{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ES2XKHVKIBWFLQNBV4NBNAOU4L","short_pith_number":"pith:ES2XKHVK","canonical_record":{"source":{"id":"2104.13478","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-27T21:09:51Z","cross_cats_sorted":["cs.AI","cs.CG","cs.CV","stat.ML"],"title_canon_sha256":"55dae958200f9452d05bc5fac583d19f9d124d9dacc0b87ba3eb522830a813d8","abstract_canon_sha256":"21f60e4288538aae64035a297ba8364c02a1e0499fddb02a8c1882f07a64ed5c"},"schema_version":"1.0"},"canonical_sha256":"24b5751eaa406c55c1a1af1a1681d4e2ca97294dacb94eccd59e3daf2c03ad60","source":{"kind":"arxiv","id":"2104.13478","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.13478","created_at":"2026-07-05T02:36:50Z"},{"alias_kind":"arxiv_version","alias_value":"2104.13478v2","created_at":"2026-07-05T02:36:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.13478","created_at":"2026-07-05T02:36:50Z"},{"alias_kind":"pith_short_12","alias_value":"ES2XKHVKIBWF","created_at":"2026-07-05T02:36:50Z"},{"alias_kind":"pith_short_16","alias_value":"ES2XKHVKIBWFLQNB","created_at":"2026-07-05T02:36:50Z"},{"alias_kind":"pith_short_8","alias_value":"ES2XKHVK","created_at":"2026-07-05T02:36:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ES2XKHVKIBWFLQNBV4NBNAOU4L","target":"record","payload":{"canonical_record":{"source":{"id":"2104.13478","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-27T21:09:51Z","cross_cats_sorted":["cs.AI","cs.CG","cs.CV","stat.ML"],"title_canon_sha256":"55dae958200f9452d05bc5fac583d19f9d124d9dacc0b87ba3eb522830a813d8","abstract_canon_sha256":"21f60e4288538aae64035a297ba8364c02a1e0499fddb02a8c1882f07a64ed5c"},"schema_version":"1.0"},"canonical_sha256":"24b5751eaa406c55c1a1af1a1681d4e2ca97294dacb94eccd59e3daf2c03ad60","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:50.338001Z","signature_b64":"MhZXoMF5ENcBFRmz+n6aKY8NwJiHpg5/THn4eDoC3flWmEaAceZaY1Ar5HVKxlj2U64cFc4qulxx0ZTAShf6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24b5751eaa406c55c1a1af1a1681d4e2ca97294dacb94eccd59e3daf2c03ad60","last_reissued_at":"2026-07-05T02:36:50.337593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:50.337593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.13478","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":"2026-07-05T02:36:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vds1ex2jJQicQQUWAWFVFb8RHSD3+/Yx8J+vLQfkmt77WK41138P6OFx8qSV7h3EhqILiUHgCPjTb8uiMBH0Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:14:48.492188Z"},"content_sha256":"67b8eb10b72890e2ce4c86c8e069415b3ac18a3467f76d2dc637ef4612fd6f0f","schema_version":"1.0","event_id":"sha256:67b8eb10b72890e2ce4c86c8e069415b3ac18a3467f76d2dc637ef4612fd6f0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ES2XKHVKIBWFLQNBV4NBNAOU4L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Geometric principles provide a unified framework for CNNs, RNNs, GNNs, and Transformers while enabling the design of new architectures.","cross_cats":["cs.AI","cs.CG","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Joan Bruna, Michael M. Bronstein, Petar Veli\\v{c}kovi\\'c, Taco Cohen","submitted_at":"2021-04-27T21:09:51Z","abstract_excerpt":"The last decade has witnessed an experimental revolution in data science and machine learning, epitomised by deep learning methods. Indeed, many high-dimensional learning tasks previously thought to be beyond reach -- such as computer vision, playing Go, or protein folding -- are in fact feasible with appropriate computational scale. Remarkably, the essence of deep learning is built from two simple algorithmic principles: first, the notion of representation or feature learning, whereby adapted, often hierarchical, features capture the appropriate notion of regularity for each task, and second,"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Such a 'geometric unification' endeavour, in the spirit of Felix Klein's Erlangen Program, serves a dual purpose: on one hand, it provides a common mathematical framework to study the most successful neural network architectures, such as CNNs, RNNs, GNNs, and Transformers. On the other hand, it gives a constructive procedure to incorporate prior physical knowledge into neural architectures and provide principled way to build future architectures yet to be invented.