{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:UV36QCALFHYMBTQWFHP64N7M4L","short_pith_number":"pith:UV36QCAL","canonical_record":{"source":{"id":"2003.12022","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-26T16:42:22Z","cross_cats_sorted":[],"title_canon_sha256":"fbccc4a43264c0901651650f6a25aa8b2e19824ae94124ecdfb4cb056701d7f5","abstract_canon_sha256":"6588cd012df11c98ab8b83c61fca3c459cd77a75ebb3c648a3cccde90cbe1c53"},"schema_version":"1.0"},"canonical_sha256":"a577e8080b29f0c0ce1629dfee37ece2fb1dc531111f4244a171f9f8ba2e488c","source":{"kind":"arxiv","id":"2003.12022","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.12022","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"arxiv_version","alias_value":"2003.12022v3","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12022","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"pith_short_12","alias_value":"UV36QCALFHYM","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"pith_short_16","alias_value":"UV36QCALFHYMBTQW","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"pith_short_8","alias_value":"UV36QCAL","created_at":"2026-07-05T01:08:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:UV36QCALFHYMBTQWFHP64N7M4L","target":"record","payload":{"canonical_record":{"source":{"id":"2003.12022","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-26T16:42:22Z","cross_cats_sorted":[],"title_canon_sha256":"fbccc4a43264c0901651650f6a25aa8b2e19824ae94124ecdfb4cb056701d7f5","abstract_canon_sha256":"6588cd012df11c98ab8b83c61fca3c459cd77a75ebb3c648a3cccde90cbe1c53"},"schema_version":"1.0"},"canonical_sha256":"a577e8080b29f0c0ce1629dfee37ece2fb1dc531111f4244a171f9f8ba2e488c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:28.752725Z","signature_b64":"a/pRgSX5V4d9RQ/V/tqUXTKb2rpHssSlyj+ZMiqMmc60KbK2EKkyyAcKL3GlbzMV/ETKeOD+h3XFuJ/ealenBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a577e8080b29f0c0ce1629dfee37ece2fb1dc531111f4244a171f9f8ba2e488c","last_reissued_at":"2026-07-05T01:08:28.752205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:28.752205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.12022","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:08:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XL3Z1KsY22U0YlENpDOUvgbBF70JBQbnQsBH3NTYOzt4ObTSji5l2ywHap5WMMXVHVVm9TPzjKlzPf6WH8IBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:38:00.648947Z"},"content_sha256":"5d61761b694527743e3d73041ee1ec9ce23d23f50311a0c3ea6b9336c29eff9a","schema_version":"1.0","event_id":"sha256:5d61761b694527743e3d73041ee1ec9ce23d23f50311a0c3ea6b9336c29eff9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:UV36QCALFHYMBTQWFHP64N7M4L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Milking CowMask for Semi-Supervised Image Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Avital Oliver, Geoff French, Tim Salimans","submitted_at":"2020-03-26T16:42:22Z","abstract_excerpt":"Consistency regularization is a technique for semi-supervised learning that underlies a number of strong results for classification with few labeled data. It works by encouraging a learned model to be robust to perturbations on unlabeled data. Here, we present a novel mask-based augmentation method called CowMask. Using it to provide perturbations for semi-supervised consistency regularization, we achieve a state-of-the-art result on ImageNet with 10% labeled data, with a top-5 error of 8.76% and top-1 error of 26.06%. Moreover, we do so with a method that is much simpler than many alternative"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12022","kind":"arxiv","version":3},"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/2003.12022/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":"2026-07-05T01:08:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kcQuk2qLypjyznHaUE0yBoNqY5h5OGdLlvW6QjPnYzN6H6KioG8hrxkCEYtF0fTW92dhygc82XvjzdWn7wZOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:38:00.649438Z"},"content_sha256":"2f978b3250a362102be01d1e26cb9ae1d26f65798edc3451532c44c03708eccb","schema_version":"1.0","event_id":"sha256:2f978b3250a362102be01d1e26cb9ae1d26f65798edc3451532c44c03708eccb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UV36QCALFHYMBTQWFHP64N7M4L/bundle.json","state_url":"https://pith.science/pith/UV36