{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5CHYGABH5WBTKRU6A3FOXCN5I7","short_pith_number":"pith:5CHYGABH","canonical_record":{"source":{"id":"2604.11679","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T16:23:46Z","cross_cats_sorted":[],"title_canon_sha256":"9de3505ecb67719c45c1a222e95530bd55cb0b5638ac88c9f8f365c6275e09ca","abstract_canon_sha256":"75619bae72345284aeee19249edc39a21f55eb6a042ae15f48832ae43b972b6e"},"schema_version":"1.0"},"canonical_sha256":"e88f830027ed8335469e06caeb89bd47f8154d98584a5191b8f622f376367bbd","source":{"kind":"arxiv","id":"2604.11679","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.11679","created_at":"2026-05-25T02:01:20Z"},{"alias_kind":"arxiv_version","alias_value":"2604.11679v2","created_at":"2026-05-25T02:01:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11679","created_at":"2026-05-25T02:01:20Z"},{"alias_kind":"pith_short_12","alias_value":"5CHYGABH5WBT","created_at":"2026-05-25T02:01:20Z"},{"alias_kind":"pith_short_16","alias_value":"5CHYGABH5WBTKRU6","created_at":"2026-05-25T02:01:20Z"},{"alias_kind":"pith_short_8","alias_value":"5CHYGABH","created_at":"2026-05-25T02:01:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5CHYGABH5WBTKRU6A3FOXCN5I7","target":"record","payload":{"canonical_record":{"source":{"id":"2604.11679","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T16:23:46Z","cross_cats_sorted":[],"title_canon_sha256":"9de3505ecb67719c45c1a222e95530bd55cb0b5638ac88c9f8f365c6275e09ca","abstract_canon_sha256":"75619bae72345284aeee19249edc39a21f55eb6a042ae15f48832ae43b972b6e"},"schema_version":"1.0"},"canonical_sha256":"e88f830027ed8335469e06caeb89bd47f8154d98584a5191b8f622f376367bbd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:20.106148Z","signature_b64":"Jw0KYsGqbpb1HjGHBUd/e9MIUOtcCx9n7/+V63M2VZnUDXK3bSaQtCQUVoCPl9t9HyWkS49nQ6tELjPw0SqOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e88f830027ed8335469e06caeb89bd47f8154d98584a5191b8f622f376367bbd","last_reissued_at":"2026-05-25T02:01:20.105339Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:20.105339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.11679","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:01:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SSlCQti64ZZMrZinz5WmOWv7HxdMVZX7UoxaY6Yi53QBH5YDXnNw6e0UTRDjQ5dXLJ7SSVE58iE04x7xgLWPBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T17:38:12.847752Z"},"content_sha256":"fc4e4b3d086fcd3e99a33af6cc2234b0733392297d2c2de6d0277a67e7ae3c89","schema_version":"1.0","event_id":"sha256:fc4e4b3d086fcd3e99a33af6cc2234b0733392297d2c2de6d0277a67e7ae3c89"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5CHYGABH5WBTKRU6A3FOXCN5I7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Self-supervised pretraining on large unlabeled brain MRI data improves generalization to noisy clinical scans over supervised in-domain training.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdul Qayyum, Akshay Pai, Anant Madabhushi, Andr\\'es Mart\\'inez Mora, Anthony Winder, Antoine Saporta, Asbj{\\o}rn Munk, Baptiste Callard, Beno\\^it G\\'erin, Bhakti Baheti, Branislav Setlak, Chang Yang, Chris Kang, Christian Hedeager Krag, Christoph Brune, Constantin Ulrich, Corentin Dancette, Cornelius Crijnen, Emily Kaczmarek, Espen Jimenez Solem, Felix Meister, Fucang Jia, Jae Sung Lee, Jakob Ambsdorf, Jakub Gazda, Jaume Banus, Jelmer M. Wolterink, Jiexin Jiang, Jinah Park, Jonas Richiardi, Juan Eugenio Iglesias, Julia Machnio, Julien Khlaut, Justin Szeto, Kamil Barbierik, Kimberly Amador, Klaus H. Maier-Hein, Leonard N\\\"urnberg, Leroy Volmer, Mads Nielsen, Matej Gazda, Maxence Wynen, Mengye Lyu, Meritxell Bach Cuadra, Michael Eriksen Benros, Mikael Boesen, Mingchen Ma, Mohammad Khazaei, Moona Mazher, Mostafa Mehdipour Ghazi, Nasrin Akbari, Nataliia Molchanova, Nils D. Forkert, Ning Shen, Pablo Rocamora Garc\\'ia, Partha Ghosh, Pedro M. Gordaliza, Peirong Liu, Peter