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That most tasks of interest come with essential pre-defined regularities arising from the underlying low-dimensionality and structure of the physical world that can be exposed and exploited through unified geometric principles.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Geometric deep learning provides a unified mathematical framework based on grids, groups, graphs, geodesics, and gauges to explain and extend neural network architectures by incorporating physical regularities.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Geometric principles provide a unified framework for CNNs, RNNs, GNNs, and Transformers while enabling the design of new architectures.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a254da476534914d8cb658f5bcf694a93e874be4abaf00a920d666d3d8cc9976"},"source":{"id":"2104.13478","kind":"arxiv","version":2},"verdict":{"id":"8dc3aba6-0d12-4228-a939-12fda18873a9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T02:33:20.624266Z","strongest_claim":"Such a 'geometric unification' endeavour, in the spirit of Felix Klein's Erlangen Program, serves a dual purpose: on one hand, it provides a common mathematical framework to study the most successful neural network architectures, such as CNNs, RNNs, GNNs, and Transformers. On the other hand, it gives a constructive procedure to incorporate prior physical knowledge into neural architectures and provide principled way to build future architectures yet to be invented.","one_line_summary":"Geometric deep learning provides a unified mathematical framework based on grids, groups, graphs, geodesics, and gauges to explain and extend neural network architectures by incorporating physical regularities.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That most tasks of interest come with essential pre-defined regularities arising from the underlying low-dimensionality and structure of the physical world that can be exposed and exploited through unified geometric principles.","pith_extraction_headline":"Geometric principles provide a unified framework for CNNs, RNNs, GNNs, and Transformers while enabling the design of new architectures."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.13478/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":109,"sample":[{"doi":"","year":2006,"title":"On the bottleneck of graph neural networks and its practical implications","work_id":"4dc88c40-c0d4-4c5d-a0f9-5c863c1fabdc","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1906,"title":"Cormorant: Covariant Molecular Neur al Networks","work_id":"c4840a09-723f-41ae-8ad8-87d65ff0c135","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Layer Normalization","work_id":"20a2d720-0046-4c7c-bcd6-327ec8143f69","ref_index":3,"cited_arxiv_id":"1607.06450","is_internal_anchor":true},{"doi":"","year":null,"title":"Neural Machine Translation by Jointly Learning to Align and Translate","work_id":"d831e763-d530-4029-a65c-ac595d82cb2a","ref_index":4,"cited_arxiv_id":"1409.0473","is_internal_anchor":true},{"doi":"","year":null,"title":"Discovering transforms: A tutorial on circulant matrices, circular convolution, and the discrete fourier transform.arXiv:1805.05533","work_id":"917ec4a9-7299-4959-80e4-e31fdeb3888f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":109,"snapshot_sha256":"5f318c983af9fc04b7bc3bd29a766f3081fed94a789c8a71e3de1134717a020f","internal_anchors":22},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3215ad1688a4f1a745439aeb640598d246aa13ee5bd22a640b1656d6a7afe666"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"8dc3aba6-0d12-4228-a939-12fda18873a9"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:36:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2FaUmh2diB/rZJ/nTI5JB065VL1VBVkgRrKUfp6b6Wqp6vPMFGrGOXEOZTWoPwrPgbdIQ4iRI2dybJ+395dWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:14:48.493178Z"},"content_sha256":"9e83993d74e54585c6b792d9812e852020941860c75a4ef894740d66624283a1","schema_version":"1.0","event_id":"sha256:9e83993d74e54585c6b792d9812e852020941860c75a4ef894740d66624283a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ES2XKHVKIBWFLQNBV4NBNAOU4L/bundle.json","state_url":"https://