{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:757O5WSIJRINA5I4LSWOTE3PDD","short_pith_number":"pith:757O5WSI","canonical_record":{"source":{"id":"2605.15459","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T22:41:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dc46a3f87fb546ad38ad9fccf985fd41d5c06dfc22ee793bf571dbc2d309494a","abstract_canon_sha256":"49dd21b8cf8cbcecac185e9b3d228ecfb376867870c8c180ba8b3a3889be1946"},"schema_version":"1.0"},"canonical_sha256":"ff7eeeda484c50d0751c5cace9936f18d7804a04e1c061229c5e39554c70f9ac","source":{"kind":"arxiv","id":"2605.15459","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15459","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15459v1","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15459","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"pith_short_12","alias_value":"757O5WSIJRIN","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"pith_short_16","alias_value":"757O5WSIJRINA5I4","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"pith_short_8","alias_value":"757O5WSI","created_at":"2026-05-20T00:00:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:757O5WSIJRINA5I4LSWOTE3PDD","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15459","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T22:41:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dc46a3f87fb546ad38ad9fccf985fd41d5c06dfc22ee793bf571dbc2d309494a","abstract_canon_sha256":"49dd21b8cf8cbcecac185e9b3d228ecfb376867870c8c180ba8b3a3889be1946"},"schema_version":"1.0"},"canonical_sha256":"ff7eeeda484c50d0751c5cace9936f18d7804a04e1c061229c5e39554c70f9ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:59.679978Z","signature_b64":"AqC+su+G0/d0qTwKs+pUk02hYaG05oiapLejNFG4PB+Rh5jbBDS6f5XgBmG7aP3GVk064bRDzfIEBpe4HmQyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff7eeeda484c50d0751c5cace9936f18d7804a04e1c061229c5e39554c70f9ac","last_reissued_at":"2026-05-20T00:00:59.679172Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:59.679172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15459","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":"2026-05-20T00:00:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F/khkPN0+FhElwlJG6Dl4Sza8+83xeaAgZg2bLt42/m9pOMQpFhMbKSccjZnOnDOGAlkdnlCZExZQqSmpVRPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:26:18.822472Z"},"content_sha256":"04c7ea607e28a3dd4fee623a9ca26b96843ba5e23cfb0a814d55b637d089c780","schema_version":"1.0","event_id":"sha256:04c7ea607e28a3dd4fee623a9ca26b96843ba5e23cfb0a814d55b637d089c780"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:757O5WSIJRINA5I4LSWOTE3PDD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Don't Stop Me Yet: Sampling Loss Minima via Dissipative Riemannian Mechanics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A new dynamical sampler called DiMS exactly targets the connected components of reparameterization-invariant minima in neural network losses.","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Albert Kj{\\o}ller Jacobsen, Georgios Arvanitidis, Johanna Marie Gegenfurtner, Leo Uhre Jakobsen","submitted_at":"2026-05-14T22:41:01Z","abstract_excerpt":"The minima of modern neural network loss functions are typically not isolated, rather they form connected components of reparameterization invariant solutions on the training data. Analytically characterizing these solutions is a hard problem, but sampling approaches are feasible. By construction, existing methods either spread over low-loss regions, and thus do not sample reparameterization invariant solutions exactly, or are inherently local, which limits exploration of other minima valleys. We propose sampling such reparameterization invariant models using a dynamical system based on kineti"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our proposed sampler, DiMS, is guaranteed to sample exactly from the minimum level sets and depends on physically motivated hyperparameters which allows control over the exploration capabilities of the sampler.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The claim that minima of modern neural network loss functions typically form connected components of reparameterization invariant solutions on the training data, which is required for the dynamical system to target exactly those level sets rather than broader low-loss regions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DiMS is a physics-inspired dynamical sampler guaranteed to exactly sample reparameterization-invariant minimum level sets in neural network loss landscapes.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A new dynamical sampler called DiMS exactly targets the connected components of reparameterization-invariant minima in neural network losses.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b9049ca8fde16e7f6626e96cab77bb266c4015be0acb160d13adbd91c9917c8e"},"source":{"id":"2605.15459","kind":"arxiv","version":1},"verdict":{"id":"4a4a1535-209c-45af-9754-b6f3bf7ca50f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T15:27:50.274768Z","strongest_claim":"Our proposed sampler, DiMS, is guaranteed to sample exactly from the minimum level sets and depends on physically motivated hyperparameters which allows control over the exploration capabilities of the sampler.","one_line_summary":"DiMS is a physics-inspired dynamical sampler guaranteed to exactly sample reparameterization-invariant minimum level sets in neural network loss landscapes.