{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PB2DAXN5A5DR2TFT5WX4U2GL3J","short_pith_number":"pith:PB2DAXN5","schema_version":"1.0","canonical_sha256":"7874305dbd07471d4cb3edafca68cbda77b635935e5dbae9f2a606d5e8e6fced","source":{"kind":"arxiv","id":"1804.09278","version":1},"attestation_state":"computed","paper":{"title":"Opening the black box of neural nets: case studies in stop/top discrimination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"hep-ph","authors_text":"Matthew Reece, Thomas Roxlo","submitted_at":"2018-04-24T22:08:54Z","abstract_excerpt":"We introduce techniques for exploring the functionality of a neural network and extracting simple, human-readable approximations to its performance. By performing gradient ascent on the input space of the network, we are able to produce large populations of artificial events which strongly excite a given classifier. By studying the populations of these events, we then directly produce what are essentially contour maps of the network's classification function. Combined with a suite of tools for identifying the input dimensions deemed most important by the network, we can utilize these maps to e"},"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":"1804.09278","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"hep-ph","submitted_at":"2018-04-24T22:08:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e0f60428230d5d562459a4bd4d76629b49f4b816ab7bf11897de3824a4b65482","abstract_canon_sha256":"990f97b868fb328da7ec3548377f00f1b00993966a39ba138cb8ffd329abe405"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:32.305003Z","signature_b64":"/odccLFSbliHqG/m6VwukuVDnvtklp7kp6s2nXKtEFtzIHSa8k3juJ+45EHqn3cngwoWxeAJNUyCTuDjVUHjBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7874305dbd07471d4cb3edafca68cbda77b635935e5dbae9f2a606d5e8e6fced","last_reissued_at":"2026-05-18T00:17:32.304191Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:32.304191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Opening the black box of neural nets: case studies in stop/top discrimination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"hep-ph","authors_text":"Matthew Reece, Thomas Roxlo","submitted_at":"2018-04-24T22:08:54Z","abstract_excerpt":"We introduce techniques for exploring the functionality of a neural network and extracting simple, human-readable approximations to its performance. By performing gradient ascent on the input space of the network, we are able to produce large populations of artificial events which strongly excite a given classifier. By studying the populations of these events, we then directly produce what are essentially contour maps of the network's classification function. Combined with a suite of tools for identifying the input dimensions deemed most important by the network, we can utilize these maps to e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.09278","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":""},"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":"1804.09278","created_at":"2026-05-18T00:17:32.304347+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.09278v1","created_at":"2026-05-18T00:17:32.304347+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.09278","created_at":"2026-05-18T00:17:32.304347+00:00"},{"alias_kind":"pith_short_12","alias_value":"PB2DAXN5A5DR","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"PB2DAXN5A5DR2TFT","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"PB2DAXN5","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07643","citing_title":"A Step Toward Interpretability: Smearing the Likelihood","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PB2DAXN5A5DR2TFT5WX4U2GL3J","json":"https://pith.science/pith/PB2DAXN5A5DR2TFT5WX4U2GL3J.json","graph_json":"https://pith.science/api/pith-number/PB2DAXN5A5DR2TFT5WX4U2GL3J/graph.json","events_json":"https://pith.science/api/pith-number/PB2DAXN5A5DR2TFT5WX4U2GL3J/events.json","paper":"https://pith.science/paper/PB2DAXN5"},"agent_actions":{"view_html":"https://pith.science/pith/PB2DAXN5A5DR2TFT5WX4U2GL3J","download_json":"https://pith.science/pith/PB2DAXN5A5DR2TFT5WX4U2GL3J.json","view_paper":"https://pith.science/paper/PB2DAXN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.09278&json=true","fetch_graph":"https://pith.science/api/pith-number/PB2DAXN5A5DR2TFT5WX4U2GL3J/graph.json","fetch_events":"https://pith.science/api/pith-number/PB2DAXN5A5DR2TFT5WX4U2GL3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PB2DAXN5A5DR2TFT5WX4U2GL3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PB2DAXN5A5DR2TFT5WX4U2GL3J/action/storage_attestation","attest_author":"https://pith.science/pith/PB2DAXN5A5DR2TFT5WX4U2GL3J/action/author_attestation","sign_citation":"https://pith.science/pith/PB2DAXN5A5DR2TFT5WX4U2GL3J/action/citation_signature","submit_replication":"https://pith.science/pith/PB2DAXN5A5DR2TFT5WX4U2GL3J/action/replication_record"}},"created_at":"2026-05-18T00:17:32.304347+00:00","updated_at":"2026-05-18T00:17:32.304347+00:00"}