{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OWHWVJP37EZWFTZNMTJWJ4ESK3","short_pith_number":"pith:OWHWVJP3","canonical_record":{"source":{"id":"2606.21099","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-19T04:59:16Z","cross_cats_sorted":[],"title_canon_sha256":"908bb35187ea9347c5efdc3b4a9b4310b158b9ca06a67b9456242f676343765e","abstract_canon_sha256":"87e902604f8de9c481870411233afed29345602266f257ea65e158c8e4480651"},"schema_version":"1.0"},"canonical_sha256":"758f6aa5fbf93362cf2d64d364f09256e0fb37ee34b6ba24110684d0b905890c","source":{"kind":"arxiv","id":"2606.21099","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21099","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21099v1","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21099","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_12","alias_value":"OWHWVJP37EZW","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_16","alias_value":"OWHWVJP37EZWFTZN","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_8","alias_value":"OWHWVJP3","created_at":"2026-06-23T01:12:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OWHWVJP37EZWFTZNMTJWJ4ESK3","target":"record","payload":{"canonical_record":{"source":{"id":"2606.21099","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-19T04:59:16Z","cross_cats_sorted":[],"title_canon_sha256":"908bb35187ea9347c5efdc3b4a9b4310b158b9ca06a67b9456242f676343765e","abstract_canon_sha256":"87e902604f8de9c481870411233afed29345602266f257ea65e158c8e4480651"},"schema_version":"1.0"},"canonical_sha256":"758f6aa5fbf93362cf2d64d364f09256e0fb37ee34b6ba24110684d0b905890c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:29.886603Z","signature_b64":"9/w8ubymlwUfDH2D/MBXm8StKruj7tGFCseWVnYQZOYalZbmnNixl1rORCaKCtUhiYPmYJslKlQPplKnwZSECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"758f6aa5fbf93362cf2d64d364f09256e0fb37ee34b6ba24110684d0b905890c","last_reissued_at":"2026-06-23T01:12:29.886147Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:29.886147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.21099","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":"2026-06-23T01:12:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PhdcTgnA6+Z0ovptppnhplppUztPnOScrSVlVBfZ8DvozjiTvFk0LHmT1PlLqXTip+9qYgI2uIcz0ovQWK4kBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T03:31:51.308682Z"},"content_sha256":"8aa9ed16a495c05ade2f3bd150e8bb9953631607b2b7d6aa3aa4310af8b06387","schema_version":"1.0","event_id":"sha256:8aa9ed16a495c05ade2f3bd150e8bb9953631607b2b7d6aa3aa4310af8b06387"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OWHWVJP37EZWFTZNMTJWJ4ESK3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ShuffleFlow: Scalable Posterior Inference for Bayesian Inverse Imaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Emma Alexander, Tianao Li, Tjitske Starkenburg, Yu Sun","submitted_at":"2026-06-19T04:59:16Z","abstract_excerpt":"Variational inference (VI) is a powerful method for principled posterior inference for scientific inverse imaging. VI learns the posterior distribution, often with a flow-based network, which can cheaply generate posterior samples upon optimization, and can flexibly incorporate score-based or classic priors. However, its application to large-scale image reconstruction is severely hindered by the poor scalability of the flow-based networks. In this work, we introduce ShuffleFlow, a scalable VI framework to address this challenge. Our method breaks down the problem into three parts: a pixel-unsh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21099","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.21099/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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:12:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"40iJEDx1ghevr58fPge9yjZ+KBg32Ozl3jBkM2QPDDRsmvn6idoJwd2n8g5gHD9qNHHapX+rBbmPU1BQ9c64Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T03:31:51.309056Z"},"content_sha256":"19aec8cb4516334d4180b1f2cfdfefceeab0bc7186042da2fe91b217fa9615b1","schema_version":"1.0","event_id":"sha256:19aec8cb4516334d4180b1f2cfdfefceeab0bc7186042da2fe91b217fa9615b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OWHWVJP37EZWFTZNMTJWJ4ESK3/bundle.json","state