{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2010:ADGVP2NZEJ6RHQW2WFENVC32NX","short_pith_number":"pith:ADGVP2NZ","schema_version":"1.0","canonical_sha256":"00cd57e9b9227d13c2dab148da8b7a6ddb0ee0076ece0845dca27ff9d47b0c1d","source":{"kind":"arxiv","id":"1009.4570","version":1},"attestation_state":"computed","paper":{"title":"Extraction of Symbolic Rules from Artificial Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Md. Monirul Islam, S. M. Kamruzzaman","submitted_at":"2010-09-23T10:37:54Z","abstract_excerpt":"Although backpropagation ANNs generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions cannot be explained as those of decision trees. In many applications, it is desirable to extract knowledge from trained ANNs for the users to gain a better understanding of how the networks solve the problems. A new rule extraction algorithm, called rule extraction from artificial neural networks (REANN) is proposed and implemented to extract symbolic rules from ANNs. A standard three-layer feedforward ANN is the basi"},"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":"1009.4570","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2010-09-23T10:37:54Z","cross_cats_sorted":[],"title_canon_sha256":"052b935236c658ae61ffc054edbd3a99155c77593bbf28a6130de5667b4f99f3","abstract_canon_sha256":"354cc86161cbea85108ef9384b506f06dc58dd4e9eb17c185e3014479adeff95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:40:19.769774Z","signature_b64":"wOXsX08qZto5atM7b+7oLof+cFTo6NBimzFrXRlEkthObrNXMvO0eSsrRC3WZgaBOMZzPUOLI+DZEuxW6NTeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00cd57e9b9227d13c2dab148da8b7a6ddb0ee0076ece0845dca27ff9d47b0c1d","last_reissued_at":"2026-05-18T04:40:19.769204Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:40:19.769204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extraction of Symbolic Rules from Artificial Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Md. Monirul Islam, S. M. Kamruzzaman","submitted_at":"2010-09-23T10:37:54Z","abstract_excerpt":"Although backpropagation ANNs generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions cannot be explained as those of decision trees. In many applications, it is desirable to extract knowledge from trained ANNs for the users to gain a better understanding of how the networks solve the problems. A new rule extraction algorithm, called rule extraction from artificial neural networks (REANN) is proposed and implemented to extract symbolic rules from ANNs. A standard three-layer feedforward ANN is the basi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1009.4570","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":"1009.4570","created_at":"2026-05-18T04:40:19.769299+00:00"},{"alias_kind":"arxiv_version","alias_value":"1009.4570v1","created_at":"2026-05-18T04:40:19.769299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1009.4570","created_at":"2026-05-18T04:40:19.769299+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADGVP2NZEJ6R","created_at":"2026-05-18T12:26:05.355336+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADGVP2NZEJ6RHQW2","created_at":"2026-05-18T12:26:05.355336+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADGVP2NZ","created_at":"2026-05-18T12:26:05.355336+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/ADGVP2NZEJ6RHQW2WFENVC32NX","json":"https://pith.science/pith/ADGVP2NZEJ6RHQW2WFENVC32NX.json","graph_json":"https://pith.science/api/pith-number/ADGVP2NZEJ6RHQW2WFENVC32NX/graph.json","events_json":"https://pith.science/api/pith-number/ADGVP2NZEJ6RHQW2WFENVC32NX/events.json","paper":"https://pith.science/paper/ADGVP2NZ"},"agent_actions":{"view_html":"https://pith.science/pith/ADGVP2NZEJ6RHQW2WFENVC32NX","download_json":"https://pith.science/pith/ADGVP2NZEJ6RHQW2WFENVC32NX.json","view_paper":"https://pith.science/paper/ADGVP2NZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1009.4570&json=true","fetch_graph":"https://pith.science/api/pith-number/ADGVP2NZEJ6RHQW2WFENVC32NX/graph.json","fetch_events":"https://pith.science/api/pith-number/ADGVP2NZEJ6RHQW2WFENVC32NX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADGVP2NZEJ6RHQW2WFENVC32NX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADGVP2NZEJ6RHQW2WFENVC32NX/action/storage_attestation","attest_author":"https://pith.science/pith/ADGVP2NZEJ6RHQW2WFENVC32NX/action/author_attestation","sign_citation":"https://pith.science/pith/ADGVP2NZEJ6RHQW2WFENVC32NX/action/citation_signature","submit_replication":"https://pith.science/pith/ADGVP2NZEJ6RHQW2WFENVC32NX/action/replication_record"}},"created_at":"2026-05-18T04:40:19.769299+00:00","updated_at":"2026-05-18T04:40:19.769299+00:00"}