{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PYP526UPSCFQJHNHO46DL7BJNL","short_pith_number":"pith:PYP526UP","canonical_record":{"source":{"id":"1804.09401","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-25T07:40:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"07b64970c0a7dffe5e487ce490ed597608f450fb920c8487bde16e490c5bfd93","abstract_canon_sha256":"e7aa262a32bc39a66c4c2b13ec2ee35b8299735918f1757564062e3de62ac559"},"schema_version":"1.0"},"canonical_sha256":"7e1fdd7a8f908b049da7773c35fc296afb28ca978afd4b038beb1b65d0d5c1c2","source":{"kind":"arxiv","id":"1804.09401","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.09401","created_at":"2026-05-18T00:10:21Z"},{"alias_kind":"arxiv_version","alias_value":"1804.09401v2","created_at":"2026-05-18T00:10:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.09401","created_at":"2026-05-18T00:10:21Z"},{"alias_kind":"pith_short_12","alias_value":"PYP526UPSCFQ","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PYP526UPSCFQJHNH","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PYP526UP","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PYP526UPSCFQJHNHO46DL7BJNL","target":"record","payload":{"canonical_record":{"source":{"id":"1804.09401","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-25T07:40:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"07b64970c0a7dffe5e487ce490ed597608f450fb920c8487bde16e490c5bfd93","abstract_canon_sha256":"e7aa262a32bc39a66c4c2b13ec2ee35b8299735918f1757564062e3de62ac559"},"schema_version":"1.0"},"canonical_sha256":"7e1fdd7a8f908b049da7773c35fc296afb28ca978afd4b038beb1b65d0d5c1c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:21.819339Z","signature_b64":"bxfoLZc1/JkivhsL1A/qUmMqe9FycPaEN0Zm+ZO4dkjAFw83x1kc3bd78Ce+MTSJ3nd19rXrGnuzAvP1hN+0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e1fdd7a8f908b049da7773c35fc296afb28ca978afd4b038beb1b65d0d5c1c2","last_reissued_at":"2026-05-18T00:10:21.818448Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:21.818448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.09401","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:10:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/d4nYdJ+UMS/hBjYrMmL71mvMA1aEuwLQhklpzOQbLHBvSuGhIXupsAdPkiSgnOYDhFoTGxP5bznU41ZZ6r2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:52:15.399033Z"},"content_sha256":"1927933df8a04c7ac033e136469a211c3a35a62a8488d264d20e6ed6461bf559","schema_version":"1.0","event_id":"sha256:1927933df8a04c7ac033e136469a211c3a35a62a8488d264d20e6ed6461bf559"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PYP526UPSCFQJHNHO46DL7BJNL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Temporal Models with Spatial Memory for Partially Observed Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Pritzel, Danilo Jimenez Rezende, Fabio Viola, Marco Fraccaro, S. M. Ali Eslami, Yori Zwols","submitted_at":"2018-04-25T07:40:37Z","abstract_excerpt":"In model-based reinforcement learning, generative and temporal models of environments can be leveraged to boost agent performance, either by tuning the agent's representations during training or via use as part of an explicit planning mechanism. However, their application in practice has been limited to simplistic environments, due to the difficulty of training such models in larger, potentially partially-observed and 3D environments. In this work we introduce a novel action-conditioned generative model of such challenging environments. The model features a non-parametric spatial memory system"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.09401","kind":"arxiv","version":2},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:10:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k6hNZhFdohGc7z9whRcCfFhNopnzrHY2PAeCtG4ITEUz/W5PvoF2OAIJHNjqM2IoTZPwEBwYCyWCOV3hHpRmBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:52:15.399660Z"},"content_sha256":"0bd4db96a0b8cbf708905adbc63e7c555f6a584e1cc4b39db3c667bd1b43c3ac","schema_version":"1.0","event_id":"sha256:0bd4db96a0b8cbf708905adbc63e7c555f6a584e1cc4b39db3c667bd1b43c3ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PYP526UPSCFQJHNHO46DL7BJNL/bundle.json","state_url":"https://