{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:IQQOG3K7BIZACFGWWCTA5MTW6I","short_pith_number":"pith:IQQOG3K7","canonical_record":{"source":{"id":"2106.10070","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-18T11:37:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"37368213c3b4227e7524e4178ac3313543c308e937c6d896191fa55a2f1787d7","abstract_canon_sha256":"3513f03d864dbfc984081f03bf5fb9076a97a12f2fbcd764f8e9194bc281a6af"},"schema_version":"1.0"},"canonical_sha256":"4420e36d5f0a320114d6b0a60eb276f21237488ddefaaec799564ec86aeacf29","source":{"kind":"arxiv","id":"2106.10070","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.10070","created_at":"2026-07-05T04:18:14Z"},{"alias_kind":"arxiv_version","alias_value":"2106.10070v2","created_at":"2026-07-05T04:18:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10070","created_at":"2026-07-05T04:18:14Z"},{"alias_kind":"pith_short_12","alias_value":"IQQOG3K7BIZA","created_at":"2026-07-05T04:18:14Z"},{"alias_kind":"pith_short_16","alias_value":"IQQOG3K7BIZACFGW","created_at":"2026-07-05T04:18:14Z"},{"alias_kind":"pith_short_8","alias_value":"IQQOG3K7","created_at":"2026-07-05T04:18:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:IQQOG3K7BIZACFGWWCTA5MTW6I","target":"record","payload":{"canonical_record":{"source":{"id":"2106.10070","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-18T11:37:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"37368213c3b4227e7524e4178ac3313543c308e937c6d896191fa55a2f1787d7","abstract_canon_sha256":"3513f03d864dbfc984081f03bf5fb9076a97a12f2fbcd764f8e9194bc281a6af"},"schema_version":"1.0"},"canonical_sha256":"4420e36d5f0a320114d6b0a60eb276f21237488ddefaaec799564ec86aeacf29","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:18:14.970034Z","signature_b64":"/m/DSs/Gv49sjA5lZCieHibydCdfZNqEQ3cOOXZ1bgrgLDVIRn6asE3WMFJCdjL9ZWwwl+N8UXzF6Wl71BifBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4420e36d5f0a320114d6b0a60eb276f21237488ddefaaec799564ec86aeacf29","last_reissued_at":"2026-07-05T04:18:14.969574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:18:14.969574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.10070","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:18:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G05S1tUTQh1SSDnNs9N5zLcQMQly2HUlseFHij07MZQWJnwRr8AjxcDeESX6J/bo4WmWAbQ2FC9x0QiPm1/2BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T12:55:48.258664Z"},"content_sha256":"d611c44455b7572be886cdbceae23d08a263799537fd11a8415b088588f54d6b","schema_version":"1.0","event_id":"sha256:d611c44455b7572be886cdbceae23d08a263799537fd11a8415b088588f54d6b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:IQQOG3K7BIZACFGWWCTA5MTW6I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Residual Contrastive Learning for Image Reconstruction: Learning Transferable Representations from Noisy Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ales Leonardis, Eduardo P\\'erez-Pellitero, Matteo Maggioni, Nanqing Dong, Steven McDonagh, Yongxin Yang","submitted_at":"2021-06-18T11:37:05Z","abstract_excerpt":"This paper is concerned with contrastive learning (CL) for low-level image restoration and enhancement tasks. We propose a new label-efficient learning paradigm based on residuals, residual contrastive learning (RCL), and derive an unsupervised visual representation learning framework, suitable for low-level vision tasks with noisy inputs. While supervised image reconstruction aims to minimize residual terms directly, RCL alternatively builds a connection between residuals and CL by defining a novel instance discrimination pretext task, using residuals as the discriminative feature. Our formul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.10070","kind":"arxiv","version":2},"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/2106.10070/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":"2026-07-05T04:18:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pwOxADBXNxeM9/e/1EfMVg74/HHviX+4h/fbPozva8DpHgXH6eB6Z9mlpM2aqEb0OH4noihDINKv9146aIy9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T12:55:48.259285Z"},"content_sha256":"dd9b94295fcc6e3c7508c77a18127b0d0dd3eacc5f1a0ba96c252f0ec7366025","schema_version":"1.0","event_id":"sha256:dd9b94295fcc6e3c7508c77a18127b0d0dd3eacc5f1a0ba96c252f0ec7366025"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IQQOG3K7BIZACFGWWCTA5MTW6I/bundle.json","state_