{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VV3IKPFETLF6ZBIYZN2I3MZCEN","short_pith_number":"pith:VV3IKPFE","canonical_record":{"source":{"id":"2603.21717","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-23T09:01:02Z","cross_cats_sorted":[],"title_canon_sha256":"31828eeb2e0b535b46b4d658c58b2c34a54f477b0029ff79a6aafe0e4d9bf46b","abstract_canon_sha256":"4443010cc7f0a04c6d7225a1c6552f1b47edb5101cd78828e7bb3aa63805a46a"},"schema_version":"1.0"},"canonical_sha256":"ad76853ca49acbec8518cb748db322235805bb46319485a39cf6f8ce6bb83d4f","source":{"kind":"arxiv","id":"2603.21717","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.21717","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"arxiv_version","alias_value":"2603.21717v4","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.21717","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"pith_short_12","alias_value":"VV3IKPFETLF6","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"pith_short_16","alias_value":"VV3IKPFETLF6ZBIY","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"pith_short_8","alias_value":"VV3IKPFE","created_at":"2026-05-22T01:03:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VV3IKPFETLF6ZBIYZN2I3MZCEN","target":"record","payload":{"canonical_record":{"source":{"id":"2603.21717","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-23T09:01:02Z","cross_cats_sorted":[],"title_canon_sha256":"31828eeb2e0b535b46b4d658c58b2c34a54f477b0029ff79a6aafe0e4d9bf46b","abstract_canon_sha256":"4443010cc7f0a04c6d7225a1c6552f1b47edb5101cd78828e7bb3aa63805a46a"},"schema_version":"1.0"},"canonical_sha256":"ad76853ca49acbec8518cb748db322235805bb46319485a39cf6f8ce6bb83d4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:18.828442Z","signature_b64":"wicsWdN0ks3qIvkviV6CV7w0iJGwubMrhQe4TLJEoa3gC/1hK9ZEUFfrCH471cEEc8yAhaQxC/5gERRH8FSFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad76853ca49acbec8518cb748db322235805bb46319485a39cf6f8ce6bb83d4f","last_reissued_at":"2026-05-22T01:03:18.827506Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:18.827506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.21717","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:03:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W85Zji8P7TlgRUhsOSqa2ujjtKNDEtNyE+e2iBXpXyWFKjj+VN0RaEVd23Isoe4gS0sV5A9amt+x1VrhR0oaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T19:17:07.179749Z"},"content_sha256":"ab4608476f42f550134fa0bc3f3774ffeecc79974d0e1812cd143c3916a2e9c1","schema_version":"1.0","event_id":"sha256:ab4608476f42f550134fa0bc3f3774ffeecc79974d0e1812cd143c3916a2e9c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VV3IKPFETLF6ZBIYZN2I3MZCEN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imaging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Bayesian Stochastic Flow Matching disentangles aleatoric and epistemic uncertainty in distribution-to-distribution generative models.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dongxia Wu, Emily B. Fox, Emma Lundberg, Serena Yeung-Levy, Yuhui Zhang","submitted_at":"2026-03-23T09:01:02Z","abstract_excerpt":"Distribution-to-distribution generative models support scientific imaging tasks ranging from modeling cellular perturbation responses to translating medical images across conditions. Trustworthy generation requires reliability, or generalization across labs, devices, and experimental conditions, and accountability, or detecting out-of-distribution cases where predictions may be unreliable. We leverage Stochastic Flow Matching (SFM), a marginal-preserving stochastic extension of flow matching for improved generalization under distribution shift. SFM augments deterministic flows with a diffusion"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We present a unified UQ framework, Bayesian Stochastic Flow Matching (BSFM), that disentangles aleatoric and epistemic uncertainty.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that augmenting deterministic flows with a diffusion term (SFM) improves generalization to unseen scenarios and that MCD-Antithetic produces effective anomaly scores, without supporting derivations or controls visible in the abstract.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Bayesian Stochastic Flow Matching augments flow models with stochastic diffusion for better generalization and uses Monte Carlo Dropout with antithetic sampling to disentangle uncertainties and detect out-of-distribution cases in scientific imaging.