{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:M43VC25VZ5J4FY7GR43PVXBGC6","short_pith_number":"pith:M43VC25V","canonical_record":{"source":{"id":"2202.02018","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-04T08:36:34Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"2001043481f6de7cea73ba52bfe7a8369a34c2df4ce08db911e81813dcf1b473","abstract_canon_sha256":"1778a150e567fc8f063ff334a6437d70ff49a8ca93a601527c797b5e1e6e2fa7"},"schema_version":"1.0"},"canonical_sha256":"6737516bb5cf53c2e3e68f36fadc2617aa709c295faac76b1ed547265abd75c3","source":{"kind":"arxiv","id":"2202.02018","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.02018","created_at":"2026-07-05T03:54:08Z"},{"alias_kind":"arxiv_version","alias_value":"2202.02018v1","created_at":"2026-07-05T03:54:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.02018","created_at":"2026-07-05T03:54:08Z"},{"alias_kind":"pith_short_12","alias_value":"M43VC25VZ5J4","created_at":"2026-07-05T03:54:08Z"},{"alias_kind":"pith_short_16","alias_value":"M43VC25VZ5J4FY7G","created_at":"2026-07-05T03:54:08Z"},{"alias_kind":"pith_short_8","alias_value":"M43VC25V","created_at":"2026-07-05T03:54:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:M43VC25VZ5J4FY7GR43PVXBGC6","target":"record","payload":{"canonical_record":{"source":{"id":"2202.02018","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-04T08:36:34Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"2001043481f6de7cea73ba52bfe7a8369a34c2df4ce08db911e81813dcf1b473","abstract_canon_sha256":"1778a150e567fc8f063ff334a6437d70ff49a8ca93a601527c797b5e1e6e2fa7"},"schema_version":"1.0"},"canonical_sha256":"6737516bb5cf53c2e3e68f36fadc2617aa709c295faac76b1ed547265abd75c3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:08.104191Z","signature_b64":"vVqIgVA80CPBJJABPu6IY1suTGYSV64rS3olsNyN6nGLo/z+2rNZVaxdXzNzSU33NZx5anH6GBcgHFav0H+aAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6737516bb5cf53c2e3e68f36fadc2617aa709c295faac76b1ed547265abd75c3","last_reissued_at":"2026-07-05T03:54:08.103623Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:08.103623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.02018","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":"2026-07-05T03:54:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tUX3pSSSnaroiF50lpW7jDuFyNW+Dy+aAEbPt+RTwO1Mtl1ouowX0n1sthPKP8TqZxMUJ4j5PL21pvpdoFEdCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:49:33.917560Z"},"content_sha256":"051d59063a62601361cd8a8e512bcea05167f15290e77dffc94956ba6c5e2890","schema_version":"1.0","event_id":"sha256:051d59063a62601361cd8a8e512bcea05167f15290e77dffc94956ba6c5e2890"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:M43VC25VZ5J4FY7GR43PVXBGC6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Image-to-Image MLP-mixer for Image Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Kang Lin, Reinhard Heckel, Youssef Mansour","submitted_at":"2022-02-04T08:36:34Z","abstract_excerpt":"Neural networks are highly effective tools for image reconstruction problems such as denoising and compressive sensing. To date, neural networks for image reconstruction are almost exclusively convolutional. The most popular architecture is the U-Net, a convolutional network with a multi-resolution architecture. In this work, we show that a simple network based on the multi-layer perceptron (MLP)-mixer enables state-of-the art image reconstruction performance without convolutions and without a multi-resolution architecture, provided that the training set and the size of the network are moderat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.02018","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/2202.02018/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":"2026-07-05T03:54:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mJm+k3zDizd1noXvjl311Wbk2+xRuPyL2qIki3y7mf5XmME2Dya48EuSc0u5VLohRALSNq8crCS0QCL0tTVdDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:49:33.918096Z"},"content_sha256":"bf30cfd973def802d10a69a64ca23c851f0c94c6501a1a481a1465cedac71e7e","schema_version":"1.0","event_id":"sha256:bf30cfd973def802d10a69a64ca23c851f0c94c6501a1a481a1465cedac71e7e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M43VC25VZ5J4FY7GR43PVXBGC6/bundle.json","state_url":"https://pith.science/pith/M43VC25VZ5J4FY7GR43PVXBGC6