Drotar, Petros Koutsouvelis, Pierre Manceron, Prasad Dutande, Puru Vaish, Sam Hashemi, Saurabh Garg, Sebastian N{\\o}rgaard Llambias, Seung Kwan Kang, Sina Amirrajab, Siqi Wei, Si Young Yie, Stefano Cerri, Steven A. Niederer, Suhyun Ahn, Tal Arbel, Tobias Heimann, Ujjwal Baid, Vardan Nersesjan, Vibujithan Vigneshwaran, Weikang Gong, Yansong Bu, Yasmina Al Khalil, Yuchong Li, Yuhan Chen, Zihao Wang","submitted_at":"2026-04-13T16:23:46Z","abstract_excerpt":"Clinical deployment of automated brain MRI analysis faces a fundamental challenge: clinical data is heterogeneous and noisy, and high-quality labels are prohibitively costly to obtain. Self-supervised learning (SSL) can address this by leveraging the vast amounts of unlabeled data produced in clinical workflows to train robust \\textit{foundation models} that adapt out-of-domain with minimal supervision. However, the development of foundation models for brain MRI has been limited by small pretraining datasets and in-domain benchmarking focused on high-quality, research-grade data. To address th"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"self-supervised pretraining improves generalization on clinical data under domain shift, with the strongest models trained out-of-domain surpassing supervised baselines trained in-domain.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the FOMO60K pretraining dataset and the chosen clinical evaluation tasks and data splits sufficiently represent the heterogeneity and noise encountered in actual clinical workflows.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Self-supervised pretraining on 60K clinical-style brain MRIs improves out-of-domain generalization on classification, segmentation, and regression tasks, with hybrid objectives and small models showing strong results.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Self-supervised pretraining on large unlabeled brain MRI data improves generalization to noisy clinical scans over supervised in-domain training.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"28a055a961fef525c6e67f7cba24569bd55d122f449c8d2b5a3510e581795232"},"source":{"id":"2604.11679","kind":"arxiv","version":2},"verdict":{"id":"a42fc3b5-af13-463c-b915-912bc007d29e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T16:41:30.144342Z","strongest_claim":"self-supervised pretraining improves generalization on clinical data under domain shift, with the strongest models trained out-of-domain surpassing supervised baselines trained in-domain.","one_line_summary":"Self-supervised pretraining on 60K clinical-style brain MRIs improves out-of-domain generalization on classification, segmentation, and regression tasks, with hybrid objectives and small models showing strong results.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the FOMO60K pretraining dataset and the chosen clinical evaluation tasks and data splits sufficiently represent the heterogeneity and noise encountered in actual clinical workflows.","pith_extraction_headline":"Self-supervised pretraining on large unlabeled brain MRI data improves generalization to noisy clinical scans over supervised in-domain training."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.11679/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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":"a42fc3b5-af13-463c-b915-912bc007d29e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:01:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hQIY92F0BOsnkBek8ZX3491MYsV5cgE9OR5JUoJD97YeRyFwWTtaM3ogYvNc/5EOqZoFAwqxpWoSOPclH6gcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T17:38:12.848621Z"},"content_sha256":"9d51105230fc1de55bd06d5ae9919af6b9e07e4f2124617217c8796e387ffffc","schema_version":"1.0","event_id":"sha256:9d51105230fc1de55bd06d5ae9919af6b9e07e4f2124617217c8796e387ffffc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5CHYGABH5WBTKRU6A3FOXCN5I7/bundle.json","state