482fd3a64dd87f7686aea36b95c3155072"},"source":{"id":"2505.13211","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-13T20:24:41.013969Z","id":"0583df12-90a9-4312-8daf-8bb8d321a03a","model_set":{"reader":"grok-4.3"},"one_line_summary":"MAGI-1 is a 24B-parameter autoregressive video world model that predicts denoised frame chunks sequentially with increasing noise to enable causal, scalable, streaming generation up to 4M token contexts.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MAGI-1 generates videos by autoregressively predicting fixed-length chunks of frames.","strongest_claim":"MAGI-1 achieves strong performance on image-to-video tasks conditioned on text instructions, providing high temporal consistency and scalability, made possible by chunk-wise autoregressive prediction and supporting context lengths of up to 4 million tokens with a 24B parameter model.","weakest_assumption":"That training to denoise per-chunk noise increasing monotonically over time is sufficient to produce causal temporal modeling and high consistency without additional mechanisms, post-processing, or architectural constraints."}},"verdict_id":"0583df12-90a9-4312-8daf-8bb8d321a03a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:35bb815271239b18cac00c1f7a81dc573c026305fa0bd88b73d92ecbf03b7b3d","target":"record","created_at":"2026-07-05T11:05:26Z","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":"252ee3808b5c1e4d990797ee31c613f491bb3456842115351135abab295969d6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T14:58:50Z","title_canon_sha256":"2a12493bd1c0e3529215d42d23f41bfeecef6662e6b88cf83d28362eaae5f67b"},"schema_version":"1.0","source":{"id":"2505.13211","kind":"arxiv","version":1}},"canonical_sha256":"24a3dc848ca23b9554568f680db7f8942cb64f40d42a6affd3c3b62293538bbe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24a3dc848ca23b9554568f680db7f8942cb64f40d42a6affd3c3b62293538bbe","first_computed_at":"2026-07-05T11:05:26.901031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:26.901031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2OBJYIkxxovkCPChQhDmK/hCvRQW5tCw4cvZ+AD2hkg+TRTDfG0Z/JrD9dN08SPws+XR//bqfomAzSNAUWL+Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:26.901541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13211","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35bb815271239b18cac00c1f7a81dc573c026305fa0bd88b73d92ecbf03b7b3d","sha256:8c360248665572ed185b85adb10ebeb7781c3b682ee36fa081d7fb7fe7df309c"],"state_sha256":"a25a65005666dcd34a93735a55f64f004afb32fe23049bc3e405465103788d90"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ozGJXRFBUqIu9h6Q4DqMxOa/2t+lgdVpa6p0LwOFEbIaCcaw4KrU2kOktpOZlkvGiFFAqJsx8NR0SiJKMW5Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:03:26.527777Z","bundle_sha256":"69f61545aa9b0905bfd58a2779549f02a03ad6472cd738e34b54291adadf24d3"}}