{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XGHADERRULC36H5KHRYIRLSZBI","short_pith_number":"pith:XGHADERR","schema_version":"1.0","canonical_sha256":"b98e019231a2c5bf1faa3c7088ae590a06276bc53bb3e11d9fb4998c4223f03e","source":{"kind":"arxiv","id":"1808.01591","version":1},"attestation_state":"computed","paper":{"title":"LISA: Explaining Recurrent Neural Network Judgments via Layer-wIse Semantic Accumulation and Example to Pattern Transformation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hinrich Sch\\\"utze, Pankaj Gupta","submitted_at":"2018-08-05T09:50:47Z","abstract_excerpt":"Recurrent neural networks (RNNs) are temporal networks and cumulative in nature that have shown promising results in various natural language processing tasks. Despite their success, it still remains a challenge to understand their hidden behavior. In this work, we analyze and interpret the cumulative nature of RNN via a proposed technique named as Layer-wIse-Semantic-Accumulation (LISA) for explaining decisions and detecting the most likely (i.e., saliency) patterns that the network relies on while decision making. We demonstrate (1) LISA: \"How an RNN accumulates or builds semantics during it"},"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":"1808.01591","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-05T09:50:47Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"e6693c2e5fb06ae08c50775206d216a690a2bb19dda440b37dc6d4a2d46e0903","abstract_canon_sha256":"1e0c21138c190984f677d9bd29a5db76fdec7204baaa160b1cd4c65bf43d645a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:52.508508Z","signature_b64":"DkZ1g5MxOVKim7HBZQDDq0ux7q2ml2GIXMtx6RWpUaa7s/EsSZcLySKAHzfbf1JGX1HoNUaDnZNWL10gQebCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b98e019231a2c5bf1faa3c7088ae590a06276bc53bb3e11d9fb4998c4223f03e","last_reissued_at":"2026-05-18T00:08:52.507641Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:52.507641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LISA: Explaining Recurrent Neural Network Judgments via Layer-wIse Semantic Accumulation and Example to Pattern Transformation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hinrich Sch\\\"utze, Pankaj Gupta","submitted_at":"2018-08-05T09:50:47Z","abstract_excerpt":"Recurrent neural networks (RNNs) are temporal networks and cumulative in nature that have shown promising results in various natural language processing tasks. Despite their success, it still remains a challenge to understand their hidden behavior. In this work, we analyze and interpret the cumulative nature of RNN via a proposed technique named as Layer-wIse-Semantic-Accumulation (LISA) for explaining decisions and detecting the most likely (i.e., saliency) patterns that the network relies on while decision making. We demonstrate (1) LISA: \"How an RNN accumulates or builds semantics during it"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.01591","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":"1808.01591","created_at":"2026-05-18T00:08:52.507783+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.01591v1","created_at":"2026-05-18T00:08:52.507783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.01591","created_at":"2026-05-18T00:08:52.507783+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGHADERRULC3","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGHADERRULC36H5K","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGHADERR","created_at":"2026-05-18T12:33:01.666342+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/XGHADERRULC36H5KHRYIRLSZBI","json":"https://pith.science/pith/XGHADERRULC36H5KHRYIRLSZBI.json","graph_json":"https://pith.science/api/pith-number/XGHADERRULC36H5KHRYIRLSZBI/graph.json","events_json":"https://pith.science/api/pith-number/XGHADERRULC36H5KHRYIRLSZBI/events.json","paper":"https://pith.science/paper/XGHADERR"},"agent_actions":{"view_html":"https://pith.science/pith/XGHADERRULC36H5KHRYIRLSZBI","download_json":"https://pith.science/pith/XGHADERRULC36H5KHRYIRLSZBI.json","view_paper":"https://pith.science/paper/XGHADERR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.01591&json=true","fetch_graph":"https://pith.science/api/pith-number/XGHADERRULC36H5KHRYIRLSZBI/graph.json","fetch_events":"https://pith.science/api/pith-number/XGHADERRULC36H5KHRYIRLSZBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGHADERRULC36H5KHRYIRLSZBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGHADERRULC36H5KHRYIRLSZBI/action/storage_attestation","attest_author":"https://pith.science/pith/XGHADERRULC36H5KHRYIRLSZBI/action/author_attestation","sign_citation":"https://pith.science/pith/XGHADERRULC36H5KHRYIRLSZBI/action/citation_signature","submit_replication":"https://pith.science/pith/XGHADERRULC36H5KHRYIRLSZBI/action/replication_record"}},"created_at":"2026-05-18T00:08:52.507783+00:00","updated_at":"2026-05-18T00:08:52.507783+00:00"}