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The claim that minima of modern neural network loss functions typically form connected components of reparameterization invariant solutions on the training data, which is required for the dynamical system to target exactly those level sets rather than broader low-loss regions.","pith_extraction_headline":"A new dynamical sampler called DiMS exactly targets the connected components of reparameterization-invariant minima in neural network losses."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15459/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T16:01:17.975581Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T15:49:48.733182Z","status":"completed","version":"0.1.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:40:36.846159Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T15:23:29.008531Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.099902Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.671743Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"88fe3c8bb0b413cd06b2395f4c6785635666d529a79ae8dcf76762d2b88eca2b"},"references":{"count":56,"sample":[{"doi":"","year":null,"title":"arXiv preprint arXiv:2510.26266 , year=","work_id":"1ffef25e-c7f5-4885-8842-d922308146c3","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Neural Information Processing Systems (NeurIPS) , year=","work_id":"8edb8cf7-d8d7-4673-ba0f-f75d12be9e79","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Neural Information Processing Systems (NeurIPS) , year=","work_id":"5f908e7a-e423-4cb1-8d15-aaf174a80d91","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Yu, Hanlin and Hartmann, Marcelo and Sanchez, Bernardo Williams Moreno and Girolami, Mark and Klami, Arto , booktitle=","work_id":"b982ad09-a2bd-4ac9-838c-43c186d556e3","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Reichlin, Alfredo and Vasco, Miguel and Kragic Jensfelt, Danica , journal=","work_id":"515d3153-ac9c-4f85-b5ed-22f5b9026dcf","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":56,"snapshot_sha256":"760fede8c97e3bb7db21b31c5910540c8c5d083840107178cf333d8f0f6e0f62","internal_anchors":2},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4956496b8781702926c9367e570208d8fc049ddd71e1459249488d2a639f7093"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"4a4a1535-209c-45af-9754-b6f3bf7ca50f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WJ0IvK0J9PfkGYOPN4lS9IU/+or2pnaWl8L1p18J8wUVIj7VdypcRGO9XQzX+6YwK4fVlFVBjwfLSGGYL/QpAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:26:18.823625Z"},"content_sha256":"3f33cec9a0e653537a0f9d263a58cab9400e409c4cc117760227bd9f7ffd0e23","schema_version":"1.0","event_id":"sha256:3f33cec9a0e653537a0f9d263a58cab9400e409c4cc117760227bd9f7ffd0e23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/757O5WSIJRINA5I4LSWOTE3PDD/bundle.json","state_url":"https://pith.science/pith/757O5WSIJRINA5I4LSWOTE3PDD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/757O5WSIJRINA5I4LSWOTE3PDD/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":"2026-05-25T20:26:18Z","links":{"resolver":"https://pith.science/pith/757O5WSIJRINA5I4LSWOTE3PDD","bundle":"https://pith.science/pith/757O5WSIJRINA5I4LSWOTE3PDD/bundle.json","state":"https://pith.science/pith/757O5WSIJRINA5I4LSWOTE3PDD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/757O5WSIJRINA5I4LSWOTE3PDD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:757O5WSIJRINA5I4LSWOTE3PDD","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":"49dd21b8cf8cbcecac185e9b3d228ecfb376867870c8c180ba8b3a3889be1946","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T22:41:01Z","title_canon_sha256":"dc46a3f87fb546ad38ad9fccf985fd41d5c06dfc22ee793bf571dbc2d309494a"},"schema_version":"1.0","source":{"id":"2605.15459","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15459","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15459v1","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15459","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"pith_short_12","alias_value":"757O5WSIJRIN","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"pith_short_16","alias_value":"757O5WSIJRINA5I4","created_at":"2026-05-20T00:00:59Z"},{"alias_kind":"pith_short_8","alias_value":"757O5WSI","created_at":"2026-05-20T00:00:59Z"}],"graph_snapshots":[{"event_id":"sha256:3f33cec9a0e653537a0f9d263a58cab9400e409c4cc117760227bd9f7ffd0e23","target":"graph","created_at":"2026-05-20T00:00:59Z","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":"Our proposed sampler, DiMS, is guaranteed to sample exactly from the minimum level sets and depends on physically motivated hyperparameters which allows control over the exploration capabilities of the sampler."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The claim that minima of modern neural network loss functions typically form connected components of reparameterization invariant solutions on the training data, which is required for the dynamical system to target exactly those level sets rather than broader low-loss regions."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DiMS is a physics-inspired dynamical sampler guaranteed to exactly sample reparameterization-invariant minimum level sets in neural network loss landscapes."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A new dynamical sampler called DiMS exactly targets the connected components of reparameterization-invariant minima in neural network losses."}],"snapshot_sha256":"b9049ca8fde16e7f6626e96cab77bb266c4015be0acb160d13adbd91c9917c8e"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4956496b8781702926c9367e570208d8fc049ddd71e1459249488d2a639f7093"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T16:01:17.975581Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T15:49:48.733182Z","status":"completed","version":"0.1.