QCALFHYMBTQWFHP64N7M4L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UV36QCALFHYMBTQWFHP64N7M4L/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":"2026-08-10T01:38:00Z","links":{"resolver":"https://pith.science/pith/UV36QCALFHYMBTQWFHP64N7M4L","bundle":"https://pith.science/pith/UV36QCALFHYMBTQWFHP64N7M4L/bundle.json","state":"https://pith.science/pith/UV36QCALFHYMBTQWFHP64N7M4L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UV36QCALFHYMBTQWFHP64N7M4L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UV36QCALFHYMBTQWFHP64N7M4L","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":"6588cd012df11c98ab8b83c61fca3c459cd77a75ebb3c648a3cccde90cbe1c53","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-26T16:42:22Z","title_canon_sha256":"fbccc4a43264c0901651650f6a25aa8b2e19824ae94124ecdfb4cb056701d7f5"},"schema_version":"1.0","source":{"id":"2003.12022","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.12022","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"arxiv_version","alias_value":"2003.12022v3","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12022","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"pith_short_12","alias_value":"UV36QCALFHYM","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"pith_short_16","alias_value":"UV36QCALFHYMBTQW","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"pith_short_8","alias_value":"UV36QCAL","created_at":"2026-07-05T01:08:28Z"}],"graph_snapshots":[{"event_id":"sha256:2f978b3250a362102be01d1e26cb9ae1d26f65798edc3451532c44c03708eccb","target":"graph","created_at":"2026-07-05T01:08:28Z","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/2003.12022/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Consistency regularization is a technique for semi-supervised learning that underlies a number of strong results for classification with few labeled data. It works by encouraging a learned model to be robust to perturbations on unlabeled data. Here, we present a novel mask-based augmentation method called CowMask. Using it to provide perturbations for semi-supervised consistency regularization, we achieve a state-of-the-art result on ImageNet with 10% labeled data, with a top-5 error of 8.76% and top-1 error of 26.06%. Moreover, we do so with a method that is much simpler than many alternative","authors_text":"Avital Oliver, Geoff French, Tim Salimans","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-26T16:42:22Z","title":"Milking CowMask for Semi-Supervised Image Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12022","kind":"arxiv","version":3},"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":"sha256:5d61761b694527743e3d73041ee1ec9ce23d23f50311a0c3ea6b9336c29eff9a","target":"record","created_at":"2026-07-05T01:08:28Z","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":"6588cd012df11c98ab8b83c61fca3c459cd77a75ebb3c648a3cccde90cbe1c53","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-26T16:42:22Z","title_canon_sha256":"fbccc4a43264c0901651650f6a25aa8b2e19824ae94124ecdfb4cb056701d7f5"},"schema_version":"1.0","source":{"id":"2003.12022","kind":"arxiv","version":3}},"canonical_sha256":"a577e8080b29f0c0ce1629dfee37ece2fb1dc531111f4244a171f9f8ba2e488c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a577e8080b29f0c0ce1629dfee37ece2fb1dc531111f4244a171f9f8ba2e488c","first_computed_at":"2026-07-05T01:08:28.752205Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:08:28.752205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a/pRgSX5V4d9RQ/V/tqUXTKb2rpHssSlyj+ZMiqMmc60KbK2EKkyyAcKL3GlbzMV/ETKeOD+h3XFuJ/ealenBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:08:28.752725Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.12022","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d61761b694527743e3d73041ee1ec9ce23d23f50311a0c3ea6b9336c29eff9a","sha256:2f978b3250a362102be01d1e26cb9ae1d26f65798edc3451532c44c03708eccb"],"state_sha256":"bb5224b6d3f54d7f4032f4213812188f5a0ffad7009da576e6b9bb66859fd069"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9yEBE3JGWcJoiZRyvQDCTaaCJu/3Sw9nbDlp28QIWpNfEqSahwfi4IUliU7nVga+YYbSsJPuNUTaapmqGOwtBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T01:38:00.652714Z","bundle_sha256":"eefe4559a0b8432232ad58035c21096c02cd3d2c9a90e9108e6ff39c040cd45f"}}