{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IWO7APZGBKTOYHCZ26XGGCKDBM","short_pith_number":"pith:IWO7APZG","schema_version":"1.0","canonical_sha256":"459df03f260aa6ec1c59d7ae6309430b2ea2bad134abb59fb3cca06159ba7c2c","source":{"kind":"arxiv","id":"1910.01189","version":7},"attestation_state":"computed","paper":{"title":"Improved Attention Models for Memory Augmented Neural Network Adaptive Controllers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Deepan Muthirayan, Pramod P. Khargonekar, Scott Nivison","submitted_at":"2019-10-02T19:52:03Z","abstract_excerpt":"We introduced a {\\it working memory} augmented adaptive controller in our recent work. The controller uses attention to read from and write to the working memory. Attention allows the controller to read specific information that is relevant and update its working memory with information based on its relevance. The retrieved information is used to modify the final control input computed by the controller. We showed that this modification speeds up learning. In the above work, we used a soft-attention mechanism for the adaptive controller. Controllers that use soft attention or hard attention me"},"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":"1910.01189","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2019-10-02T19:52:03Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"e024620d531f2f5206ce6ff9f0f4580223c8e466dfdd9c771bf63a0f5643fb42","abstract_canon_sha256":"6b7f666504e82336c8fc7ed0886d864fe62dbd2e61c5fbe232aa5513ad096ba8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:24.901808Z","signature_b64":"MaV/XUsgudpE/AndrvhOHRBLYMk+aOMLa/OnGPEQ2LxCHdV74oK7RzIQsSqZdQZ2ySqusywKKvZMXFSSD7MSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"459df03f260aa6ec1c59d7ae6309430b2ea2bad134abb59fb3cca06159ba7c2c","last_reissued_at":"2026-07-05T00:49:24.901273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:24.901273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Attention Models for Memory Augmented Neural Network Adaptive Controllers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Deepan Muthirayan, Pramod P. Khargonekar, Scott Nivison","submitted_at":"2019-10-02T19:52:03Z","abstract_excerpt":"We introduced a {\\it working memory} augmented adaptive controller in our recent work. The controller uses attention to read from and write to the working memory. Attention allows the controller to read specific information that is relevant and update its working memory with information based on its relevance. The retrieved information is used to modify the final control input computed by the controller. We showed that this modification speeds up learning. In the above work, we used a soft-attention mechanism for the adaptive controller. Controllers that use soft attention or hard attention me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.01189","kind":"arxiv","version":7},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.01189/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1910.01189","created_at":"2026-07-05T00:49:24.901347+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.01189v7","created_at":"2026-07-05T00:49:24.901347+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.01189","created_at":"2026-07-05T00:49:24.901347+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWO7APZGBKTO","created_at":"2026-07-05T00:49:24.901347+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWO7APZGBKTOYHCZ","created_at":"2026-07-05T00:49:24.901347+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWO7APZG","created_at":"2026-07-05T00:49:24.901347+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05669","citing_title":"Context-Aware Multi-Turn Visual-Textual Reasoning in LVLMs via Dynamic Memory and Adaptive Visual Guidance","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IWO7APZGBKTOYHCZ26XGGCKDBM","json":"https://pith.science/pith/IWO7APZGBKTOYHCZ26XGGCKDBM.json","graph_json":"https://pith.science/api/pith-number/IWO7APZGBKTOYHCZ26XGGCKDBM/graph.json","events_json":"https://pith.science/api/pith-number/IWO7APZGBKTOYHCZ26XGGCKDBM/events.json","paper":"https://pith.science/paper/IWO7APZG"},"agent_actions":{"view_html":"https://pith.science/pith/IWO7APZGBKTOYHCZ26XGGCKDBM","download_json":"https://pith.science/pith/IWO7APZGBKTOYHCZ26XGGCKDBM.json","view_paper":"https://pith.science/paper/IWO7APZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.01189&json=true","fetch_graph":"https://pith.science/api/pith-number/IWO7APZGBKTOYHCZ26XGGCKDBM/graph.json","fetch_events":"https://pith.science/api/pith-number/IWO7APZGBKTOYHCZ26XGGCKDBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWO7APZGBKTOYHCZ26XGGCKDBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWO7APZGBKTOYHCZ26XGGCKDBM/action/storage_attestation","attest_author":"https://pith.science/pith/IWO7APZGBKTOYHCZ26XGGCKDBM/action/author_attestation","sign_citation":"https://pith.science/pith/IWO7APZGBKTOYHCZ26XGGCKDBM/action/citation_signature","submit_replication":"https://pith.science/pith/IWO7APZGBKTOYHCZ26XGGCKDBM/action/replication_record"}},"created_at":"2026-07-05T00:49:24.901347+00:00","updated_at":"2026-07-05T00:49:24.901347+00:00"}