{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:J54V66PV4EU2EQ6MTQFOGSDHNT","short_pith_number":"pith:J54V66PV","canonical_record":{"source":{"id":"1507.04296","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-15T16:56:56Z","cross_cats_sorted":["cs.AI","cs.DC","cs.NE"],"title_canon_sha256":"239ac75310d89dc45e0e22c98bb581b363f6174d72a5a6e47c58caacca508962","abstract_canon_sha256":"bde7497031978bf24896d5e912566ba5bdb6ad59fdff3e8a60d6f753dd0b105b"},"schema_version":"1.0"},"canonical_sha256":"4f795f79f5e129a243cc9c0ae348676cfcdb594908651849f8e5076faf8bff91","source":{"kind":"arxiv","id":"1507.04296","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.04296","created_at":"2026-05-18T01:36:47Z"},{"alias_kind":"arxiv_version","alias_value":"1507.04296v2","created_at":"2026-05-18T01:36:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.04296","created_at":"2026-05-18T01:36:47Z"},{"alias_kind":"pith_short_12","alias_value":"J54V66PV4EU2","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"J54V66PV4EU2EQ6M","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"J54V66PV","created_at":"2026-05-18T12:29:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:J54V66PV4EU2EQ6MTQFOGSDHNT","target":"record","payload":{"canonical_record":{"source":{"id":"1507.04296","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-15T16:56:56Z","cross_cats_sorted":["cs.AI","cs.DC","cs.NE"],"title_canon_sha256":"239ac75310d89dc45e0e22c98bb581b363f6174d72a5a6e47c58caacca508962","abstract_canon_sha256":"bde7497031978bf24896d5e912566ba5bdb6ad59fdff3e8a60d6f753dd0b105b"},"schema_version":"1.0"},"canonical_sha256":"4f795f79f5e129a243cc9c0ae348676cfcdb594908651849f8e5076faf8bff91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:36:47.627487Z","signature_b64":"QDgzGyB0uZSPo9vwXHkua817kxn/T9IDGjjliQj5zQIL/zCNd56x7Sb57Fj3IkvYyqw4WwNPuCVTESWjka1QDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f795f79f5e129a243cc9c0ae348676cfcdb594908651849f8e5076faf8bff91","last_reissued_at":"2026-05-18T01:36:47.626824Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:36:47.626824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.04296","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":"2026-05-18T01:36:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jDilsf6rrjKkU7U1fyAYUvJYvNWd392+EbXzjNilnjjCWreV5IgyZs1iUPXpOMVYYyfsikcjbmMWbpUOqtwNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:46:06.460943Z"},"content_sha256":"944fb9fecef9762d6688660e1d1b79d456b85a305cc64dc0417fd44d3a90a7ba","schema_version":"1.0","event_id":"sha256:944fb9fecef9762d6688660e1d1b79d456b85a305cc64dc0417fd44d3a90a7ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:J54V66PV4EU2EQ6MTQFOGSDHNT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Massively Parallel Methods for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.NE"],"primary_cat":"cs.LG","authors_text":"Alessandro De Maria, Arun Nair, Cagdas Alcicek, Charles Beattie, David Silver, Koray Kavukcuoglu, Mustafa Suleyman, Praveen Srinivasan, Rory Fearon, Sam Blackwell, Shane Legg, Stig Petersen, Vedavyas Panneershelvam, Volodymyr Mnih","submitted_at":"2015-07-15T16:56:56Z","abstract_excerpt":"We present the first massively distributed architecture for deep reinforcement learning. This architecture uses four main components: parallel actors that generate new behaviour; parallel learners that are trained from stored experience; a distributed neural network to represent the value function or behaviour policy; and a distributed store of experience. We used our architecture to implement the Deep Q-Network algorithm (DQN). Our distributed algorithm was applied to 49 games from Atari 2600 games from the Arcade Learning Environment, using identical hyperparameters. Our performance