{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XASQI6KUAFV7SWRJ5T62BZZWTN","short_pith_number":"pith:XASQI6KU","schema_version":"1.0","canonical_sha256":"b825047954016bf95a29ecfda0e7369b74023170d80031d7519e5d9464b5cae7","source":{"kind":"arxiv","id":"2506.01230","version":1},"attestation_state":"computed","paper":{"title":"Stress-Testing ML Pipelines with Adversarial Data Corruption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Babak Salimi, Boris Glavic, Felipe Lorenzi, Geyang Xu, Jiongli Zhu","submitted_at":"2025-06-02T00:41:24Z","abstract_excerpt":"Structured data-quality issues, such as missing values correlated with demographics, culturally biased labels, or systemic selection biases, routinely degrade the reliability of machine-learning pipelines. Regulators now increasingly demand evidence that high-stakes systems can withstand these realistic, interdependent errors, yet current robustness evaluations typically use random or overly simplistic corruptions, leaving worst-case scenarios unexplored. We introduce SAVAGE, a causally inspired framework that (i) formally models realistic data-quality issues through dependency graphs and flex"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.01230","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T00:41:24Z","cross_cats_sorted":[],"title_canon_sha256":"7eada99f4c5bf0315fd89539fe91b43f4506761c1cf6d9bf46cdebf7ee587071","abstract_canon_sha256":"e299d21b6833b583d219b4743e3c7d982f703d235c98f7995ecdb9a854ec46cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:10.165203Z","signature_b64":"Sl7DcF233u48kJaqS76Z9iLJY9xBPkY3sxGUlxd+eGxPGWT1zknhsX0nQJdYGvaSrhH+b6VB30XeYAOkbmqADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b825047954016bf95a29ecfda0e7369b74023170d80031d7519e5d9464b5cae7","last_reissued_at":"2026-07-05T11:14:10.164739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:10.164739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stress-Testing ML Pipelines with Adversarial Data Corruption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Babak Salimi, Boris Glavic, Felipe Lorenzi, Geyang Xu, Jiongli Zhu","submitted_at":"2025-06-02T00:41:24Z","abstract_excerpt":"Structured data-quality issues, such as missing values correlated with demographics, culturally biased labels, or systemic selection biases, routinely degrade the reliability of machine-learning pipelines. Regulators now increasingly demand evidence that high-stakes systems can withstand these realistic, interdependent errors, yet current robustness evaluations typically use random or overly simplistic corruptions, leaving worst-case scenarios unexplored. We introduce SAVAGE, a causally inspired framework that (i) formally models realistic data-quality issues through dependency graphs and flex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01230","kind":"arxiv","version":1},"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/2506.01230/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.01230","created_at":"2026-07-05T11:14:10.164794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01230v1","created_at":"2026-07-05T11:14:10.164794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01230","created_at":"2026-07-05T11:14:10.164794+00:00"},{"alias_kind":"pith_short_12","alias_value":"XASQI6KUAFV7","created_at":"2026-07-05T11:14:10.164794+00:00"},{"alias_kind":"pith_short_16","alias_value":"XASQI6KUAFV7SWRJ","created_at":"2026-07-05T11:14:10.164794+00:00"},{"alias_kind":"pith_short_8","alias_value":"XASQI6KU","created_at":"2026-07-05T11:14:10.164794+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XASQI6KUAFV7SWRJ5T62BZZWTN","json":"https://pith.science/pith/XASQI6KUAFV7SWRJ5T62BZZWTN.json","graph_json":"https://pith.science/api/pith-number/XASQI6KUAFV7SWRJ5T62BZZWTN/graph.json","events_json":"https://pith.science/api/pith-number/XASQI6KUAFV7SWRJ5T62BZZWTN/events.json","paper":"https://pith.science/paper/XASQI6KU"},"agent_actions":{"view_html":"https://pith.science/pith/XASQI6KUAFV7SWRJ5T62BZZWTN","download_json":"https://pith.science/pith/XASQI6KUAFV7SWRJ5T62BZZWTN.json","view_paper":"https://pith.science/paper/XASQI6KU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01230&json=true","fetch_graph":"https://pith.science/api/pith-number/XASQI6KUAFV7SWRJ5T62BZZWTN/graph.json","fetch_events":"https://pith.science/api/pith-number/XASQI6KUAFV7SWRJ5T62BZZWTN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XASQI6KUAFV7SWRJ5T62BZZWTN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XASQI6KUAFV7SWRJ5T62BZZWTN/action/storage_attestation","attest_author":"https://pith.science/pith/XASQI6KUAFV7SWRJ5T62BZZWTN/action/author_attestation","sign_citation":"https://pith.science/pith/XASQI6KUAFV7SWRJ5T62BZZWTN/action/citation_signature","submit_replication":"https://pith.science/pith/XASQI6KUAFV7SWRJ5T62BZZWTN/action/replication_record"}},"created_at":"2026-07-05T11:14:10.164794+00:00","updated_at":"2026-07-05T11:14:10.164794+00:00"}