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T15:40:36.846159Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T15:23:29.008531Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.099902Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.671743Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15459/integrity.json","findings":[],"snapshot_sha256":"88fe3c8bb0b413cd06b2395f4c6785635666d529a79ae8dcf76762d2b88eca2b","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The minima of modern neural network loss functions are typically not isolated, rather they form connected components of reparameterization invariant solutions on the training data. Analytically characterizing these solutions is a hard problem, but sampling approaches are feasible. By construction, existing methods either spread over low-loss regions, and thus do not sample reparameterization invariant solutions exactly, or are inherently local, which limits exploration of other minima valleys. We propose sampling such reparameterization invariant models using a dynamical system based on kineti","authors_text":"Albert Kj{\\o}ller Jacobsen, Georgios Arvanitidis, Johanna Marie Gegenfurtner, Leo Uhre Jakobsen","cross_cats":["stat.ML"],"headline":"A new dynamical sampler called DiMS exactly targets the connected components of reparameterization-invariant minima in neural network losses.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T22:41:01Z","title":"Don't Stop Me Yet: Sampling Loss Minima via Dissipative Riemannian Mechanics"},"references":{"count":56,"internal_anchors":2,"resolved_work":56,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"arXiv preprint arXiv:2510.26266 , year=","work_id":"1ffef25e-c7f5-4885-8842-d922308146c3","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Neural Information Processing Systems (NeurIPS) , year=","work_id":"8edb8cf7-d8d7-4673-ba0f-f75d12be9e79","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Neural Information Processing Systems (NeurIPS) , year=","work_id":"5f908e7a-e423-4cb1-8d15-aaf174a80d91","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Yu, Hanlin and Hartmann, Marcelo and Sanchez, Bernardo Williams Moreno and Girolami, Mark and Klami, Arto , booktitle=","work_id":"b982ad09-a2bd-4ac9-838c-43c186d556e3","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Reichlin, Alfredo and Vasco, Miguel and Kragic Jensfelt, Danica , journal=","work_id":"515d3153-ac9c-4f85-b5ed-22f5b9026dcf","year":null}],"snapshot_sha256":"760fede8c97e3bb7db21b31c5910540c8c5d083840107178cf333d8f0f6e0f62"},"source":{"id":"2605.15459","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T15:27:50.274768Z","id":"4a4a1535-209c-45af-9754-b6f3bf7ca50f","model_set":{"reader":"grok-4.3"},"one_line_summary":"DiMS is a physics-inspired dynamical sampler guaranteed to exactly sample reparameterization-invariant minimum level sets in neural network loss landscapes.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A new dynamical sampler called DiMS exactly targets the connected components of reparameterization-invariant minima in neural network losses.","strongest_claim":"Our proposed sampler, DiMS, is guaranteed to sample exactly from the minimum level sets and depends on physically motivated hyperparameters which allows control over the exploration capabilities of the sampler.","weakest_assumption":"The claim that minima of modern neural network loss functions typically form connected components of reparameterization invariant solutions on the training data, which is required for the dynamical system to target exactly those level sets rather than broader low-loss regions."}},"verdict_id":"4a4a1535-209c-45af-9754-b6f3bf7ca50f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:04c7ea607e28a3dd4fee623a9ca26b96843ba5e23cfb0a814d55b637d089c780","target":"record","created_at":"2026-05-20T00:00:59Z","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":"49dd21b8cf8cbcecac185e9b3d228ecfb376867870c8c180ba8b3a3889be1946","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T22:41:01Z","title_canon_sha256":"dc46a3f87fb546ad38ad9fccf985fd41d5c06dfc22ee793bf571dbc2d309494a"},"schema_version":"1.0","source":{"id":"2605.15459","kind":"arxiv","version":1}},"canonical_sha256":"ff7eeeda484c50d0751c5cace9936f18d7804a04e1c061229c5e39554c70f9ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff7eeeda484c50d0751c5cace9936f18d7804a04e1c061229c5e39554c70f9ac","first_computed_at":"2026-05-20T00:00:59.679172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:59.679172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AqC+su+G0/d0qTwKs+pUk02hYaG05oiapLejNFG4PB+Rh5jbBDS6f5XgBmG7aP3GVk064bRDzfIEBpe4HmQyCw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:59.679978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15459","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04c7ea607e28a3dd4fee623a9ca26b96843ba5e23cfb0a814d55b637d089c780","sha256:3f33cec9a0e653537a0f9d263a58cab9400e409c4cc117760227bd9f7ffd0e23"],"state_sha256":"6467871ca40cf3d0ba852c82f3e43e4e1f13e08bdd90b5b2c0f8fced0be58ac6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1f1YaxL1GzlzfP0H2WVx6HHplmcNQ6oGzcFFoKASD84h0FSUSSKV8B1hLEhGk05DIpCi/GolqZhRuLQ+PvLIBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T20:26:18.828646Z","bundle_sha256":"f85f01e98fe634300565865e8443ae02c7685c6d6acca5ed8d0a96bc7ce28d31"}}