{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5NY3CKWOUBOGDS7GEAOYAZ2TW5","short_pith_number":"pith:5NY3CKWO","schema_version":"1.0","canonical_sha256":"eb71b12acea05c61cbe6201d806753b76fcfbf207fd31fc82a7a0c7e66017fa3","source":{"kind":"arxiv","id":"1803.10760","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Predictive Memory in a Goal-Directed Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Cain, Adam Santoro, Agnieszka Grabska-Barwinska, Arun Ahuja, Chia-Chun Hung, Chloe Hillier, Danilo Rezende, David Amos, David Saxton, David Silver, Demis Hassabis, Greg Wayne, Jack Rae, Joel Z. Leibo, Josh Abramson, Koray Kavukcuoglu, Malcolm Reynolds, Matt Botvinick, Mehdi Mirza, Mevlana Gemici, Piotr Mirowski, Shakir Mohamed, Tim Harley, Timothy Lillicrap","submitted_at":"2018-03-28T17:54:01Z","abstract_excerpt":"Animals execute goal-directed behaviours despite the limited range and scope of their sensors. To cope, they explore environments and store memories maintaining estimates of important information that is not presently available. Recently, progress has been made with artificial intelligence (AI) agents that learn to perform tasks from sensory input, even at a human level, by merging reinforcement learning (RL) algorithms with deep neural networks, and the excitement surrounding these results has led to the pursuit of related ideas as explanations of non-human animal learning. However, we demons"},"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":"1803.10760","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-28T17:54:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c26350a0adc3d86f556d0ce5a8c1d2e4aaaa2cb70f2d80d2457711e3758de60c","abstract_canon_sha256":"bd83f530fe3b7621c9dc634a2ad42ce43c04b930fa467c58df1474eeb50b6860"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:54.184393Z","signature_b64":"O2VwO4Ubk2tJnkw1KYrPORoXDFyJX/YLMzRO1Q6xC8k0YaTP+Yi2cPhmbGUixN1lVrPk20B6xBeE67+PdXG8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb71b12acea05c61cbe6201d806753b76fcfbf207fd31fc82a7a0c7e66017fa3","last_reissued_at":"2026-05-18T00:19:54.183593Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:54.183593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Predictive Memory in a Goal-Directed Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Cain, Adam Santoro, Agnieszka Grabska-Barwinska, Arun Ahuja, Chia-Chun Hung, Chloe Hillier, Danilo Rezende, David Amos, David Saxton, David Silver, Demis Hassabis, Greg Wayne, Jack Rae, Joel Z. Leibo, Josh Abramson, Koray Kavukcuoglu, Malcolm Reynolds, Matt Botvinick, Mehdi Mirza, Mevlana Gemici, Piotr Mirowski, Shakir Mohamed, Tim Harley, Timothy Lillicrap","submitted_at":"2018-03-28T17:54:01Z","abstract_excerpt":"Animals execute goal-directed behaviours despite the limited range and scope of their sensors. To cope, they explore environments and store memories maintaining estimates of important information that is not presently available. Recently, progress has been made with artificial intelligence (AI) agents that learn to perform tasks from sensory input, even at a human level, by merging reinforcement learning (RL) algorithms with deep neural networks, and the excitement surrounding these results has led to the pursuit of related ideas as explanations of non-human animal learning. However, we demons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10760","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":"1803.10760","created_at":"2026-05-18T00:19:54.183733+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.10760v1","created_at":"2026-05-18T00:19:54.183733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10760","created_at":"2026-05-18T00:19:54.183733+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NY3CKWOUBOG","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NY3CKWOUBOGDS7G","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NY3CKWO","created_at":"2026-05-18T12:32:08.215937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2010.02193","citing_title":"Mastering Atari with Discrete World Models","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01694","citing_title":"Latent State Design for World Models under Sufficiency Constraints","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5NY3CKWOUBOGDS7GEAOYAZ2TW5","json":"https://pith.science/pith/5NY3CKWOUBOGDS7GEAOYAZ2TW5.json","graph_json":"https://pith.science/api/pith-number/5NY3CKWOUBOGDS7GEAOYAZ2TW5/graph.json","events_json":"https://pith.science/api/pith-number/5NY3CKWOUBOGDS7GEAOYAZ2TW5/events.json","paper":"https://pith.science/paper/5NY3CKWO"},"agent_actions":{"view_html":"https://pith.science/pith/5NY3CKWOUBOGDS7GEAOYAZ2TW5","download_json":"https://pith.science/pith/5NY3CKWOUBOGDS7GEAOYAZ2TW5.json","view_paper":"https://pith.science/paper/5NY3CKWO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.10760&json=true","fetch_graph":"https://pith.science/api/pith-number/5NY3CKWOUBOGDS7GEAOYAZ2TW5/graph.json","fetch_events":"https://pith.science/api/pith-number/5NY3CKWOUBOGDS7GEAOYAZ2TW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NY3CKWOUBOGDS7GEAOYAZ2TW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NY3CKWOUBOGDS7GEAOYAZ2TW5/action/storage_attestation","attest_author":"https://pith.science/pith/5NY3CKWOUBOGDS7GEAOYAZ2TW5/action/author_attestation","sign_citation":"https://pith.science/pith/5NY3CKWOUBOGDS7GEAOYAZ2TW5/action/citation_signature","submit_replication":"https://pith.science/pith/5NY3CKWOUBOGDS7GEAOYAZ2TW5/action/replication_record"}},"created_at":"2026-05-18T00:19:54.183733+00:00","updated_at":"2026-05-18T00:19:54.183733+00:00"}