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Bayesian Stochastic Flow Matching disentangles aleatoric and epistemic uncertainty in distribution-to-distribution generative models.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f08617f4ce4a9720a281d6c8610d3961050ea43d7f8db3d10e7b9a1eb3670d3a"},"source":{"id":"2603.21717","kind":"arxiv","version":4},"verdict":{"id":"53f767e5-beb4-4736-942d-c8ef75acf747","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:07:12.680827Z","strongest_claim":"We present a unified UQ framework, Bayesian Stochastic Flow Matching (BSFM), that disentangles aleatoric and epistemic uncertainty.","one_line_summary":"Bayesian Stochastic Flow Matching augments flow models with stochastic diffusion for better generalization and uses Monte Carlo Dropout with antithetic sampling to disentangle uncertainties and detect out-of-distribution cases in scientific imaging.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that augmenting deterministic flows with a diffusion term (SFM) improves generalization to unseen scenarios and that MCD-Antithetic produces effective anomaly scores, without supporting derivations or controls visible in the abstract.","pith_extraction_headline":"Bayesian Stochastic Flow Matching disentangles aleatoric and epistemic uncertainty in distribution-to-distribution generative models."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.21717/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":"53f767e5-beb4-4736-942d-c8ef75acf747"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:03:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wEdOFby+ZBhYw4EJPBCHxm9agoO9tBhDzyxRhG/ndilE+osE4mWWP6HaCtnnc2hWHGcb7rZw/FKZ0luUwQlaAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T19:17:07.180630Z"},"content_sha256":"e27b05ca6b66ae88368c90d6453e5cbe750e9b5ecb6dadc7ad1b7ff9ad7a609a","schema_version":"1.0","event_id":"sha256:e27b05ca6b66ae88368c90d6453e5cbe750e9b5ecb6dadc7ad1b7ff9ad7a609a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VV3IKPFETLF6ZBIYZN2I3MZCEN/bundle.json","state_url":"https://pith.science/pith/VV3IKPFETLF6ZBIYZN2I3MZCEN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VV3IKPFETLF6ZBIYZN2I3MZCEN/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":"2026-05-30T19:17:07Z","links":{"resolver":"https://pith.science/pith/VV3IKPFETLF6ZBIYZN2I3MZCEN","bundle":"https://pith.science/pith/VV3IKPFETLF6ZBIYZN2I3MZCEN/bundle.json","state":"https://pith.science/pith/VV3IKPFETLF6ZBIYZN2I3MZCEN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VV3IKPFETLF6ZBIYZN2I3MZCEN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VV3IKPFETLF6ZBIYZN2I3MZCEN","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":"4443010cc7f0a04c6d7225a1c6552f1b47edb5101cd78828e7bb3aa63805a46a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-23T09:01:02Z","title_canon_sha256":"31828eeb2e0b535b46b4d658c58b2c34a54f477b0029ff79a6aafe0e4d9bf46b"},"schema_version":"1.0","source":{"id":"2603.21717","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.21717","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"arxiv_version","alias_value":"2603.21717v4","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.21717","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"pith_short_12","alias_value":"VV3IKPFETLF6","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"pith_short_16","alias_value":"VV3IKPFETLF6ZBIY","created_at":"2026-05-22T01:03:18Z"},{"alias_kind":"pith_short_8","alias_value":"VV3IKPFE","created_at":"2026-05-22T01:03:18Z"}],"graph_snapshots":[{"event_id":"sha256:e27b05ca6b66ae88368c90d6453e5cbe750e9b5ecb6dadc7ad1b7ff9ad7a609a","target":"graph","created_at":"2026-05-22T01:03:18Z","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":"We present a unified UQ framework, Bayesian Stochastic Flow Matching (BSFM), that disentangles aleatoric and epistemic uncertainty."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that augmenting deterministic flows with a diffusion term (SFM) improves generalization to unseen scenarios and that MCD-Antithetic produces effective anomaly scores, without supporting derivations or controls visible in the abstract."