{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:REZHTCQRCZV3HKO2Z3HS65PBM3","short_pith_number":"pith:REZHTCQR","canonical_record":{"source":{"id":"2103.14749","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-03-26T21:54:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a82fc7eaba50cfd80027c2ffd6b1791163bfa9ed5fc72d35062d926924beb8e1","abstract_canon_sha256":"1cf5eb8f9d4a07e1f5044d84d9a113ae71e374b45bc1bbd4e2c06095d46b9646"},"schema_version":"1.0"},"canonical_sha256":"8932798a11166bb3a9dacecf2f75e166e006bffb064d2179d0331e3e1027c093","source":{"kind":"arxiv","id":"2103.14749","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.14749","created_at":"2026-07-05T03:29:48Z"},{"alias_kind":"arxiv_version","alias_value":"2103.14749v4","created_at":"2026-07-05T03:29:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14749","created_at":"2026-07-05T03:29:48Z"},{"alias_kind":"pith_short_12","alias_value":"REZHTCQRCZV3","created_at":"2026-07-05T03:29:48Z"},{"alias_kind":"pith_short_16","alias_value":"REZHTCQRCZV3HKO2","created_at":"2026-07-05T03:29:48Z"},{"alias_kind":"pith_short_8","alias_value":"REZHTCQR","created_at":"2026-07-05T03:29:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:REZHTCQRCZV3HKO2Z3HS65PBM3","target":"record","payload":{"canonical_record":{"source":{"id":"2103.14749","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-03-26T21:54:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a82fc7eaba50cfd80027c2ffd6b1791163bfa9ed5fc72d35062d926924beb8e1","abstract_canon_sha256":"1cf5eb8f9d4a07e1f5044d84d9a113ae71e374b45bc1bbd4e2c06095d46b9646"},"schema_version":"1.0"},"canonical_sha256":"8932798a11166bb3a9dacecf2f75e166e006bffb064d2179d0331e3e1027c093","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:48.043663Z","signature_b64":"8nXyspMMxYHzU7gDKz+XaR2As7bWSQ0XjEUi1r51zJvQOXcrAHMD0qxN/rDLiYZH03+vqLGez1498wCDW7/gDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8932798a11166bb3a9dacecf2f75e166e006bffb064d2179d0331e3e1027c093","last_reissued_at":"2026-07-05T03:29:48.043233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:48.043233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.14749","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:29:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KOrqibqGe9vBSDwXa2nTbnOAEGBDQ3W4U53frqaMLUWS5vU6B61BvC8Iyx9DJl6JMkVoQnU7p2x/whx8vNU4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:08:31.247686Z"},"content_sha256":"6e5a45d10c0c13a14df1c772b8d971b8f16fef1bbda8bca49f566d338ad7b1b0","schema_version":"1.0","event_id":"sha256:6e5a45d10c0c13a14df1c772b8d971b8f16fef1bbda8bca49f566d338ad7b1b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:REZHTCQRCZV3HKO2Z3HS65PBM3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Anish Athalye, Curtis G. Northcutt, Jonas Mueller","submitted_at":"2021-03-26T21:54:36Z","abstract_excerpt":"We identify label errors in the test sets of 10 of the most commonly-used computer vision, natural language, and audio datasets, and subsequently study the potential for these label errors to affect benchmark results. Errors in test sets are numerous and widespread: we estimate an average of at least 3.3% errors across the 10 datasets, where for example label errors comprise at least 6% of the ImageNet validation set. Putative label errors are identified using confident learning algorithms and then human-validated via crowdsourcing (51% of the algorithmically-flagged candidates are indeed erro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14749","kind":"arxiv","version":4},"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/2103.14749/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":"2026-07-05T03:29:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4h81d4TuCb5xnvczW7ctVmRP1Oi6s+rUq0aD0PHdU04nmnBkKMRTEbWzw1FVsefgqlPSYx5f7xIsExrTcENrAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:08:31.248216Z"},"content_sha256":"64503ecb600273a9037ac9f2dab711006cea337d0995b81d9f83d9dbd5e58f18","schema_version":"1.0","event_id":"sha256:64503ecb600273a9037ac9f2dab711006cea337d0995b81d9f83d9dbd5e58f18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/REZHTCQRCZV3HKO2Z3HS65PBM3/bundle.json","state_url":"https://pith.science/pith/REZHTCQRCZV3HKO2Z3HS65PBM3