url":"https://pith.science/pith/IQQOG3K7BIZACFGWWCTA5MTW6I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IQQOG3K7BIZACFGWWCTA5MTW6I/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":"2026-07-05T12:55:48Z","links":{"resolver":"https://pith.science/pith/IQQOG3K7BIZACFGWWCTA5MTW6I","bundle":"https://pith.science/pith/IQQOG3K7BIZACFGWWCTA5MTW6I/bundle.json","state":"https://pith.science/pith/IQQOG3K7BIZACFGWWCTA5MTW6I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IQQOG3K7BIZACFGWWCTA5MTW6I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IQQOG3K7BIZACFGWWCTA5MTW6I","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":"3513f03d864dbfc984081f03bf5fb9076a97a12f2fbcd764f8e9194bc281a6af","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-18T11:37:05Z","title_canon_sha256":"37368213c3b4227e7524e4178ac3313543c308e937c6d896191fa55a2f1787d7"},"schema_version":"1.0","source":{"id":"2106.10070","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.10070","created_at":"2026-07-05T04:18:14Z"},{"alias_kind":"arxiv_version","alias_value":"2106.10070v2","created_at":"2026-07-05T04:18:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10070","created_at":"2026-07-05T04:18:14Z"},{"alias_kind":"pith_short_12","alias_value":"IQQOG3K7BIZA","created_at":"2026-07-05T04:18:14Z"},{"alias_kind":"pith_short_16","alias_value":"IQQOG3K7BIZACFGW","created_at":"2026-07-05T04:18:14Z"},{"alias_kind":"pith_short_8","alias_value":"IQQOG3K7","created_at":"2026-07-05T04:18:14Z"}],"graph_snapshots":[{"event_id":"sha256:dd9b94295fcc6e3c7508c77a18127b0d0dd3eacc5f1a0ba96c252f0ec7366025","target":"graph","created_at":"2026-07-05T04:18:14Z","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/2106.10070/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper is concerned with contrastive learning (CL) for low-level image restoration and enhancement tasks. We propose a new label-efficient learning paradigm based on residuals, residual contrastive learning (RCL), and derive an unsupervised visual representation learning framework, suitable for low-level vision tasks with noisy inputs. While supervised image reconstruction aims to minimize residual terms directly, RCL alternatively builds a connection between residuals and CL by defining a novel instance discrimination pretext task, using residuals as the discriminative feature. Our formul","authors_text":"Ales Leonardis, Eduardo P\\'erez-Pellitero, Matteo Maggioni, Nanqing Dong, Steven McDonagh, Yongxin Yang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-18T11:37:05Z","title":"Residual Contrastive Learning for Image Reconstruction: Learning Transferable Representations from Noisy Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.10070","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:d611c44455b7572be886cdbceae23d08a263799537fd11a8415b088588f54d6b","target":"record","created_at":"2026-07-05T04:18:14Z","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":"3513f03d864dbfc984081f03bf5fb9076a97a12f2fbcd764f8e9194bc281a6af","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-18T11:37:05Z","title_canon_sha256":"37368213c3b4227e7524e4178ac3313543c308e937c6d896191fa55a2f1787d7"},"schema_version":"1.0","source":{"id":"2106.10070","kind":"arxiv","version":2}},"canonical_sha256":"4420e36d5f0a320114d6b0a60eb276f21237488ddefaaec799564ec86aeacf29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4420e36d5f0a320114d6b0a60eb276f21237488ddefaaec799564ec86aeacf29","first_computed_at":"2026-07-05T04:18:14.969574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:18:14.969574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/m/DSs/Gv49sjA5lZCieHibydCdfZNqEQ3cOOXZ1bgrgLDVIRn6asE3WMFJCdjL9ZWwwl+N8UXzF6Wl71BifBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:18:14.970034Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.10070","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d611c44455b7572be886cdbceae23d08a263799537fd11a8415b088588f54d6b","sha256:dd9b94295fcc6e3c7508c77a18127b0d0dd3eacc5f1a0ba96c252f0ec7366025"],"state_sha256":"edaea91471b1af294d8237b859352866e3b9eb0e23cb126efc64628ed893586f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DlZF9TGC+TeRFw6xxgXTpw/J6BVDVOI5TRKXqShphF14K6KEJUqWWZZfPsKwDM5FPbGMAPFwpm05+p/qgHqWDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T12:55:48.262491Z","bundle_sha256":"85abcf1470dbaec49c06854e2cba1ca7ac971a830573832e28db7c445fc2d61a"}}