{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ACWEZZMSA7AQDHAT2OGROVTF7H","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":"c1d838304af79ce8b6ad48f189e1d5e0baa559b2898a0cb5620b10142c7e7cb7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-16T22:00:15Z","title_canon_sha256":"e2b64364436f90d2b583a889720d5e43b7268e7fcf429969999ffb85ae5d01d8"},"schema_version":"1.0","source":{"id":"2109.08237","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.08237","created_at":"2026-07-05T03:40:46Z"},{"alias_kind":"arxiv_version","alias_value":"2109.08237v3","created_at":"2026-07-05T03:40:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08237","created_at":"2026-07-05T03:40:46Z"},{"alias_kind":"pith_short_12","alias_value":"ACWEZZMSA7AQ","created_at":"2026-07-05T03:40:46Z"},{"alias_kind":"pith_short_16","alias_value":"ACWEZZMSA7AQDHAT","created_at":"2026-07-05T03:40:46Z"},{"alias_kind":"pith_short_8","alias_value":"ACWEZZMS","created_at":"2026-07-05T03:40:46Z"}],"graph_snapshots":[{"event_id":"sha256:6ca8fa45cd53b52e0e65ad3bd74b9b6f48de20a9754f9bbc7bbdc293ef8dd739","target":"graph","created_at":"2026-07-05T03:40:46Z","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/2109.08237/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While open databases are an important resource in the Deep Learning (DL) era, they are sometimes used \"off-label\": data published for one task are used for training algorithms for a different one. This work aims to highlight that in some cases, this common practice may lead to biased, overly-optimistic results. We demonstrate this phenomenon for inverse problem solvers and show how their biased performance stems from hidden data preprocessing pipelines. We describe two preprocessing pipelines typical of open-access databases and study their effects on three well-established algorithms develope","authors_text":"Efrat Shimron, Jonathan I. Tamir, Ke Wang, Michael Lustig","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-16T22:00:15Z","title":"Subtle Data Crimes: Naively training machine learning algorithms could lead to overly-optimistic results"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08237","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":"sha256:6ee1563c53873c1f1069586df16126741c95f13a8ea46292c475cd0234d21dea","target":"record","created_at":"2026-07-05T03:40:46Z","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":"c1d838304af79ce8b6ad48f189e1d5e0baa559b2898a0cb5620b10142c7e7cb7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-16T22:00:15Z","title_canon_sha256":"e2b64364436f90d2b583a889720d5e43b7268e7fcf429969999ffb85ae5d01d8"},"schema_version":"1.0","source":{"id":"2109.08237","kind":"arxiv","version":3}},"canonical_sha256":"00ac4ce59207c1019c13d38d175665f9c848436cc61609a5afba8bfcb31769ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00ac4ce59207c1019c13d38d175665f9c848436cc61609a5afba8bfcb31769ee","first_computed_at":"2026-07-05T03:40:46.407697Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:40:46.407697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4HxWNqEB3QcQ3glCB29ePoyojHAgiOLmOo1DW5uMyJWYE6VMn8m0Jp9LDlvz4UBvvbim7YTrb0rxuM4hrs0uDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:40:46.408193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.08237","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ee1563c53873c1f1069586df16126741c95f13a8ea46292c475cd0234d21dea","sha256:6ca8fa45cd53b52e0e65ad3bd74b9b6f48de20a9754f9bbc7bbdc293ef8dd739"],"state_sha256":"a72ba50af32ee24c3522e5750d444e5d21812b2833adb4793ee0f3ae95beef27"}