{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IJUFY3ZG3H4MGAHOI3JDDPTH7W","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":"0943f490ffd1be0f477a288d8620bb97293607ab9058392d002b54ab040467a3","cross_cats_sorted":["cs.AI","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-29T05:57:03Z","title_canon_sha256":"0a3f97fa40f01460342d123510de4056b918ccb956d5e2f00bd741ffdcc3d7e9"},"schema_version":"1.0","source":{"id":"2404.18444","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18444","created_at":"2026-07-05T08:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18444v2","created_at":"2026-07-05T08:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18444","created_at":"2026-07-05T08:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"IJUFY3ZG3H4M","created_at":"2026-07-05T08:14:06Z"},{"alias_kind":"pith_short_16","alias_value":"IJUFY3ZG3H4MGAHO","created_at":"2026-07-05T08:14:06Z"},{"alias_kind":"pith_short_8","alias_value":"IJUFY3ZG","created_at":"2026-07-05T08:14:06Z"}],"graph_snapshots":[{"event_id":"sha256:3d6a2d506355eef087bb5db1970c5162b8a635df0de1da0cd0efdcead489471d","target":"graph","created_at":"2026-07-05T08:14:06Z","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/2404.18444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"U-Nets are among the most widely used architectures in computer vision, renowned for their exceptional performance in applications such as image segmentation, denoising, and diffusion modeling. However, a theoretical explanation of the U-Net architecture design has not yet been fully established.\n  This paper introduces a novel interpretation of the U-Net architecture by studying certain generative hierarchical models, which are tree-structured graphical models extensively utilized in both language and image domains. With their encoder-decoder structure, long skip connections, and pooling and ","authors_text":"Song Mei","cross_cats":["cs.AI","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-29T05:57:03Z","title":"U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18444","kind":"arxiv","version":2},"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":"sha256:05d0a63cdbdcf11bb701c17994eceaca6ea063c4871677175dca5d5e41ca25ab","target":"record","created_at":"2026-07-05T08:14:06Z","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":"0943f490ffd1be0f477a288d8620bb97293607ab9058392d002b54ab040467a3","cross_cats_sorted":["cs.AI","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-29T05:57:03Z","title_canon_sha256":"0a3f97fa40f01460342d123510de4056b918ccb956d5e2f00bd741ffdcc3d7e9"},"schema_version":"1.0","source":{"id":"2404.18444","kind":"arxiv","version":2}},"canonical_sha256":"42685c6f26d9f8c300ee46d231be67fd895a388ae089af86da239a644a125215","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42685c6f26d9f8c300ee46d231be67fd895a388ae089af86da239a644a125215","first_computed_at":"2026-07-05T08:14:06.389994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:14:06.389994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ngppErbxMMMaGZ74O4krpN2nC5UcqND8/J7A1uSsKcVGPpEH3yEpiIOQfu8sSdWqpZ0aAU/BNLq/rRqKlSk1Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:14:06.390541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.18444","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05d0a63cdbdcf11bb701c17994eceaca6ea063c4871677175dca5d5e41ca25ab","sha256:3d6a2d506355eef087bb5db1970c5162b8a635df0de1da0cd0efdcead489471d"],"state_sha256":"d7757f2702ed4526609d3d45d2284c9f975953ee1586814f9bb4f5185e32ce15"}