{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:34HXKLRYRGERYZTBTLE5QPY4ND","short_pith_number":"pith:34HXKLRY","canonical_record":{"source":{"id":"1512.04455","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-14T18:44:48Z","cross_cats_sorted":[],"title_canon_sha256":"cb89ea8cca6845956564ea83ead799308ac06c98ff25a472b78c725ffc49c269","abstract_canon_sha256":"3edf02a416cc3b691539e2cf5db6e2bf68451400692079384496f7cea3197c79"},"schema_version":"1.0"},"canonical_sha256":"df0f752e3889891c66619ac9d83f1c68ce0c347ed9821c0cfa937178dabf5a07","source":{"kind":"arxiv","id":"1512.04455","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.04455","created_at":"2026-05-18T01:24:22Z"},{"alias_kind":"arxiv_version","alias_value":"1512.04455v1","created_at":"2026-05-18T01:24:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.04455","created_at":"2026-05-18T01:24:22Z"},{"alias_kind":"pith_short_12","alias_value":"34HXKLRYRGER","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"34HXKLRYRGERYZTB","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"34HXKLRY","created_at":"2026-05-18T12:29:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:34HXKLRYRGERYZTBTLE5QPY4ND","target":"record","payload":{"canonical_record":{"source":{"id":"1512.04455","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-14T18:44:48Z","cross_cats_sorted":[],"title_canon_sha256":"cb89ea8cca6845956564ea83ead799308ac06c98ff25a472b78c725ffc49c269","abstract_canon_sha256":"3edf02a416cc3b691539e2cf5db6e2bf68451400692079384496f7cea3197c79"},"schema_version":"1.0"},"canonical_sha256":"df0f752e3889891c66619ac9d83f1c68ce0c347ed9821c0cfa937178dabf5a07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:24:22.245670Z","signature_b64":"LKyozvmb9cEw83mE1i5B41nGvsMPhy+bQ+DBzvtpZGBHG2YkhrEPRlSm4H2HdskT1bxOPrFdtAoThALnGvGKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df0f752e3889891c66619ac9d83f1c68ce0c347ed9821c0cfa937178dabf5a07","last_reissued_at":"2026-05-18T01:24:22.244968Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:24:22.244968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.04455","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:24:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OW/2YyVW1Yvl58x6wvFeMuskibXvEX2EJfyWozYBRdJ+g0kQJ+EgMCjaRmzZ0iK5ThhXzzl1htV7wn0u+FKPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T15:43:44.354731Z"},"content_sha256":"ce2c05b88a581d06e982c31e735731b8680c06d218d9d94bf4bb624cc193b399","schema_version":"1.0","event_id":"sha256:ce2c05b88a581d06e982c31e735731b8680c06d218d9d94bf4bb624cc193b399"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:34HXKLRYRGERYZTBTLE5QPY4ND","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Memory-based control with recurrent neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Silver, Jonathan J Hunt, Nicolas Heess, Timothy P Lillicrap","submitted_at":"2015-12-14T18:44:48Z","abstract_excerpt":"Partially observed control problems are a challenging aspect of reinforcement learning. We extend two related, model-free algorithms for continuous control -- deterministic policy gradient and stochastic value gradient -- to solve partially observed domains using recurrent neural networks trained with backpropagation through time.\n  We demonstrate that this approach, coupled with long-short term memory is able to solve a variety of physical control problems exhibiting an assortment of memory requirements. These include the short-term integration of information from noisy sensors and the identi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.04455","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:24:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JYHQPsUSmdEhLOjgXzaorNeJNkFnNUi9ydvGzjNyO0Tu2m7U4ZWKTBpez5n+yltlTqaI0hzVe9c5jTf9/fWxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T15:43:44.355273Z"},"content_sha256":"c2cb1ce8a7212db7728cf4593cca0e5ce87e646d58c3576056b85b59e4134e78","schema_version":"1.0","event_id":"sha256:c2cb1ce8a7212db7728cf4593cca0e5ce87e646d58c3576056b85b59e4134e78"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/34HXKLRYRGERYZTBTLE5QPY4ND/bundle.json","state_url":"https://pith.science/pith/34HXKLRYRGERYZTBTLE5QPY4ND/