pith.science/pith/ES2XKHVKIBWFLQNBV4NBNAOU4L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ES2XKHVKIBWFLQNBV4NBNAOU4L/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":"2026-08-07T12:14:48Z","links":{"resolver":"https://pith.science/pith/ES2XKHVKIBWFLQNBV4NBNAOU4L","bundle":"https://pith.science/pith/ES2XKHVKIBWFLQNBV4NBNAOU4L/bundle.json","state":"https://pith.science/pith/ES2XKHVKIBWFLQNBV4NBNAOU4L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ES2XKHVKIBWFLQNBV4NBNAOU4L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ES2XKHVKIBWFLQNBV4NBNAOU4L","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":"21f60e4288538aae64035a297ba8364c02a1e0499fddb02a8c1882f07a64ed5c","cross_cats_sorted":["cs.AI","cs.CG","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-27T21:09:51Z","title_canon_sha256":"55dae958200f9452d05bc5fac583d19f9d124d9dacc0b87ba3eb522830a813d8"},"schema_version":"1.0","source":{"id":"2104.13478","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.13478","created_at":"2026-07-05T02:36:50Z"},{"alias_kind":"arxiv_version","alias_value":"2104.13478v2","created_at":"2026-07-05T02:36:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.13478","created_at":"2026-07-05T02:36:50Z"},{"alias_kind":"pith_short_12","alias_value":"ES2XKHVKIBWF","created_at":"2026-07-05T02:36:50Z"},{"alias_kind":"pith_short_16","alias_value":"ES2XKHVKIBWFLQNB","created_at":"2026-07-05T02:36:50Z"},{"alias_kind":"pith_short_8","alias_value":"ES2XKHVK","created_at":"2026-07-05T02:36:50Z"}],"graph_snapshots":[{"event_id":"sha256:9e83993d74e54585c6b792d9812e852020941860c75a4ef894740d66624283a1","target":"graph","created_at":"2026-07-05T02:36:50Z","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":"Such a 'geometric unification' endeavour, in the spirit of Felix Klein's Erlangen Program, serves a dual purpose: on one hand, it provides a common mathematical framework to study the most successful neural network architectures, such as CNNs, RNNs, GNNs, and Transformers. On the other hand, it gives a constructive procedure to incorporate prior physical knowledge into neural architectures and provide principled way to build future architectures yet to be invented."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That most tasks of interest come with essential pre-defined regularities arising from the underlying low-dimensionality and structure of the physical world that can be exposed and exploited through unified geometric principles."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Geometric deep learning provides a unified mathematical framework based on grids, groups, graphs, geodesics, and gauges to explain and extend neural network architectures by incorporating physical regularities."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Geometric principles provide a unified framework for CNNs, RNNs, GNNs, and Transformers while enabling the design of new architectures."}],"snapshot_sha256":"a254da476534914d8cb658f5bcf694a93e874be4abaf00a920d666d3d8cc9976"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3215ad1688a4f1a745439aeb640598d246aa13ee5bd22a640b1656d6a7afe666"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2104.13478/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The last decade has witnessed an experimental revolution in data science and machine learning, epitomised by deep learning methods. Indeed, many high-dimensional learning tasks previously thought to be beyond reach -- such as computer vision, playing Go, or protein folding -- are in fact feasible with appropriate computational scale. Remarkably, the essence of deep learning is built from two simple algorithmic principles: first, the notion of representation or feature learning, whereby adapted, often hierarchical, features capture the appropriate notion of regularity for each task, and second,","authors_text":"Joan Bruna, Michael M. Bronstein, Petar Veli\\v{c}kovi\\'c, Taco Cohen","cross_cats":["cs.AI","cs.CG","cs.CV","stat.ML"],"headline":"Geometric principles provide a unified framework for CNNs, RNNs, GNNs, and Transformers while enabling the design of new architectures.