{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MHEHRPZTQOKX63NPWJ7KZFNOYI","short_pith_number":"pith:MHEHRPZT","schema_version":"1.0","canonical_sha256":"61c878bf3383957f6dafb27eac95aec2177cf010c47c08ef512112dbd90de2d0","source":{"kind":"arxiv","id":"1810.11953","version":4},"attestation_state":"computed","paper":{"title":"Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Stephan G\\\"unnemann, Stephan Rabanser, Zachary C. Lipton","submitted_at":"2018-10-29T04:50:18Z","abstract_excerpt":"We might hope that when faced with unexpected inputs, well-designed software systems would fire off warnings. Machine learning (ML) systems, however, which depend strongly on properties of their inputs (e.g. the i.i.d. assumption), tend to fail silently. This paper explores the problem of building ML systems that fail loudly, investigating methods for detecting dataset shift, identifying exemplars that most typify the shift, and quantifying shift malignancy. We focus on several datasets and various perturbations to both covariates and label distributions with varying magnitudes and fractions o"},"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":"1810.11953","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-29T04:50:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bb961f857103634a446fb78586bdb5461ea6f7c59bbd2b396ad4e7a628bf6890","abstract_canon_sha256":"b73b2d000315b43926b2d2cafecd48e49fb5d5df453f78aa472aa5c08fb61e18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:01.621921Z","signature_b64":"5X0ZVPJGAVXTshXEHeF85gXzF68N843MbOdDi8WZ8NQeQEnzd/QN7hGXlNx41Svw7eSo7UYt6LZiOjN9hMTbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61c878bf3383957f6dafb27eac95aec2177cf010c47c08ef512112dbd90de2d0","last_reissued_at":"2026-07-05T00:15:01.621374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:01.621374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Stephan G\\\"unnemann, Stephan Rabanser, Zachary C. Lipton","submitted_at":"2018-10-29T04:50:18Z","abstract_excerpt":"We might hope that when faced with unexpected inputs, well-designed software systems would fire off warnings. Machine learning (ML) systems, however, which depend strongly on properties of their inputs (e.g. the i.i.d. assumption), tend to fail silently. This paper explores the problem of building ML systems that fail loudly, investigating methods for detecting dataset shift, identifying exemplars that most typify the shift, and quantifying shift malignancy. We focus on several datasets and various perturbations to both covariates and label distributions with varying magnitudes and fractions o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11953","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/1810.11953/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":"1810.11953","created_at":"2026-07-05T00:15:01.621441+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.11953v4","created_at":"2026-07-05T00:15:01.621441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11953","created_at":"2026-07-05T00:15:01.621441+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHEHRPZTQOKX","created_at":"2026-07-05T00:15:01.621441+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHEHRPZTQOKX63NP","created_at":"2026-07-05T00:15:01.621441+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHEHRPZT","created_at":"2026-07-05T00:15:01.621441+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08192","citing_title":"Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15740","citing_title":"Evidence Sufficiency Under Delayed Ground Truth: Proxy Monitoring for Risk Decision Systems","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MHEHRPZTQOKX63NPWJ7KZFNOYI","json":"https://pith.science/pith/MHEHRPZTQOKX63NPWJ7KZFNOYI.json","graph_json":"https://pith.science/api/pith-number/MHEHRPZTQOKX63NPWJ7KZFNOYI/graph.json","events_json":"https://pith.science/api/pith-number/MHEHRPZTQOKX63NPWJ7KZFNOYI/events.json","paper":"https://pith.science/paper/MHEHRPZT"},"agent_actions":{"view_html":"https://pith.science/pith/MHEHRPZTQOKX63NPWJ7KZFNOYI","download_json":"https://pith.science/pith/MHEHRPZTQOKX63NPWJ7KZFNOYI.json","view_paper":"https://pith.science/paper/MHEHRPZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.11953&json=true","fetch_graph":"https://pith.science/api/pith-number/MHEHRPZTQOKX63NPWJ7KZFNOYI/graph.json","fetch_events":"https://pith.science/api/pith-number/MHEHRPZTQOKX63NPWJ7KZFNOYI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHEHRPZTQOKX63NPWJ7KZFNOYI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHEHRPZTQOKX63NPWJ7KZFNOYI/action/storage_attestation","attest_author":"https://pith.science/pith/MHEHRPZTQOKX63NPWJ7KZFNOYI/action/author_attestation","sign_citation":"https://pith.science/pith/MHEHRPZTQOKX63NPWJ7KZFNOYI/action/citation_signature","submit_replication":"https://pith.science/pith/MHEHRPZTQOKX63NPWJ7KZFNOYI/action/replication_record"}},"created_at":"2026-07-05T00:15:01.621441+00:00","updated_at":"2026-07-05T00:15:01.621441+00:00"}