_url":"https://pith.science/pith/OWHWVJP37EZWFTZNMTJWJ4ESK3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OWHWVJP37EZWFTZNMTJWJ4ESK3/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":"2026-07-01T03:31:51Z","links":{"resolver":"https://pith.science/pith/OWHWVJP37EZWFTZNMTJWJ4ESK3","bundle":"https://pith.science/pith/OWHWVJP37EZWFTZNMTJWJ4ESK3/bundle.json","state":"https://pith.science/pith/OWHWVJP37EZWFTZNMTJWJ4ESK3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OWHWVJP37EZWFTZNMTJWJ4ESK3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OWHWVJP37EZWFTZNMTJWJ4ESK3","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":"87e902604f8de9c481870411233afed29345602266f257ea65e158c8e4480651","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-19T04:59:16Z","title_canon_sha256":"908bb35187ea9347c5efdc3b4a9b4310b158b9ca06a67b9456242f676343765e"},"schema_version":"1.0","source":{"id":"2606.21099","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21099","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21099v1","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21099","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_12","alias_value":"OWHWVJP37EZW","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_16","alias_value":"OWHWVJP37EZWFTZN","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_8","alias_value":"OWHWVJP3","created_at":"2026-06-23T01:12:29Z"}],"graph_snapshots":[{"event_id":"sha256:19aec8cb4516334d4180b1f2cfdfefceeab0bc7186042da2fe91b217fa9615b1","target":"graph","created_at":"2026-06-23T01:12:29Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.21099/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Variational inference (VI) is a powerful method for principled posterior inference for scientific inverse imaging. VI learns the posterior distribution, often with a flow-based network, which can cheaply generate posterior samples upon optimization, and can flexibly incorporate score-based or classic priors. However, its application to large-scale image reconstruction is severely hindered by the poor scalability of the flow-based networks. In this work, we introduce ShuffleFlow, a scalable VI framework to address this challenge. Our method breaks down the problem into three parts: a pixel-unsh","authors_text":"Emma Alexander, Tianao Li, Tjitske Starkenburg, Yu Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-19T04:59:16Z","title":"ShuffleFlow: Scalable Posterior Inference for Bayesian Inverse Imaging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21099","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8aa9ed16a495c05ade2f3bd150e8bb9953631607b2b7d6aa3aa4310af8b06387","target":"record","created_at":"2026-06-23T01:12:29Z","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":"87e902604f8de9c481870411233afed29345602266f257ea65e158c8e4480651","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-19T04:59:16Z","title_canon_sha256":"908bb35187ea9347c5efdc3b4a9b4310b158b9ca06a67b9456242f676343765e"},"schema_version":"1.0","source":{"id":"2606.21099","kind":"arxiv","version":1}},"canonical_sha256":"758f6aa5fbf93362cf2d64d364f09256e0fb37ee34b6ba24110684d0b905890c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"758f6aa5fbf93362cf2d64d364f09256e0fb37ee34b6ba24110684d0b905890c","first_computed_at":"2026-06-23T01:12:29.886147Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:29.886147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9/w8ubymlwUfDH2D/MBXm8StKruj7tGFCseWVnYQZOYalZbmnNixl1rORCaKCtUhiYPmYJslKlQPplKnwZSECA==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:29.886603Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21099","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8aa9ed16a495c05ade2f3bd150e8bb9953631607b2b7d6aa3aa4310af8b06387","sha256:19aec8cb4516334d4180b1f2cfdfefceeab0bc7186042da2fe91b217fa9615b1"],"state_sha256":"7f2d33639ab5310d301b0232a8e8977fb515ba01d5dfbca54c28c64089c59895"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FuM5Na1m1+Ao55b5X7+RIyCxv9FOGRmF1R+/X2k0H1vS1qPBHQypQBHo+ahnfWZfzVP5CVLIKEUYXW5ylSZzCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T03:31:51.311162Z","bundle_sha256":"55b49f96e62969772c05d5c5503626b14f7d619bca0c7c48837a6c423db3e1dd"}}