pith.science/pith/PYP526UPSCFQJHNHO46DL7BJNL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PYP526UPSCFQJHNHO46DL7BJNL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T19:52:15Z","links":{"resolver":"https://pith.science/pith/PYP526UPSCFQJHNHO46DL7BJNL","bundle":"https://pith.science/pith/PYP526UPSCFQJHNHO46DL7BJNL/bundle.json","state":"https://pith.science/pith/PYP526UPSCFQJHNHO46DL7BJNL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PYP526UPSCFQJHNHO46DL7BJNL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PYP526UPSCFQJHNHO46DL7BJNL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e7aa262a32bc39a66c4c2b13ec2ee35b8299735918f1757564062e3de62ac559","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-25T07:40:37Z","title_canon_sha256":"07b64970c0a7dffe5e487ce490ed597608f450fb920c8487bde16e490c5bfd93"},"schema_version":"1.0","source":{"id":"1804.09401","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.09401","created_at":"2026-05-18T00:10:21Z"},{"alias_kind":"arxiv_version","alias_value":"1804.09401v2","created_at":"2026-05-18T00:10:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.09401","created_at":"2026-05-18T00:10:21Z"},{"alias_kind":"pith_short_12","alias_value":"PYP526UPSCFQ","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PYP526UPSCFQJHNH","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PYP526UP","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:0bd4db96a0b8cbf708905adbc63e7c555f6a584e1cc4b39db3c667bd1b43c3ac","target":"graph","created_at":"2026-05-18T00:10:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In model-based reinforcement learning, generative and temporal models of environments can be leveraged to boost agent performance, either by tuning the agent's representations during training or via use as part of an explicit planning mechanism. However, their application in practice has been limited to simplistic environments, due to the difficulty of training such models in larger, potentially partially-observed and 3D environments. In this work we introduce a novel action-conditioned generative model of such challenging environments. The model features a non-parametric spatial memory system","authors_text":"Alexander Pritzel, Danilo Jimenez Rezende, Fabio Viola, Marco Fraccaro, S. M. Ali Eslami, Yori Zwols","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-25T07:40:37Z","title":"Generative Temporal Models with Spatial Memory for Partially Observed Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.09401","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1927933df8a04c7ac033e136469a211c3a35a62a8488d264d20e6ed6461bf559","target":"record","created_at":"2026-05-18T00:10:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e7aa262a32bc39a66c4c2b13ec2ee35b8299735918f1757564062e3de62ac559","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-25T07:40:37Z","title_canon_sha256":"07b64970c0a7dffe5e487ce490ed597608f450fb920c8487bde16e490c5bfd93"},"schema_version":"1.0","source":{"id":"1804.09401","kind":"arxiv","version":2}},"canonical_sha256":"7e1fdd7a8f908b049da7773c35fc296afb28ca978afd4b038beb1b65d0d5c1c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e1fdd7a8f908b049da7773c35fc296afb28ca978afd4b038beb1b65d0d5c1c2","first_computed_at":"2026-05-18T00:10:21.818448Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:21.818448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bxfoLZc1/JkivhsL1A/qUmMqe9FycPaEN0Zm+ZO4dkjAFw83x1kc3bd78Ce+MTSJ3nd19rXrGnuzAvP1hN+0Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:21.819339Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.09401","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1927933df8a04c7ac033e136469a211c3a35a62a8488d264d20e6ed6461bf559","sha256:0bd4db96a0b8cbf708905adbc63e7c555f6a584e1cc4b39db3c667bd1b43c3ac"],"state_sha256":"03d84fe2e2fb7896676c2ca0738ab361fb363eb725f529547c13cdad9bc228b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bxnxeKCxk+Ds64lxwGP++5GaYUtZhr+ReAZbFQWUo4moUm7ZQXnCvNBPvGwCPX20rYI0bW2Dem0B8aKw8MYIDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:52:15.403168Z","bundle_sha256":"3fc924a0fdf59bddb9fee4b2959b9a048b30d8859ab2cb5a69399ba1829e8ef8"}}