{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EWLZGT3BZRV27SAKLWJEZ5A62D","short_pith_number":"pith:EWLZGT3B","schema_version":"1.0","canonical_sha256":"2597934f61cc6bafc80a5d924cf41ed0ef6e6a51e1f76c9a5162edc0769a5626","source":{"kind":"arxiv","id":"1806.03107","version":3},"attestation_state":"computed","paper":{"title":"Temporal Difference Variational Auto-Encoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Frederic Besse, George Papamakarios, Karol Gregor, Lars Buesing, Theophane Weber","submitted_at":"2018-06-08T12:10:58Z","abstract_excerpt":"To act and plan in complex environments, we posit that agents should have a mental simulator of the world with three characteristics: (a) it should build an abstract state representing the condition of the world; (b) it should form a belief which represents uncertainty on the world; (c) it should go beyond simple step-by-step simulation, and exhibit temporal abstraction. Motivated by the absence of a model satisfying all these requirements, we propose TD-VAE, a generative sequence model that learns representations containing explicit beliefs about states several steps into the future, and that"},"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":"1806.03107","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-08T12:10:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fcf83341c4cbf7feaf177791ca7ecc679e3e12027475fc02714c0883ca8025d2","abstract_canon_sha256":"df1a6d46e63d8fa880aa91eb17501c41ee038e438f41582b762023ad893391f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:06.167750Z","signature_b64":"b871YOupyviS9Cu+m+gTrE2aij5+3d0fsN6p87wtxvqMlKE2JJu05IMTuPJ+xShamLOguT5jKdtxOlmdvoOXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2597934f61cc6bafc80a5d924cf41ed0ef6e6a51e1f76c9a5162edc0769a5626","last_reissued_at":"2026-05-17T23:57:06.167149Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:06.167149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal Difference Variational Auto-Encoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Frederic Besse, George Papamakarios, Karol Gregor, Lars Buesing, Theophane Weber","submitted_at":"2018-06-08T12:10:58Z","abstract_excerpt":"To act and plan in complex environments, we posit that agents should have a mental simulator of the world with three characteristics: (a) it should build an abstract state representing the condition of the world; (b) it should form a belief which represents uncertainty on the world; (c) it should go beyond simple step-by-step simulation, and exhibit temporal abstraction. Motivated by the absence of a model satisfying all these requirements, we propose TD-VAE, a generative sequence model that learns representations containing explicit beliefs about states several steps into the future, and that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03107","kind":"arxiv","version":3},"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":"1806.03107","created_at":"2026-05-17T23:57:06.167237+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.03107v3","created_at":"2026-05-17T23:57:06.167237+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03107","created_at":"2026-05-17T23:57:06.167237+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWLZGT3BZRV2","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWLZGT3BZRV27SAK","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWLZGT3B","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"1906.09237","citing_title":"Shaping Belief States with Generative Environment Models for RL","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"1906.09510","citing_title":"Learning Belief Representations for Imitation Learning in POMDPs","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00664","citing_title":"Learning World Graphs to Accelerate Hierarchical Reinforcement Learning","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16054","citing_title":"Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making","ref_index":295,"is_internal_anchor":true},{"citing_arxiv_id":"2010.02193","citing_title":"Mastering Atari with Discrete World Models","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EWLZGT3BZRV27SAKLWJEZ5A62D","json":"https://pith.science/pith/EWLZGT3BZRV27SAKLWJEZ5A62D.json","graph_json":"https://pith.science/api/pith-number/EWLZGT3BZRV27SAKLWJEZ5A62D/graph.json","events_json":"https://pith.science/api/pith-number/EWLZGT3BZRV27SAKLWJEZ5A62D/events.json","paper":"https://pith.science/paper/EWLZGT3B"},"agent_actions":{"view_html":"https://pith.science/pith/EWLZGT3BZRV27SAKLWJEZ5A62D","download_json":"https://pith.science/pith/EWLZGT3BZRV27SAKLWJEZ5A62D.json","view_paper":"https://pith.science/paper/EWLZGT3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.03107&json=true","fetch_graph":"https://pith.science/api/pith-number/EWLZGT3BZRV27SAKLWJEZ5A62D/graph.json","fetch_events":"https://pith.science/api/pith-number/EWLZGT3BZRV27SAKLWJEZ5A62D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWLZGT3BZRV27SAKLWJEZ5A62D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWLZGT3BZRV27SAKLWJEZ5A62D/action/storage_attestation","attest_author":"https://pith.science/pith/EWLZGT3BZRV27SAKLWJEZ5A62D/action/author_attestation","sign_citation":"https://pith.science/pith/EWLZGT3BZRV27SAKLWJEZ5A62D/action/citation_signature","submit_replication":"https://pith.science/pith/EWLZGT3BZRV27SAKLWJEZ5A62D/action/replication_record"}},"created_at":"2026-05-17T23:57:06.167237+00:00","updated_at":"2026-05-17T23:57:06.167237+00:00"}