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Bayesian Stochastic Flow Matching augments flow models with stochastic diffusion for better generalization and uses Monte Carlo Dropout with antithetic sampling to disentangle uncertainties and detect out-of-distribution cases in scientific imaging."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Bayesian Stochastic Flow Matching disentangles aleatoric and epistemic uncertainty in distribution-to-distribution generative models."}],"snapshot_sha256":"f08617f4ce4a9720a281d6c8610d3961050ea43d7f8db3d10e7b9a1eb3670d3a"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.21717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distribution-to-distribution generative models support scientific imaging tasks ranging from modeling cellular perturbation responses to translating medical images across conditions. Trustworthy generation requires reliability, or generalization across labs, devices, and experimental conditions, and accountability, or detecting out-of-distribution cases where predictions may be unreliable. We leverage Stochastic Flow Matching (SFM), a marginal-preserving stochastic extension of flow matching for improved generalization under distribution shift. SFM augments deterministic flows with a diffusion","authors_text":"Dongxia Wu, Emily B. Fox, Emma Lundberg, Serena Yeung-Levy, Yuhui Zhang","cross_cats":[],"headline":"Bayesian Stochastic Flow Matching disentangles aleatoric and epistemic uncertainty in distribution-to-distribution generative models.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-23T09:01:02Z","title":"Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imaging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.21717","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-15T01:07:12.680827Z","id":"53f767e5-beb4-4736-942d-c8ef75acf747","model_set":{"reader":"grok-4.3"},"one_line_summary":"Bayesian Stochastic Flow Matching augments flow models with stochastic diffusion for better generalization and uses Monte Carlo Dropout with antithetic sampling to disentangle uncertainties and detect out-of-distribution cases in scientific imaging.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Bayesian Stochastic Flow Matching disentangles aleatoric and epistemic uncertainty in distribution-to-distribution generative models.","strongest_claim":"We present a unified UQ framework, Bayesian Stochastic Flow Matching (BSFM), that disentangles aleatoric and epistemic uncertainty.","weakest_assumption":"The assumption that augmenting deterministic flows with a diffusion term (SFM) improves generalization to unseen scenarios and that MCD-Antithetic produces effective anomaly scores, without supporting derivations or controls visible in the abstract."}},"verdict_id":"53f767e5-beb4-4736-942d-c8ef75acf747"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ab4608476f42f550134fa0bc3f3774ffeecc79974d0e1812cd143c3916a2e9c1","target":"record","created_at":"2026-05-22T01:03:18Z","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":"4443010cc7f0a04c6d7225a1c6552f1b47edb5101cd78828e7bb3aa63805a46a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-23T09:01:02Z","title_canon_sha256":"31828eeb2e0b535b46b4d658c58b2c34a54f477b0029ff79a6aafe0e4d9bf46b"},"schema_version":"1.0","source":{"id":"2603.21717","kind":"arxiv","version":4}},"canonical_sha256":"ad76853ca49acbec8518cb748db322235805bb46319485a39cf6f8ce6bb83d4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad76853ca49acbec8518cb748db322235805bb46319485a39cf6f8ce6bb83d4f","first_computed_at":"2026-05-22T01:03:18.827506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:18.827506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wicsWdN0ks3qIvkviV6CV7w0iJGwubMrhQe4TLJEoa3gC/1hK9ZEUFfrCH471cEEc8yAhaQxC/5gERRH8FSFDw==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:18.828442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.21717","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab4608476f42f550134fa0bc3f3774ffeecc79974d0e1812cd143c3916a2e9c1","sha256:e27b05ca6b66ae88368c90d6453e5cbe750e9b5ecb6dadc7ad1b7ff9ad7a609a"],"state_sha256":"636a9bd4a18cbb3b62664ef485ca5c93c766b6cd6665c0d26fd6614148ae2187"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hLqF1isD/01tQFmavEHiMZ34z4IBMUv+bCZZHVa17tLcj7V8MpTV3P56Ee72DSyhJb62Aye3aFp0lCvUK87GBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T19:17:07.190144Z","bundle_sha256":"6e8aa2ae20bd42747d57913b03d7b26df04fad0ac304eb76661960e6cd599873"}}