{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WTB2GVARFLLVZFWFVU26SS6MDX","short_pith_number":"pith:WTB2GVAR","schema_version":"1.0","canonical_sha256":"b4c3a354112ad75c96c5ad35e94bcc1dc373f0b6a5ca8348592ebc8a2c6adab7","source":{"kind":"arxiv","id":"2111.15639","version":1},"attestation_state":"computed","paper":{"title":"DeDUCE: Generating Counterfactual Explanations Efficiently","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Benedikt H\\\"oltgen, Jan M. Brauner, Lisa Schut, Yarin Gal","submitted_at":"2021-11-29T17:47:21Z","abstract_excerpt":"When an image classifier outputs a wrong class label, it can be helpful to see what changes in the image would lead to a correct classification. This is the aim of algorithms generating counterfactual explanations. However, there is no easily scalable method to generate such counterfactuals. We develop a new algorithm providing counterfactual explanations for large image classifiers trained with spectral normalisation at low computational cost. We empirically compare this algorithm against baselines from the literature; our novel algorithm consistently finds counterfactuals that are much close"},"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":"2111.15639","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-29T17:47:21Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"b0a871c0293b40a49bb3116f61a48344b5b63fdffe1d77f7ca8bbfbe3a5c09c4","abstract_canon_sha256":"bbcf12d40d42c73f0a7a6f1beb9fdb32ee4baf84e206250b98f2dc2609cce380"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:28.578506Z","signature_b64":"T64Lmwo3IEtW8WXk00bu8L8POt4WwOSQ0sHzcaAS4/aPDKgm9NKzsjhUxMDvVU9nywbN9tdWQBIEtQxEwSNyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4c3a354112ad75c96c5ad35e94bcc1dc373f0b6a5ca8348592ebc8a2c6adab7","last_reissued_at":"2026-07-05T03:36:28.578102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:28.578102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeDUCE: Generating Counterfactual Explanations Efficiently","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Benedikt H\\\"oltgen, Jan M. Brauner, Lisa Schut, Yarin Gal","submitted_at":"2021-11-29T17:47:21Z","abstract_excerpt":"When an image classifier outputs a wrong class label, it can be helpful to see what changes in the image would lead to a correct classification. This is the aim of algorithms generating counterfactual explanations. However, there is no easily scalable method to generate such counterfactuals. We develop a new algorithm providing counterfactual explanations for large image classifiers trained with spectral normalisation at low computational cost. We empirically compare this algorithm against baselines from the literature; our novel algorithm consistently finds counterfactuals that are much close"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.15639","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/2111.15639/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":"2111.15639","created_at":"2026-07-05T03:36:28.578164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.15639v1","created_at":"2026-07-05T03:36:28.578164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.15639","created_at":"2026-07-05T03:36:28.578164+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTB2GVARFLLV","created_at":"2026-07-05T03:36:28.578164+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTB2GVARFLLVZFWF","created_at":"2026-07-05T03:36:28.578164+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTB2GVAR","created_at":"2026-07-05T03:36:28.578164+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/WTB2GVARFLLVZFWFVU26SS6MDX","json":"https://pith.science/pith/WTB2GVARFLLVZFWFVU26SS6MDX.json","graph_json":"https://pith.science/api/pith-number/WTB2GVARFLLVZFWFVU26SS6MDX/graph.json","events_json":"https://pith.science/api/pith-number/WTB2GVARFLLVZFWFVU26SS6MDX/events.json","paper":"https://pith.science/paper/WTB2GVAR"},"agent_actions":{"view_html":"https://pith.science/pith/WTB2GVARFLLVZFWFVU26SS6MDX","download_json":"https://pith.science/pith/WTB2GVARFLLVZFWFVU26SS6MDX.json","view_paper":"https://pith.science/paper/WTB2GVAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.15639&json=true","fetch_graph":"https://pith.science/api/pith-number/WTB2GVARFLLVZFWFVU26SS6MDX/graph.json","fetch_events":"https://pith.science/api/pith-number/WTB2GVARFLLVZFWFVU26SS6MDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTB2GVARFLLVZFWFVU26SS6MDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTB2GVARFLLVZFWFVU26SS6MDX/action/storage_attestation","attest_author":"https://pith.science/pith/WTB2GVARFLLVZFWFVU26SS6MDX/action/author_attestation","sign_citation":"https://pith.science/pith/WTB2GVARFLLVZFWFVU26SS6MDX/action/citation_signature","submit_replication":"https://pith.science/pith/WTB2GVARFLLVZFWFVU26SS6MDX/action/replication_record"}},"created_at":"2026-07-05T03:36:28.578164+00:00","updated_at":"2026-07-05T03:36:28.578164+00:00"}