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/34HXKLRYRGERYZTBTLE5QPY4ND/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":"2026-06-02T15:43:44Z","links":{"resolver":"https://pith.science/pith/34HXKLRYRGERYZTBTLE5QPY4ND","bundle":"https://pith.science/pith/34HXKLRYRGERYZTBTLE5QPY4ND/bundle.json","state":"https://pith.science/pith/34HXKLRYRGERYZTBTLE5QPY4ND/state.json","well_known_bundle":"https://pith.science/.well-known/pith/34HXKLRYRGERYZTBTLE5QPY4ND/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:34HXKLRYRGERYZTBTLE5QPY4ND","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":"3edf02a416cc3b691539e2cf5db6e2bf68451400692079384496f7cea3197c79","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-14T18:44:48Z","title_canon_sha256":"cb89ea8cca6845956564ea83ead799308ac06c98ff25a472b78c725ffc49c269"},"schema_version":"1.0","source":{"id":"1512.04455","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.04455","created_at":"2026-05-18T01:24:22Z"},{"alias_kind":"arxiv_version","alias_value":"1512.04455v1","created_at":"2026-05-18T01:24:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.04455","created_at":"2026-05-18T01:24:22Z"},{"alias_kind":"pith_short_12","alias_value":"34HXKLRYRGER","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"34HXKLRYRGERYZTB","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"34HXKLRY","created_at":"2026-05-18T12:29:02Z"}],"graph_snapshots":[{"event_id":"sha256:c2cb1ce8a7212db7728cf4593cca0e5ce87e646d58c3576056b85b59e4134e78","target":"graph","created_at":"2026-05-18T01:24:22Z","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":"Partially observed control problems are a challenging aspect of reinforcement learning. We extend two related, model-free algorithms for continuous control -- deterministic policy gradient and stochastic value gradient -- to solve partially observed domains using recurrent neural networks trained with backpropagation through time.\n  We demonstrate that this approach, coupled with long-short term memory is able to solve a variety of physical control problems exhibiting an assortment of memory requirements. These include the short-term integration of information from noisy sensors and the identi","authors_text":"David Silver, Jonathan J Hunt, Nicolas Heess, Timothy P Lillicrap","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-14T18:44:48Z","title":"Memory-based control with recurrent neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.04455","kind":"arxiv","version":1},"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:ce2c05b88a581d06e982c31e735731b8680c06d218d9d94bf4bb624cc193b399","target":"record","created_at":"2026-05-18T01:24:22Z","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":"3edf02a416cc3b691539e2cf5db6e2bf68451400692079384496f7cea3197c79","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-14T18:44:48Z","title_canon_sha256":"cb89ea8cca6845956564ea83ead799308ac06c98ff25a472b78c725ffc49c269"},"schema_version":"1.0","source":{"id":"1512.04455","kind":"arxiv","version":1}},"canonical_sha256":"df0f752e3889891c66619ac9d83f1c68ce0c347ed9821c0cfa937178dabf5a07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df0f752e3889891c66619ac9d83f1c68ce0c347ed9821c0cfa937178dabf5a07","first_computed_at":"2026-05-18T01:24:22.244968Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:24:22.244968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LKyozvmb9cEw83mE1i5B41nGvsMPhy+bQ+DBzvtpZGBHG2YkhrEPRlSm4H2HdskT1bxOPrFdtAoThALnGvGKBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:24:22.245670Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.04455","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce2c05b88a581d06e982c31e735731b8680c06d218d9d94bf4bb624cc193b399","sha256:c2cb1ce8a7212db7728cf4593cca0e5ce87e646d58c3576056b85b59e4134e78"],"state_sha256":"d47a3a54a90d442358c4f7185292d809134cce9b97a5aa236e8f8da1ae50f19c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cnyqN0OlmbHLXVNM3rlfAdJD+l3o5TRIHW52kntHOL9ygWdrF6XQ3YHMjtY1B1P0MQJCc/+v8Y6tjqanSMiiCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T15:43:44.357949Z","bundle_sha256":"c4f5d08598c1168b129453538d9084936a26a2af54c2f4f5f199b2b457d2ee80"}}