{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GSC6JXH3YUECGSQIK2FHCKR7HO","short_pith_number":"pith:GSC6JXH3","schema_version":"1.0","canonical_sha256":"3485e4dcfbc508234a08568a712a3f3b81bf31ba887fc43eadf1775d08b1462b","source":{"kind":"arxiv","id":"2104.08952","version":2},"attestation_state":"computed","paper":{"title":"Failing Conceptually: Concept-Based Explanations of Dataset Shift","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Botty Dimanov, Dmitry Kazhdan, Maleakhi A. Wijaya, Mateja Jamnik","submitted_at":"2021-04-18T20:17:29Z","abstract_excerpt":"Despite their remarkable performance on a wide range of visual tasks, machine learning technologies often succumb to data distribution shifts. Consequently, a range of recent work explores techniques for detecting these shifts. Unfortunately, current techniques offer no explanations about what triggers the detection of shifts, thus limiting their utility to provide actionable insights. In this work, we present Concept Bottleneck Shift Detection (CBSD): a novel explainable shift detection method. CBSD provides explanations by identifying and ranking the degree to which high-level human-understa"},"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":"2104.08952","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-18T20:17:29Z","cross_cats_sorted":[],"title_canon_sha256":"ab660343ce2232123f8dae06cea28a7ebaf4d5f31a4543808f5a88b322b12322","abstract_canon_sha256":"cc4af439ac1b6376dcf19f1699b7ad0d77a9554fe27989537c5b3241061dd6be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:49.948694Z","signature_b64":"EUR0U6R42IW5VZpZfK4D3eHJvDaPmS5Iad6QT7HRRkEb6tSTNz0KQVexdLpaavjkHQ5jUaK5zRGQ8b4cGx7UBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3485e4dcfbc508234a08568a712a3f3b81bf31ba887fc43eadf1775d08b1462b","last_reissued_at":"2026-07-05T02:36:49.948171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:49.948171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Failing Conceptually: Concept-Based Explanations of Dataset Shift","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Botty Dimanov, Dmitry Kazhdan, Maleakhi A. Wijaya, Mateja Jamnik","submitted_at":"2021-04-18T20:17:29Z","abstract_excerpt":"Despite their remarkable performance on a wide range of visual tasks, machine learning technologies often succumb to data distribution shifts. Consequently, a range of recent work explores techniques for detecting these shifts. Unfortunately, current techniques offer no explanations about what triggers the detection of shifts, thus limiting their utility to provide actionable insights. In this work, we present Concept Bottleneck Shift Detection (CBSD): a novel explainable shift detection method. CBSD provides explanations by identifying and ranking the degree to which high-level human-understa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08952","kind":"arxiv","version":2},"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/2104.08952/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":"2104.08952","created_at":"2026-07-05T02:36:49.948251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.08952v2","created_at":"2026-07-05T02:36:49.948251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08952","created_at":"2026-07-05T02:36:49.948251+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSC6JXH3YUEC","created_at":"2026-07-05T02:36:49.948251+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSC6JXH3YUECGSQI","created_at":"2026-07-05T02:36:49.948251+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSC6JXH3","created_at":"2026-07-05T02:36:49.948251+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.17921","citing_title":"Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts","ref_index":2011,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GSC6JXH3YUECGSQIK2FHCKR7HO","json":"https://pith.science/pith/GSC6JXH3YUECGSQIK2FHCKR7HO.json","graph_json":"https://pith.science/api/pith-number/GSC6JXH3YUECGSQIK2FHCKR7HO/graph.json","events_json":"https://pith.science/api/pith-number/GSC6JXH3YUECGSQIK2FHCKR7HO/events.json","paper":"https://pith.science/paper/GSC6JXH3"},"agent_actions":{"view_html":"https://pith.science/pith/GSC6JXH3YUECGSQIK2FHCKR7HO","download_json":"https://pith.science/pith/GSC6JXH3YUECGSQIK2FHCKR7HO.json","view_paper":"https://pith.science/paper/GSC6JXH3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.08952&json=true","fetch_graph":"https://pith.science/api/pith-number/GSC6JXH3YUECGSQIK2FHCKR7HO/graph.json","fetch_events":"https://pith.science/api/pith-number/GSC6JXH3YUECGSQIK2FHCKR7HO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSC6JXH3YUECGSQIK2FHCKR7HO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSC6JXH3YUECGSQIK2FHCKR7HO/action/storage_attestation","attest_author":"https://pith.science/pith/GSC6JXH3YUECGSQIK2FHCKR7HO/action/author_attestation","sign_citation":"https://pith.science/pith/GSC6JXH3YUECGSQIK2FHCKR7HO/action/citation_signature","submit_replication":"https://pith.science/pith/GSC6JXH3YUECGSQIK2FHCKR7HO/action/replication_record"}},"created_at":"2026-07-05T02:36:49.948251+00:00","updated_at":"2026-07-05T02:36:49.948251+00:00"}