{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TKCG6JLLHLDJFQM47WVXDWR76U","short_pith_number":"pith:TKCG6JLL","schema_version":"1.0","canonical_sha256":"9a846f256b3ac692c19cfdab71da3ff515129d7ef76948862a3294267a163a91","source":{"kind":"arxiv","id":"1904.07451","version":2},"attestation_state":"computed","paper":{"title":"Counterfactual Visual Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Devi Parikh, Dhruv Batra, Jan Ernst, Stefan Lee, Yash Goyal, Ziyan Wu","submitted_at":"2019-04-16T04:16:11Z","abstract_excerpt":"In this work, we develop a technique to produce counterfactual visual explanations. Given a 'query' image $I$ for which a vision system predicts class $c$, a counterfactual visual explanation identifies how $I$ could change such that the system would output a different specified class $c'$. To do this, we select a 'distractor' image $I'$ that the system predicts as class $c'$ and identify spatial regions in $I$ and $I'$ such that replacing the identified region in $I$ with the identified region in $I'$ would push the system towards classifying $I$ as $c'$. We apply our approach to multiple ima"},"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":"1904.07451","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-16T04:16:11Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"bd04e0ff3593008ed953b9ccfda54f04e5033fbdbc39e7bb97b3b1e6d68c08a9","abstract_canon_sha256":"40df9f1170969628fec77a20bea053a77a3c9e5543d0991f14aa28285ac63d41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:34.589865Z","signature_b64":"cidXVoanuWXds98b0ppjlAPFzjaTPJzFD9qNXnXRJSZW1CWyRUy8oVCcmYWpzxFdTEQ0dzf1Nx86uRe4Z64fAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a846f256b3ac692c19cfdab71da3ff515129d7ef76948862a3294267a163a91","last_reissued_at":"2026-05-17T23:43:34.589474Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:34.589474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Counterfactual Visual Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Devi Parikh, Dhruv Batra, Jan Ernst, Stefan Lee, Yash Goyal, Ziyan Wu","submitted_at":"2019-04-16T04:16:11Z","abstract_excerpt":"In this work, we develop a technique to produce counterfactual visual explanations. Given a 'query' image $I$ for which a vision system predicts class $c$, a counterfactual visual explanation identifies how $I$ could change such that the system would output a different specified class $c'$. To do this, we select a 'distractor' image $I'$ that the system predicts as class $c'$ and identify spatial regions in $I$ and $I'$ such that replacing the identified region in $I$ with the identified region in $I'$ would push the system towards classifying $I$ as $c'$. We apply our approach to multiple ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.07451","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":""},"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":"1904.07451","created_at":"2026-05-17T23:43:34.589536+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.07451v2","created_at":"2026-05-17T23:43:34.589536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.07451","created_at":"2026-05-17T23:43:34.589536+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKCG6JLLHLDJ","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKCG6JLLHLDJFQM4","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKCG6JLL","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.03077","citing_title":"Generative Counterfactual Introspection for Explainable Deep Learning","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TKCG6JLLHLDJFQM47WVXDWR76U","json":"https://pith.science/pith/TKCG6JLLHLDJFQM47WVXDWR76U.json","graph_json":"https://pith.science/api/pith-number/TKCG6JLLHLDJFQM47WVXDWR76U/graph.json","events_json":"https://pith.science/api/pith-number/TKCG6JLLHLDJFQM47WVXDWR76U/events.json","paper":"https://pith.science/paper/TKCG6JLL"},"agent_actions":{"view_html":"https://pith.science/pith/TKCG6JLLHLDJFQM47WVXDWR76U","download_json":"https://pith.science/pith/TKCG6JLLHLDJFQM47WVXDWR76U.json","view_paper":"https://pith.science/paper/TKCG6JLL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.07451&json=true","fetch_graph":"https://pith.science/api/pith-number/TKCG6JLLHLDJFQM47WVXDWR76U/graph.json","fetch_events":"https://pith.science/api/pith-number/TKCG6JLLHLDJFQM47WVXDWR76U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKCG6JLLHLDJFQM47WVXDWR76U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKCG6JLLHLDJFQM47WVXDWR76U/action/storage_attestation","attest_author":"https://pith.science/pith/TKCG6JLLHLDJFQM47WVXDWR76U/action/author_attestation","sign_citation":"https://pith.science/pith/TKCG6JLLHLDJFQM47WVXDWR76U/action/citation_signature","submit_replication":"https://pith.science/pith/TKCG6JLLHLDJFQM47WVXDWR76U/action/replication_record"}},"created_at":"2026-05-17T23:43:34.589536+00:00","updated_at":"2026-05-17T23:43:34.589536+00:00"}