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/REZHTCQRCZV3HKO2Z3HS65PBM3/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":"2026-08-01T05:08:31Z","links":{"resolver":"https://pith.science/pith/REZHTCQRCZV3HKO2Z3HS65PBM3","bundle":"https://pith.science/pith/REZHTCQRCZV3HKO2Z3HS65PBM3/bundle.json","state":"https://pith.science/pith/REZHTCQRCZV3HKO2Z3HS65PBM3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/REZHTCQRCZV3HKO2Z3HS65PBM3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:REZHTCQRCZV3HKO2Z3HS65PBM3","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":"1cf5eb8f9d4a07e1f5044d84d9a113ae71e374b45bc1bbd4e2c06095d46b9646","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-03-26T21:54:36Z","title_canon_sha256":"a82fc7eaba50cfd80027c2ffd6b1791163bfa9ed5fc72d35062d926924beb8e1"},"schema_version":"1.0","source":{"id":"2103.14749","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.14749","created_at":"2026-07-05T03:29:48Z"},{"alias_kind":"arxiv_version","alias_value":"2103.14749v4","created_at":"2026-07-05T03:29:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14749","created_at":"2026-07-05T03:29:48Z"},{"alias_kind":"pith_short_12","alias_value":"REZHTCQRCZV3","created_at":"2026-07-05T03:29:48Z"},{"alias_kind":"pith_short_16","alias_value":"REZHTCQRCZV3HKO2","created_at":"2026-07-05T03:29:48Z"},{"alias_kind":"pith_short_8","alias_value":"REZHTCQR","created_at":"2026-07-05T03:29:48Z"}],"graph_snapshots":[{"event_id":"sha256:64503ecb600273a9037ac9f2dab711006cea337d0995b81d9f83d9dbd5e58f18","target":"graph","created_at":"2026-07-05T03:29:48Z","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/2103.14749/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We identify label errors in the test sets of 10 of the most commonly-used computer vision, natural language, and audio datasets, and subsequently study the potential for these label errors to affect benchmark results. Errors in test sets are numerous and widespread: we estimate an average of at least 3.3% errors across the 10 datasets, where for example label errors comprise at least 6% of the ImageNet validation set. Putative label errors are identified using confident learning algorithms and then human-validated via crowdsourcing (51% of the algorithmically-flagged candidates are indeed erro","authors_text":"Anish Athalye, Curtis G. Northcutt, Jonas Mueller","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-03-26T21:54:36Z","title":"Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14749","kind":"arxiv","version":4},"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":"sha256:6e5a45d10c0c13a14df1c772b8d971b8f16fef1bbda8bca49f566d338ad7b1b0","target":"record","created_at":"2026-07-05T03:29:48Z","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":"1cf5eb8f9d4a07e1f5044d84d9a113ae71e374b45bc1bbd4e2c06095d46b9646","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-03-26T21:54:36Z","title_canon_sha256":"a82fc7eaba50cfd80027c2ffd6b1791163bfa9ed5fc72d35062d926924beb8e1"},"schema_version":"1.0","source":{"id":"2103.14749","kind":"arxiv","version":4}},"canonical_sha256":"8932798a11166bb3a9dacecf2f75e166e006bffb064d2179d0331e3e1027c093","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8932798a11166bb3a9dacecf2f75e166e006bffb064d2179d0331e3e1027c093","first_computed_at":"2026-07-05T03:29:48.043233Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:29:48.043233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8nXyspMMxYHzU7gDKz+XaR2As7bWSQ0XjEUi1r51zJvQOXcrAHMD0qxN/rDLiYZH03+vqLGez1498wCDW7/gDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:29:48.043663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.14749","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e5a45d10c0c13a14df1c772b8d971b8f16fef1bbda8bca49f566d338ad7b1b0","sha256:64503ecb600273a9037ac9f2dab711006cea337d0995b81d9f83d9dbd5e58f18"],"state_sha256":"3092462693fff3efb2100c4849074c8b6198c5c98d3ec1ead49521ee9d12f7b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iBHD5aySnIZUiIk2wy5u48Xi1rNNDEWEnxvpfOfZAU4IRPQ2sBUvRPjbWhr6k5w8blSHjtTfMQUt8HjN0pKDAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T05:08:31.253344Z","bundle_sha256":"1e8d0c9b791a9f88e6cba47a55470e41f4a167aaa9a5846a9c20a71aa93e17e9"}}