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-27T21:09:51Z","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges"},"references":{"count":109,"internal_anchors":22,"resolved_work":109,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"On the bottleneck of graph neural networks and its practical implications","work_id":"4dc88c40-c0d4-4c5d-a0f9-5c863c1fabdc","year":2006},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Cormorant: Covariant Molecular Neur al Networks","work_id":"c4840a09-723f-41ae-8ad8-87d65ff0c135","year":1906},{"cited_arxiv_id":"1607.06450","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Layer Normalization","work_id":"20a2d720-0046-4c7c-bcd6-327ec8143f69","year":null},{"cited_arxiv_id":"1409.0473","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Neural Machine Translation by Jointly Learning to Align and Translate","work_id":"d831e763-d530-4029-a65c-ac595d82cb2a","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Discovering transforms: A tutorial on circulant matrices, circular convolution, and the discrete fourier transform.arXiv:1805.05533","work_id":"917ec4a9-7299-4959-80e4-e31fdeb3888f","year":null}],"snapshot_sha256":"5f318c983af9fc04b7bc3bd29a766f3081fed94a789c8a71e3de1134717a020f"},"source":{"id":"2104.13478","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T02:33:20.624266Z","id":"8dc3aba6-0d12-4228-a939-12fda18873a9","model_set":{"reader":"grok-4.3"},"one_line_summary":"Geometric deep learning provides a unified mathematical framework based on grids, groups, graphs, geodesics, and gauges to explain and extend neural network architectures by incorporating physical regularities.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Geometric principles provide a unified framework for CNNs, RNNs, GNNs, and Transformers while enabling the design of new architectures.","strongest_claim":"Such a 'geometric unification' endeavour, in the spirit of Felix Klein's Erlangen Program, serves a dual purpose: on one hand, it provides a common mathematical framework to study the most successful neural network architectures, such as CNNs, RNNs, GNNs, and Transformers. On the other hand, it gives a constructive procedure to incorporate prior physical knowledge into neural architectures and provide principled way to build future architectures yet to be invented.","weakest_assumption":"That most tasks of interest come with essential pre-defined regularities arising from the underlying low-dimensionality and structure of the physical world that can be exposed and exploited through unified geometric principles."}},"verdict_id":"8dc3aba6-0d12-4228-a939-12fda18873a9"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:67b8eb10b72890e2ce4c86c8e069415b3ac18a3467f76d2dc637ef4612fd6f0f","target":"record","created_at":"2026-07-05T02:36:50Z","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":"21f60e4288538aae64035a297ba8364c02a1e0499fddb02a8c1882f07a64ed5c","cross_cats_sorted":["cs.AI","cs.CG","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-27T21:09:51Z","title_canon_sha256":"55dae958200f9452d05bc5fac583d19f9d124d9dacc0b87ba3eb522830a813d8"},"schema_version":"1.0","source":{"id":"2104.13478","kind":"arxiv","version":2}},"canonical_sha256":"24b5751eaa406c55c1a1af1a1681d4e2ca97294dacb94eccd59e3daf2c03ad60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24b5751eaa406c55c1a1af1a1681d4e2ca97294dacb94eccd59e3daf2c03ad60","first_computed_at":"2026-07-05T02:36:50.337593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:36:50.337593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MhZXoMF5ENcBFRmz+n6aKY8NwJiHpg5/THn4eDoC3flWmEaAceZaY1Ar5HVKxlj2U64cFc4qulxx0ZTAShf6AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:36:50.338001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.13478","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67b8eb10b72890e2ce4c86c8e069415b3ac18a3467f76d2dc637ef4612fd6f0f","sha256:9e83993d74e54585c6b792d9812e852020941860c75a4ef894740d66624283a1"],"state_sha256":"3da093d1ad27c4188c50f15f8a426c3e3d9490db7a518150f42d31e56d4de8af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5C8YzwIoJAuI9gbldM2mhDhJgEekd7yAuaGnY7vPO4aZH1NPquL5SgRVTEtBt5gzpba18vLvBEL4txLW2I45Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:14:48.498625Z","bundle_sha256":"39e327b9b2f9ed8eddce7655e79a8880efd211c9356778467d4458b94d9d7359"}}