{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6EW7YS4CN4EBZEJS67A5PDDSGM","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":"e92b157560a54e56ffb66e99b57ef2def23cfb528932db2c594bdb49a9cb4d77","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-22T17:39:16Z","title_canon_sha256":"24794a60fa8e5e638366c45bbb3f8d48e4adcd1b65802609d6a472fb37617610"},"schema_version":"1.0","source":{"id":"2005.11295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.11295","created_at":"2026-07-05T01:05:07Z"},{"alias_kind":"arxiv_version","alias_value":"2005.11295v1","created_at":"2026-07-05T01:05:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.11295","created_at":"2026-07-05T01:05:07Z"},{"alias_kind":"pith_short_12","alias_value":"6EW7YS4CN4EB","created_at":"2026-07-05T01:05:07Z"},{"alias_kind":"pith_short_16","alias_value":"6EW7YS4CN4EBZEJS","created_at":"2026-07-05T01:05:07Z"},{"alias_kind":"pith_short_8","alias_value":"6EW7YS4C","created_at":"2026-07-05T01:05:07Z"}],"graph_snapshots":[{"event_id":"sha256:8fc215f546f200f02f91ca74ca0e842b28c6c8198d172ad7d826b2170420f1a4","target":"graph","created_at":"2026-07-05T01:05:07Z","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/2005.11295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building rich machine learning datasets in a scalable manner often necessitates a crowd-sourced data collection pipeline. In this work, we use human studies to investigate the consequences of employing such a pipeline, focusing on the popular ImageNet dataset. We study how specific design choices in the ImageNet creation process impact the fidelity of the resulting dataset---including the introduction of biases that state-of-the-art models exploit. Our analysis pinpoints how a noisy data collection pipeline can lead to a systematic misalignment between the resulting benchmark and the real-worl","authors_text":"Aleksander Madry, Andrew Ilyas, Dimitris Tsipras, Logan Engstrom, Shibani Santurkar","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-22T17:39:16Z","title":"From ImageNet to Image Classification: Contextualizing Progress on Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.11295","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":"sha256:9b0195533279379043e8644c6367a9f90f460de3bb014257d07b255c70337bae","target":"record","created_at":"2026-07-05T01:05:07Z","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":"e92b157560a54e56ffb66e99b57ef2def23cfb528932db2c594bdb49a9cb4d77","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-22T17:39:16Z","title_canon_sha256":"24794a60fa8e5e638366c45bbb3f8d48e4adcd1b65802609d6a472fb37617610"},"schema_version":"1.0","source":{"id":"2005.11295","kind":"arxiv","version":1}},"canonical_sha256":"f12dfc4b826f081c9132f7c1d78c723333264be5627679067c0a3ed31b64a973","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f12dfc4b826f081c9132f7c1d78c723333264be5627679067c0a3ed31b64a973","first_computed_at":"2026-07-05T01:05:07.178698Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:05:07.178698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RNvmbxQzFmulwJqY+vZ160Jhe1LsdDhw8zycAoGoaBpqz2Roc9tDDlGkx9CypqchOiXC6AM8fQxRz7xIrwAJAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:05:07.179179Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.11295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b0195533279379043e8644c6367a9f90f460de3bb014257d07b255c70337bae","sha256:8fc215f546f200f02f91ca74ca0e842b28c6c8198d172ad7d826b2170420f1a4"],"state_sha256":"e3acfd37fce0a74dde23d0796a8735cd49a3a8ef52d0ce0c268f6eb716e7a9e6"}