{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B7BRPZSZNSCGIOHYXPR6FQ6XNT","short_pith_number":"pith:B7BRPZSZ","schema_version":"1.0","canonical_sha256":"0fc317e6596c846438f8bbe3e2c3d76cfa65d28962a7c419926ae3f58ce4a35b","source":{"kind":"arxiv","id":"2107.01390","version":1},"attestation_state":"computed","paper":{"title":"Memory and attention in deep learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hung Le","submitted_at":"2021-07-03T09:21:13Z","abstract_excerpt":"Intelligence necessitates memory. Without memory, humans fail to perform various nontrivial tasks such as reading novels, playing games or solving maths. As the ultimate goal of machine learning is to derive intelligent systems that learn and act automatically just like human, memory construction for machine is inevitable. Artificial neural networks model neurons and synapses in the brain by interconnecting computational units via weights, which is a typical class of machine learning algorithms that resembles memory structure. Their descendants with more complicated modeling techniques (a.k.a "},"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":"2107.01390","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-03T09:21:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3340d66f68c3b6049c1ea30dd4321c6414248d798535ae3ed1841ca8ac458ca2","abstract_canon_sha256":"145078a57c6ef50df57302fb930e9aea750c16a2ec32841bc046cc92a3f5f2ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:42.580996Z","signature_b64":"mf7nX+QWFReYbbtKLkcXFFnrOfqKoIbCdXVC9yWFFf3Qtu36etDXsns639wu0G5jauUrY/Z112tjv0MyOH9qAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fc317e6596c846438f8bbe3e2c3d76cfa65d28962a7c419926ae3f58ce4a35b","last_reissued_at":"2026-07-05T02:54:42.580640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:42.580640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory and attention in deep learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hung Le","submitted_at":"2021-07-03T09:21:13Z","abstract_excerpt":"Intelligence necessitates memory. Without memory, humans fail to perform various nontrivial tasks such as reading novels, playing games or solving maths. As the ultimate goal of machine learning is to derive intelligent systems that learn and act automatically just like human, memory construction for machine is inevitable. Artificial neural networks model neurons and synapses in the brain by interconnecting computational units via weights, which is a typical class of machine learning algorithms that resembles memory structure. Their descendants with more complicated modeling techniques (a.k.a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01390","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.01390/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":"2107.01390","created_at":"2026-07-05T02:54:42.580696+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.01390v1","created_at":"2026-07-05T02:54:42.580696+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01390","created_at":"2026-07-05T02:54:42.580696+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7BRPZSZNSCG","created_at":"2026-07-05T02:54:42.580696+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7BRPZSZNSCGIOHY","created_at":"2026-07-05T02:54:42.580696+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7BRPZSZ","created_at":"2026-07-05T02:54:42.580696+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":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B7BRPZSZNSCGIOHYXPR6FQ6XNT","json":"https://pith.science/pith/B7BRPZSZNSCGIOHYXPR6FQ6XNT.json","graph_json":"https://pith.science/api/pith-number/B7BRPZSZNSCGIOHYXPR6FQ6XNT/graph.json","events_json":"https://pith.science/api/pith-number/B7BRPZSZNSCGIOHYXPR6FQ6XNT/events.json","paper":"https://pith.science/paper/B7BRPZSZ"},"agent_actions":{"view_html":"https://pith.science/pith/B7BRPZSZNSCGIOHYXPR6FQ6XNT","download_json":"https://pith.science/pith/B7BRPZSZNSCGIOHYXPR6FQ6XNT.json","view_paper":"https://pith.science/paper/B7BRPZSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.01390&json=true","fetch_graph":"https://pith.science/api/pith-number/B7BRPZSZNSCGIOHYXPR6FQ6XNT/graph.json","fetch_events":"https://pith.science/api/pith-number/B7BRPZSZNSCGIOHYXPR6FQ6XNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7BRPZSZNSCGIOHYXPR6FQ6XNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7BRPZSZNSCGIOHYXPR6FQ6XNT/action/storage_attestation","attest_author":"https://pith.science/pith/B7BRPZSZNSCGIOHYXPR6FQ6XNT/action/author_attestation","sign_citation":"https://pith.science/pith/B7BRPZSZNSCGIOHYXPR6FQ6XNT/action/citation_signature","submit_replication":"https://pith.science/pith/B7BRPZSZNSCGIOHYXPR6FQ6XNT/action/replication_record"}},"created_at":"2026-07-05T02:54:42.580696+00:00","updated_at":"2026-07-05T02:54:42.580696+00:00"}