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M43VC25VZ5J4FY7GR43PVXBGC6/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":"2026-08-11T08:49:33Z","links":{"resolver":"https://pith.science/pith/M43VC25VZ5J4FY7GR43PVXBGC6","bundle":"https://pith.science/pith/M43VC25VZ5J4FY7GR43PVXBGC6/bundle.json","state":"https://pith.science/pith/M43VC25VZ5J4FY7GR43PVXBGC6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M43VC25VZ5J4FY7GR43PVXBGC6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:M43VC25VZ5J4FY7GR43PVXBGC6","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":"1778a150e567fc8f063ff334a6437d70ff49a8ca93a601527c797b5e1e6e2fa7","cross_cats_sorted":["cs.LG","eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-04T08:36:34Z","title_canon_sha256":"2001043481f6de7cea73ba52bfe7a8369a34c2df4ce08db911e81813dcf1b473"},"schema_version":"1.0","source":{"id":"2202.02018","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.02018","created_at":"2026-07-05T03:54:08Z"},{"alias_kind":"arxiv_version","alias_value":"2202.02018v1","created_at":"2026-07-05T03:54:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.02018","created_at":"2026-07-05T03:54:08Z"},{"alias_kind":"pith_short_12","alias_value":"M43VC25VZ5J4","created_at":"2026-07-05T03:54:08Z"},{"alias_kind":"pith_short_16","alias_value":"M43VC25VZ5J4FY7G","created_at":"2026-07-05T03:54:08Z"},{"alias_kind":"pith_short_8","alias_value":"M43VC25V","created_at":"2026-07-05T03:54:08Z"}],"graph_snapshots":[{"event_id":"sha256:bf30cfd973def802d10a69a64ca23c851f0c94c6501a1a481a1465cedac71e7e","target":"graph","created_at":"2026-07-05T03:54:08Z","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/2202.02018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural networks are highly effective tools for image reconstruction problems such as denoising and compressive sensing. To date, neural networks for image reconstruction are almost exclusively convolutional. The most popular architecture is the U-Net, a convolutional network with a multi-resolution architecture. In this work, we show that a simple network based on the multi-layer perceptron (MLP)-mixer enables state-of-the art image reconstruction performance without convolutions and without a multi-resolution architecture, provided that the training set and the size of the network are moderat","authors_text":"Kang Lin, Reinhard Heckel, Youssef Mansour","cross_cats":["cs.LG","eess.IV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-04T08:36:34Z","title":"Image-to-Image MLP-mixer for Image Reconstruction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.02018","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":"sha256:051d59063a62601361cd8a8e512bcea05167f15290e77dffc94956ba6c5e2890","target":"record","created_at":"2026-07-05T03:54:08Z","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":"1778a150e567fc8f063ff334a6437d70ff49a8ca93a601527c797b5e1e6e2fa7","cross_cats_sorted":["cs.LG","eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-04T08:36:34Z","title_canon_sha256":"2001043481f6de7cea73ba52bfe7a8369a34c2df4ce08db911e81813dcf1b473"},"schema_version":"1.0","source":{"id":"2202.02018","kind":"arxiv","version":1}},"canonical_sha256":"6737516bb5cf53c2e3e68f36fadc2617aa709c295faac76b1ed547265abd75c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6737516bb5cf53c2e3e68f36fadc2617aa709c295faac76b1ed547265abd75c3","first_computed_at":"2026-07-05T03:54:08.103623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:54:08.103623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vVqIgVA80CPBJJABPu6IY1suTGYSV64rS3olsNyN6nGLo/z+2rNZVaxdXzNzSU33NZx5anH6GBcgHFav0H+aAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:54:08.104191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.02018","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:051d59063a62601361cd8a8e512bcea05167f15290e77dffc94956ba6c5e2890","sha256:bf30cfd973def802d10a69a64ca23c851f0c94c6501a1a481a1465cedac71e7e"],"state_sha256":"0de1bc844e571501007ee0f52e88d300f76a04d36125eaf6265c4bf5ab099f70"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0AoolvO4eeiKav6hzopqWjRq31m+yu5dnGbEUj9y04Ho3aGcLTsrlH+3W/LDtL5XNfcqvscpc8o+ummhdCnyCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T08:49:33.923259Z","bundle_sha256":"5b573da195d68ed48d4d4e5fd69f79bd8617f1e1b4d8021d4fc1e33d5c090051"}}