{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:3ALMLPGHXLWF2CQG2TQ5DXXST4","short_pith_number":"pith:3ALMLPGH","canonical_record":{"source":{"id":"1507.06527","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-23T15:16:46Z","cross_cats_sorted":[],"title_canon_sha256":"9a44724b25a09d4956c27ae7adab7a388179ba9baf4de86bab06ea5c2a9ec7b9","abstract_canon_sha256":"a91f5911eb288ca34cbf3bb7ff898f355672e55451ad119e5cbe0f630cde0695"},"schema_version":"1.0"},"canonical_sha256":"d816c5bcc7baec5d0a06d4e1d1def29f21351dd8ff355e6bbabff3005dcee032","source":{"kind":"arxiv","id":"1507.06527","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.06527","created_at":"2026-05-18T00:52:59Z"},{"alias_kind":"arxiv_version","alias_value":"1507.06527v4","created_at":"2026-05-18T00:52:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.06527","created_at":"2026-05-18T00:52:59Z"},{"alias_kind":"pith_short_12","alias_value":"3ALMLPGHXLWF","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"3ALMLPGHXLWF2CQG","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"3ALMLPGH","created_at":"2026-05-18T12:29:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:3ALMLPGHXLWF2CQG2TQ5DXXST4","target":"record","payload":{"canonical_record":{"source":{"id":"1507.06527","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-23T15:16:46Z","cross_cats_sorted":[],"title_canon_sha256":"9a44724b25a09d4956c27ae7adab7a388179ba9baf4de86bab06ea5c2a9ec7b9","abstract_canon_sha256":"a91f5911eb288ca34cbf3bb7ff898f355672e55451ad119e5cbe0f630cde0695"},"schema_version":"1.0"},"canonical_sha256":"d816c5bcc7baec5d0a06d4e1d1def29f21351dd8ff355e6bbabff3005dcee032","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:59.320376Z","signature_b64":"OHYnQbcNy9hHP9Bjszv+K0jGF4achOxF27d90rYyrV3FakLUP5p9JEFJWvkbU5DTXXcSVeWwjVVZ3DPrIbFeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d816c5bcc7baec5d0a06d4e1d1def29f21351dd8ff355e6bbabff3005dcee032","last_reissued_at":"2026-05-18T00:52:59.319977Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:59.319977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.06527","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:52:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yTsfwA798aq8T1dv7uM24lrZMZrc9lLFJPCFnUKMVcFixoTRPDhHG0rONRQPi0wFZd8QkMECoZru/pA1A+ZwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T02:00:48.616060Z"},"content_sha256":"7297b903aac7f27c9f7d43d843643b926186b8bfe939126ea3506fba2a5bdf31","schema_version":"1.0","event_id":"sha256:7297b903aac7f27c9f7d43d843643b926186b8bfe939126ea3506fba2a5bdf31"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:3ALMLPGHXLWF2CQG2TQ5DXXST4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Recurrent Q-Learning for Partially Observable MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Matthew Hausknecht, Peter Stone","submitted_at":"2015-07-23T15:16:46Z","abstract_excerpt":"Deep Reinforcement Learning has yielded proficient controllers for complex tasks. However, these controllers have limited memory and rely on being able to perceive the complete game screen at each decision point. To address these shortcomings, this article investigates the effects of adding recurrency to a Deep Q-Network (DQN) by replacing the first post-convolutional fully-connected layer with a recurrent LSTM. The resulting \\textit{Deep Recurrent Q-Network} (DRQN), although capable of seeing only a single frame at each timestep, successfully integrates information through time and replicates"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.06527","kind":"arxiv","version":4},"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":"2026-05-18T00:52:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GUHxuF44Fl9jSf3fT94IZeVbZejr0khW9KA2/GAHFiurBxVR3l7iC3KMukt+v9k2Wn2FrpgagTsRwwMzhnDDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T02:00:48.616526Z"},"content_sha256":"018893cc0cd9310f71d76207053ce5eb16969cffcf2d62f7152498cb4ac50e0a","schema_version":"1.0","event_id":"sha256:018893cc0cd9310f71d76207053ce5eb16969cffcf2d62f7152498cb4ac50e0a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3ALMLPGHXLWF2CQG2TQ5DXXST4/bundle.json","state_url":"https://pith.science/pith/3ALMLPGHXLWF2CQG2TQ5DXXST4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3ALMLPGHXLWF2CQG2TQ5DXXST4/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":"2026-06-11T02:00:48Z","links":{"resolver":"https://pith.science/pith/3ALMLPGHXLWF2CQG2TQ5DXXST4","bundle":"https://pith.science/pith/3ALMLPGHXLWF2CQG2TQ5DXXST4/bundle.json","state":"https://pith.science/pith/3ALMLPGHXLWF2CQG2TQ5DXXST4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3ALMLPGHXLWF2CQG2TQ5DXXST4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:3ALMLPGHXLWF2CQG2TQ5DXXST4","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":"a91f5911eb288ca34cbf3bb7ff898f355672e55451ad119e5cbe0f630cde0695","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-23T15:16:46Z","title_canon_sha256":"9a44724b25a09d4956c27ae7adab7a388179ba9baf4de86bab06ea5c2a9ec7b9"},"schema_version":"1.0","source":{"id":"1507.06527","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.06527","created_at":"2026-05-18T00:52:59Z"},{"alias_kind":"arxiv_version","alias_value":"1507.06527v4","created_at":"2026-05-18T00:52:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.06527","created_at":"2026-05-18T00:52:59Z"},{"alias_kind":"pith_short_12","alias_value":"3ALMLPGHXLWF","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"3ALMLPGHXLWF2CQG","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"3ALMLPGH","created_at":"2026-05-18T12:29:02Z"}],"graph_snapshots":[{"event_id":"sha256:018893cc0cd9310f71d76207053ce5eb16969cffcf2d62f7152498cb4ac50e0a","target":"graph","created_at":"2026-05-18T00:52:59Z","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":"Deep Reinforcement Learning has yielded proficient controllers for complex tasks. However, these controllers have limited memory and rely on being able to perceive the complete game screen at each decision point. To address these shortcomings, this article investigates the effects of adding recurrency to a Deep Q-Network (DQN) by replacing the first post-convolutional fully-connected layer with a recurrent LSTM. The resulting \\textit{Deep Recurrent Q-Network} (DRQN), although capable of seeing only a single frame at each timestep, successfully integrates information through time and replicates","authors_text":"Matthew Hausknecht, Peter Stone","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-23T15:16:46Z","title":"Deep Recurrent Q-Learning for Partially Observable MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.06527","kind":"arxiv","version":4},"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":"sha256:7297b903aac7f27c9f7d43d843643b926186b8bfe939126ea3506fba2a5bdf31","target":"record","created_at":"2026-05-18T00:52:59Z","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":"a91f5911eb288ca34cbf3bb7ff898f355672e55451ad119e5cbe0f630cde0695","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-23T15:16:46Z","title_canon_sha256":"9a44724b25a09d4956c27ae7adab7a388179ba9baf4de86bab06ea5c2a9ec7b9"},"schema_version":"1.0","source":{"id":"1507.06527","kind":"arxiv","version":4}},"canonical_sha256":"d816c5bcc7baec5d0a06d4e1d1def29f21351dd8ff355e6bbabff3005dcee032","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d816c5bcc7baec5d0a06d4e1d1def29f21351dd8ff355e6bbabff3005dcee032","first_computed_at":"2026-05-18T00:52:59.319977Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:52:59.319977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OHYnQbcNy9hHP9Bjszv+K0jGF4achOxF27d90rYyrV3FakLUP5p9JEFJWvkbU5DTXXcSVeWwjVVZ3DPrIbFeDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:52:59.320376Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.06527","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7297b903aac7f27c9f7d43d843643b926186b8bfe939126ea3506fba2a5bdf31","sha256:018893cc0cd9310f71d76207053ce5eb16969cffcf2d62f7152498cb4ac50e0a"],"state_sha256":"742913e404b9272b731def4833ec02ed4950e5e7857f7ee76b937b1812786faa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RdDv64WVYLMayynh5aev870VXbU+grv/jlb0zVwfoh2fS6HQ5gPOPj6piOtwOwOU+805msj+eOROezg2ydYGDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T02:00:48.619989Z","bundle_sha256":"bfd6154c09441e401afbc986838e5d07eb4a2c6f5b382c6f204272667be9a148"}}