{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SEF5I24WFJMTZCXQDI6KOJVLLD","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":"8cff2f3350b0b6a5da15651cdea07087dca69a938bb81715cb1a70d50c8b9cb3","cross_cats_sorted":["eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-12T14:25:32Z","title_canon_sha256":"f2d46b9052feeeebd8218ff0277948d48e608764902bc5a0506e58e7a8bd385c"},"schema_version":"1.0","source":{"id":"2104.05495","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.05495","created_at":"2026-07-05T02:31:13Z"},{"alias_kind":"arxiv_version","alias_value":"2104.05495v1","created_at":"2026-07-05T02:31:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05495","created_at":"2026-07-05T02:31:13Z"},{"alias_kind":"pith_short_12","alias_value":"SEF5I24WFJMT","created_at":"2026-07-05T02:31:13Z"},{"alias_kind":"pith_short_16","alias_value":"SEF5I24WFJMTZCXQ","created_at":"2026-07-05T02:31:13Z"},{"alias_kind":"pith_short_8","alias_value":"SEF5I24W","created_at":"2026-07-05T02:31:13Z"}],"graph_snapshots":[{"event_id":"sha256:75fc04fc1deab670d11a68be9a08300f619a704ee17a81feea7af06b71420d85","target":"graph","created_at":"2026-07-05T02:31:13Z","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/2104.05495/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While convolutional neural networks (CNNs) trained by back-propagation have seen unprecedented success at semantic segmentation tasks, they are known to struggle on out-of-distribution data. Markov random fields (MRFs) on the other hand, encode simpler distributions over labels that, although less flexible than UNets, are less prone to over-fitting. In this paper, we propose to fuse both strategies by computing the product of distributions of a UNet and an MRF. As this product is intractable, we solve for an approximate distribution using an iterative mean-field approach. The resulting MRF-UNe","authors_text":"Geraint Rees, John Ashburner, Mikael Brudfors, M. Jorge Cardoso, Parashkev Nachev, S\\'ebastien Ourselin, Ya\\\"el Balbastre","cross_cats":["eess.IV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-12T14:25:32Z","title":"An MRF-UNet Product of Experts for Image Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05495","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":"sha256:137465993065502f52c2ccc4d02671472534b01ce9e549dd44322501c8aea470","target":"record","created_at":"2026-07-05T02:31:13Z","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":"8cff2f3350b0b6a5da15651cdea07087dca69a938bb81715cb1a70d50c8b9cb3","cross_cats_sorted":["eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-12T14:25:32Z","title_canon_sha256":"f2d46b9052feeeebd8218ff0277948d48e608764902bc5a0506e58e7a8bd385c"},"schema_version":"1.0","source":{"id":"2104.05495","kind":"arxiv","version":1}},"canonical_sha256":"910bd46b962a593c8af01a3ca726ab58cb74539d4db11593cad19621eb94d530","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"910bd46b962a593c8af01a3ca726ab58cb74539d4db11593cad19621eb94d530","first_computed_at":"2026-07-05T02:31:13.276416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:31:13.276416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"guXz5eU+2leRhiIOM0L1YPqdIqXfJ2IYNfg13SmbBuztCbpI5O00MDy6L0M00VAgUzOeT/axKX0rtHRb8rj1Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:31:13.276845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.05495","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:137465993065502f52c2ccc4d02671472534b01ce9e549dd44322501c8aea470","sha256:75fc04fc1deab670d11a68be9a08300f619a704ee17a81feea7af06b71420d85"],"state_sha256":"881c51e2f82bcf107260720f291556ae2c1831ad4a783b77e81921aff01abafd"}