{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IQLS7NNQ2RBVDOUYK5CBR776B4","short_pith_number":"pith:IQLS7NNQ","schema_version":"1.0","canonical_sha256":"44172fb5b0d44351ba98574418fffe0f04c472824857954e0333068b28b0dc42","source":{"kind":"arxiv","id":"1801.05420","version":2},"attestation_state":"computed","paper":{"title":"A Comparative Study of Rule Extraction for Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Alexander G. Ororbia II, C. Lee Giles, Kaixuan Zhang, Qinglong Wang, Xinyu Xing, Xue Liu","submitted_at":"2018-01-16T03:19:37Z","abstract_excerpt":"Understanding recurrent networks through rule extraction has a long history. This has taken on new interests due to the need for interpreting or verifying neural networks. One basic form for representing stateful rules is deterministic finite automata (DFA). Previous research shows that extracting DFAs from trained second-order recurrent networks is not only possible but also relatively stable. Recently, several new types of recurrent networks with more complicated architectures have been introduced. These handle challenging learning tasks usually involving sequential data. However, it remains"},"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":"1801.05420","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-16T03:19:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ee87510f7f8eca722db6500a9da86e3f3e27a082df7531af92fd591e9f06b8ac","abstract_canon_sha256":"08cff349402be6c64db215afaff30f3ab6ab4a810f8db800546c276e9345a0cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:39.795831Z","signature_b64":"1XzFFseOq4nPYFsd3Nl3wzT7gxDOXiQ1F+PweTuckHMN4SQkA3Kdo55pEBdySEwWMDn0JUgMQ0CyjQH3nTJqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44172fb5b0d44351ba98574418fffe0f04c472824857954e0333068b28b0dc42","last_reissued_at":"2026-05-18T00:00:39.795392Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:39.795392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparative Study of Rule Extraction for Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Alexander G. Ororbia II, C. Lee Giles, Kaixuan Zhang, Qinglong Wang, Xinyu Xing, Xue Liu","submitted_at":"2018-01-16T03:19:37Z","abstract_excerpt":"Understanding recurrent networks through rule extraction has a long history. This has taken on new interests due to the need for interpreting or verifying neural networks. One basic form for representing stateful rules is deterministic finite automata (DFA). Previous research shows that extracting DFAs from trained second-order recurrent networks is not only possible but also relatively stable. Recently, several new types of recurrent networks with more complicated architectures have been introduced. These handle challenging learning tasks usually involving sequential data. However, it remains"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.05420","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":"1801.05420","created_at":"2026-05-18T00:00:39.795452+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.05420v2","created_at":"2026-05-18T00:00:39.795452+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.05420","created_at":"2026-05-18T00:00:39.795452+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQLS7NNQ2RBV","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQLS7NNQ2RBVDOUY","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQLS7NNQ","created_at":"2026-05-18T12:32:31.084164+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/IQLS7NNQ2RBVDOUYK5CBR776B4","json":"https://pith.science/pith/IQLS7NNQ2RBVDOUYK5CBR776B4.json","graph_json":"https://pith.science/api/pith-number/IQLS7NNQ2RBVDOUYK5CBR776B4/graph.json","events_json":"https://pith.science/api/pith-number/IQLS7NNQ2RBVDOUYK5CBR776B4/events.json","paper":"https://pith.science/paper/IQLS7NNQ"},"agent_actions":{"view_html":"https://pith.science/pith/IQLS7NNQ2RBVDOUYK5CBR776B4","download_json":"https://pith.science/pith/IQLS7NNQ2RBVDOUYK5CBR776B4.json","view_paper":"https://pith.science/paper/IQLS7NNQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.05420&json=true","fetch_graph":"https://pith.science/api/pith-number/IQLS7NNQ2RBVDOUYK5CBR776B4/graph.json","fetch_events":"https://pith.science/api/pith-number/IQLS7NNQ2RBVDOUYK5CBR776B4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQLS7NNQ2RBVDOUYK5CBR776B4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQLS7NNQ2RBVDOUYK5CBR776B4/action/storage_attestation","attest_author":"https://pith.science/pith/IQLS7NNQ2RBVDOUYK5CBR776B4/action/author_attestation","sign_citation":"https://pith.science/pith/IQLS7NNQ2RBVDOUYK5CBR776B4/action/citation_signature","submit_replication":"https://pith.science/pith/IQLS7NNQ2RBVDOUYK5CBR776B4/action/replication_record"}},"created_at":"2026-05-18T00:00:39.795452+00:00","updated_at":"2026-05-18T00:00:39.795452+00:00"}