_url":"https://pith.science/pith/5CHYGABH5WBTKRU6A3FOXCN5I7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5CHYGABH5WBTKRU6A3FOXCN5I7/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":"2026-08-22T17:38:12Z","links":{"resolver":"https://pith.science/pith/5CHYGABH5WBTKRU6A3FOXCN5I7","bundle":"https://pith.science/pith/5CHYGABH5WBTKRU6A3FOXCN5I7/bundle.json","state":"https://pith.science/pith/5CHYGABH5WBTKRU6A3FOXCN5I7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5CHYGABH5WBTKRU6A3FOXCN5I7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5CHYGABH5WBTKRU6A3FOXCN5I7","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":"75619bae72345284aeee19249edc39a21f55eb6a042ae15f48832ae43b972b6e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T16:23:46Z","title_canon_sha256":"9de3505ecb67719c45c1a222e95530bd55cb0b5638ac88c9f8f365c6275e09ca"},"schema_version":"1.0","source":{"id":"2604.11679","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.11679","created_at":"2026-05-25T02:01:20Z"},{"alias_kind":"arxiv_version","alias_value":"2604.11679v2","created_at":"2026-05-25T02:01:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11679","created_at":"2026-05-25T02:01:20Z"},{"alias_kind":"pith_short_12","alias_value":"5CHYGABH5WBT","created_at":"2026-05-25T02:01:20Z"},{"alias_kind":"pith_short_16","alias_value":"5CHYGABH5WBTKRU6","created_at":"2026-05-25T02:01:20Z"},{"alias_kind":"pith_short_8","alias_value":"5CHYGABH","created_at":"2026-05-25T02:01:20Z"}],"graph_snapshots":[{"event_id":"sha256:9d51105230fc1de55bd06d5ae9919af6b9e07e4f2124617217c8796e387ffffc","target":"graph","created_at":"2026-05-25T02:01:20Z","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":"self-supervised pretraining improves generalization on clinical data under domain shift, with the strongest models trained out-of-domain surpassing supervised baselines trained in-domain."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the FOMO60K pretraining dataset and the chosen clinical evaluation tasks and data splits sufficiently represent the heterogeneity and noise encountered in actual clinical workflows."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Self-supervised pretraining on 60K clinical-style brain MRIs improves out-of-domain generalization on classification, segmentation, and regression tasks, with hybrid objectives and small models showing strong results."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Self-supervised pretraining on large unlabeled brain MRI data improves generalization to noisy clinical scans over supervised in-domain training."}],"snapshot_sha256":"28a055a961fef525c6e67f7cba24569bd55d122f449c8d2b5a3510e581795232"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.11679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Clinical deployment of automated brain MRI analysis faces a fundamental challenge: clinical data is heterogeneous and noisy, and high-quality labels are prohibitively costly to obtain. Self-supervised learning (SSL) can address this by leveraging the vast amounts of unlabeled data produced in clinical workflows to train robust \\textit{foundation models} that adapt out-of-domain with minimal supervision. However, the development of foundation models for brain MRI has been limited by small pretraining datasets and in-domain benchmarking focused on high-quality, research-grade data. To address th","authors_text":"Abdul Qayyum, Akshay Pai, Anant Madabhushi, Andr\\'es Mart\\'inez Mora, Anthony Winder, Antoine Saporta, Asbj{\\o}rn Munk, Baptiste Callard, Beno\\^it G\\'erin, Bhakti Baheti, Branislav Setlak, Chang Yang, Chris Kang, Christian Hedeager Krag, Christoph Brune, Constantin Ulrich, Corentin Dancette, Cornelius Crijnen, Emily Kaczmarek, Espen Jimenez Solem, Felix Meister, Fucang Jia, Jae Sung Lee, Jakob Ambsdorf, Jakub Gazda, Jaume Banus, Jelmer M. Wolterink, Jiexin Jiang, Jinah Park, Jonas Richiardi, Juan