{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:27F4YXF3ZZS4FECHAII7VH2WNB","short_pith_number":"pith:27F4YXF3","schema_version":"1.0","canonical_sha256":"d7cbcc5cbbce65c290470211fa9f56684bf2b2f5c516cbd933605a414c53cd6d","source":{"kind":"arxiv","id":"1812.07150","version":2},"attestation_state":"computed","paper":{"title":"Interactive Naming for Explaining Deep Neural Networks: A Formative Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alan Fern, Fuxin Li, Mandana Hamidi-Haines, Prasad Tadepalli, Zhongang Qi","submitted_at":"2018-12-18T03:31:09Z","abstract_excerpt":"We consider the problem of explaining the decisions of deep neural networks for image recognition in terms of human-recognizable visual concepts. In particular, given a test set of images, we aim to explain each classification in terms of a small number of image regions, or activation maps, which have been associated with semantic concepts by a human annotator. This allows for generating summary views of the typical reasons for classifications, which can help build trust in a classifier and/or identify example types for which the classifier may not be trusted. For this purpose, we developed a "},"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":"1812.07150","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-18T03:31:09Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"9fd99c4d69a49b96158c3b6bdec30ec4a4a6c7ac65253fdfa0969d132e25b9ba","abstract_canon_sha256":"a5c028a13d5b9aed2892bfd76d5c90bd0f0c1b64bc7660a41bee0c102eed32c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:52.029383Z","signature_b64":"C4dZDUb3r28KJ+QiCiDYRTuP8BC4RaIrZ6snPR8I1ynut7w0MmjCTubAVmtW0E96Q8IhrBRL37qMKg1tgYYnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7cbcc5cbbce65c290470211fa9f56684bf2b2f5c516cbd933605a414c53cd6d","last_reissued_at":"2026-05-17T23:57:52.028868Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:52.028868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interactive Naming for Explaining Deep Neural Networks: A Formative Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alan Fern, Fuxin Li, Mandana Hamidi-Haines, Prasad Tadepalli, Zhongang Qi","submitted_at":"2018-12-18T03:31:09Z","abstract_excerpt":"We consider the problem of explaining the decisions of deep neural networks for image recognition in terms of human-recognizable visual concepts. In particular, given a test set of images, we aim to explain each classification in terms of a small number of image regions, or activation maps, which have been associated with semantic concepts by a human annotator. This allows for generating summary views of the typical reasons for classifications, which can help build trust in a classifier and/or identify example types for which the classifier may not be trusted. For this purpose, we developed a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07150","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":"1812.07150","created_at":"2026-05-17T23:57:52.028952+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.07150v2","created_at":"2026-05-17T23:57:52.028952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07150","created_at":"2026-05-17T23:57:52.028952+00:00"},{"alias_kind":"pith_short_12","alias_value":"27F4YXF3ZZS4","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"27F4YXF3ZZS4FECH","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"27F4YXF3","created_at":"2026-05-18T12:31:59.375834+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/27F4YXF3ZZS4FECHAII7VH2WNB","json":"https://pith.science/pith/27F4YXF3ZZS4FECHAII7VH2WNB.json","graph_json":"https://pith.science/api/pith-number/27F4YXF3ZZS4FECHAII7VH2WNB/graph.json","events_json":"https://pith.science/api/pith-number/27F4YXF3ZZS4FECHAII7VH2WNB/events.json","paper":"https://pith.science/paper/27F4YXF3"},"agent_actions":{"view_html":"https://pith.science/pith/27F4YXF3ZZS4FECHAII7VH2WNB","download_json":"https://pith.science/pith/27F4YXF3ZZS4FECHAII7VH2WNB.json","view_paper":"https://pith.science/paper/27F4YXF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.07150&json=true","fetch_graph":"https://pith.science/api/pith-number/27F4YXF3ZZS4FECHAII7VH2WNB/graph.json","fetch_events":"https://pith.science/api/pith-number/27F4YXF3ZZS4FECHAII7VH2WNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/27F4YXF3ZZS4FECHAII7VH2WNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/27F4YXF3ZZS4FECHAII7VH2WNB/action/storage_attestation","attest_author":"https://pith.science/pith/27F4YXF3ZZS4FECHAII7VH2WNB/action/author_attestation","sign_citation":"https://pith.science/pith/27F4YXF3ZZS4FECHAII7VH2WNB/action/citation_signature","submit_replication":"https://pith.science/pith/27F4YXF3ZZS4FECHAII7VH2WNB/action/replication_record"}},"created_at":"2026-05-17T23:57:52.028952+00:00","updated_at":"2026-05-17T23:57:52.028952+00:00"}