Eugenio Iglesias, Julia Machnio, Julien Khlaut, Justin Szeto, Kamil Barbierik, Kimberly Amador, Klaus H. Maier-Hein, Leonard N\\\"urnberg, Leroy Volmer, Mads Nielsen, Matej Gazda, Maxence Wynen, Mengye Lyu, Meritxell Bach Cuadra, Michael Eriksen Benros, Mikael Boesen, Mingchen Ma, Mohammad Khazaei, Moona Mazher, Mostafa Mehdipour Ghazi, Nasrin Akbari, Nataliia Molchanova, Nils D. Forkert, Ning Shen, Pablo Rocamora Garc\\'ia, Partha Ghosh, Pedro M. Gordaliza, Peirong Liu, Peter Drotar, Petros Koutsouvelis, Pierre Manceron, Prasad Dutande, Puru Vaish, Sam Hashemi, Saurabh Garg, Sebastian N{\\o}rgaard Llambias, Seung Kwan Kang, Sina Amirrajab, Siqi Wei, Si Young Yie, Stefano Cerri, Steven A. Niederer, Suhyun Ahn, Tal Arbel, Tobias Heimann, Ujjwal Baid, Vardan Nersesjan, Vibujithan Vigneshwaran, Weikang Gong, Yansong Bu, Yasmina Al Khalil, Yuchong Li, Yuhan Chen, Zihao Wang","cross_cats":[],"headline":"Self-supervised pretraining on large unlabeled brain MRI data improves generalization to noisy clinical scans over supervised in-domain training.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T16:23:46Z","title":"Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.11679","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T16:41:30.144342Z","id":"a42fc3b5-af13-463c-b915-912bc007d29e","model_set":{"reader":"grok-4.3"},"one_line_summary":"Self-supervised pretraining on 60K clinical-style brain MRIs improves out-of-domain generalization on classification, segmentation, and regression tasks, with hybrid objectives and small models showing strong results.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Self-supervised pretraining on large unlabeled brain MRI data improves generalization to noisy clinical scans over supervised in-domain training.","strongest_claim":"self-supervised pretraining improves generalization on clinical data under domain shift, with the strongest models trained out-of-domain surpassing supervised baselines trained in-domain.","weakest_assumption":"That the FOMO60K pretraining dataset and the chosen clinical evaluation tasks and data splits sufficiently represent the heterogeneity and noise encountered in actual clinical workflows."}},"verdict_id":"a42fc3b5-af13-463c-b915-912bc007d29e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fc4e4b3d086fcd3e99a33af6cc2234b0733392297d2c2de6d0277a67e7ae3c89","target":"record","created_at":"2026-05-25T02:01:20Z","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":"75619bae72345284aeee19249edc39a21f55eb6a042ae15f48832ae43b972b6e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T16:23:46Z","title_canon_sha256":"9de3505ecb67719c45c1a222e95530bd55cb0b5638ac88c9f8f365c6275e09ca"},"schema_version":"1.0","source":{"id":"2604.11679","kind":"arxiv","version":2}},"canonical_sha256":"e88f830027ed8335469e06caeb89bd47f8154d98584a5191b8f622f376367bbd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e88f830027ed8335469e06caeb89bd47f8154d98584a5191b8f622f376367bbd","first_computed_at":"2026-05-25T02:01:20.105339Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:20.105339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jw0KYsGqbpb1HjGHBUd/e9MIUOtcCx9n7/+V63M2VZnUDXK3bSaQtCQUVoCPl9t9HyWkS49nQ6tELjPw0SqOCA==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:20.106148Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.11679","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc4e4b3d086fcd3e99a33af6cc2234b0733392297d2c2de6d0277a67e7ae3c89","sha256:9d51105230fc1de55bd06d5ae9919af6b9e07e4f2124617217c8796e387ffffc"],"state_sha256":"e3aa13ba91534a5ec4848a184e985717a5b1fd34242cd38e9eaacbca34530643"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mFAGuEPm/bx3RQRUybWf54UIXA/pfao82zByK8nkPFbAbmXIIbQ508ltzqOBN0p1u27B8fpjB42gEhxPy5nmBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T17:38:12.853202Z","bundle_sha256":"011ac257bee96f5ca35f91ec971639a017fe8b26a395f467ad0130e7e0a30998"}}