surpasse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.04296","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":"2026-05-18T01:36:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ylkDYzeloX+MFByZ3t/tClnoHG+DYT3Gp1ZgQa4CYWT2GWvK4Uu/NDN8cBv2tlAMpPMgmpvwWeWQxy/CqEq0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:46:06.461303Z"},"content_sha256":"582bea34b8877e0a8d44b74c68439993016c2fc494317cdfd325323932456168","schema_version":"1.0","event_id":"sha256:582bea34b8877e0a8d44b74c68439993016c2fc494317cdfd325323932456168"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J54V66PV4EU2EQ6MTQFOGSDHNT/bundle.json","state_url":"https://pith.science/pith/J54V66PV4EU2EQ6MTQFOGSDHNT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J54V66PV4EU2EQ6MTQFOGSDHNT/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":"2026-05-26T19:46:06Z","links":{"resolver":"https://pith.science/pith/J54V66PV4EU2EQ6MTQFOGSDHNT","bundle":"https://pith.science/pith/J54V66PV4EU2EQ6MTQFOGSDHNT/bundle.json","state":"https://pith.science/pith/J54V66PV4EU2EQ6MTQFOGSDHNT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J54V66PV4EU2EQ6MTQFOGSDHNT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:J54V66PV4EU2EQ6MTQFOGSDHNT","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":"bde7497031978bf24896d5e912566ba5bdb6ad59fdff3e8a60d6f753dd0b105b","cross_cats_sorted":["cs.AI","cs.DC","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-15T16:56:56Z","title_canon_sha256":"239ac75310d89dc45e0e22c98bb581b363f6174d72a5a6e47c58caacca508962"},"schema_version":"1.0","source":{"id":"1507.04296","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.04296","created_at":"2026-05-18T01:36:47Z"},{"alias_kind":"arxiv_version","alias_value":"1507.04296v2","created_at":"2026-05-18T01:36:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.04296","created_at":"2026-05-18T01:36:47Z"},{"alias_kind":"pith_short_12","alias_value":"J54V66PV4EU2","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"J54V66PV4EU2EQ6M","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"J54V66PV","created_at":"2026-05-18T12:29:27Z"}],"graph_snapshots":[{"event_id":"sha256:582bea34b8877e0a8d44b74c68439993016c2fc494317cdfd325323932456168","target":"graph","created_at":"2026-05-18T01:36:47Z","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":"We present the first massively distributed architecture for deep reinforcement learning. This architecture uses four main components: parallel actors that generate new behaviour; parallel learners that are trained from stored experience; a distributed neural network to represent the value function or behaviour policy; and a distributed store of experience. We used our architecture to implement the Deep Q-Network algorithm (DQN). Our distributed algorithm was applied to 49 games from Atari 2600 games from the Arcade Learning Environment, using identical hyperparameters. Our performance surpasse","authors_text":"Alessandro De Maria, Arun Nair, Cagdas Alcicek, Charles Beattie, David Silver, Koray Kavukcuoglu, Mustafa Suleyman, Praveen Srinivasan, Rory Fearon, Sam Blackwell, Shane Legg, Stig Petersen, Vedavyas Panneershelvam, Volodymyr Mnih","cross_cats":["cs.AI","cs.DC","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-15T16:56:56Z","title":"Massively Parallel Methods for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.04296","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":"sha256:944fb9fecef9762d6688660e1d1b79d456b85a305cc64dc0417fd44d3a90a7ba","target":"record","created_at":"2026-05-18T01:36:47Z","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":"bde7497031978bf24896d5e912566ba5bdb6ad59fdff3e8a60d6f753dd0b105b","cross_cats_sorted":["cs.AI","cs.DC","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-15T16:56:56Z","title_canon_sha256":"239ac75310d89dc45e0e22c98bb581b363f6174d72a5a6e47c58caacca508962"},"schema_version":"1.0","source":{"id":"1507.04296","kind":"arxiv","version":2}},"canonical_sha256":"4f795f79f5e129a243cc9c0ae348676cfcdb594908651849f8e5076faf8bff91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f795f79f5e129a243cc9c0ae348676cfcdb594908651849f8e5076faf8bff91","first_computed_at":"2026-05-18T01:36:47.626824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:36:47.626824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QDgzGyB0uZSPo9vwXHkua817kxn/T9IDGjjliQj5zQIL/zCNd56x7Sb57Fj3IkvYyqw4WwNPuCVTESWjka1QDg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:36:47.627487Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.04296","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:944fb9fecef9762d6688660e1d1b79d456b85a305cc64dc0417fd44d3a90a7ba","sha256:582bea34b8877e0a8d44b74c68439993016c2fc494317cdfd325323932456168"],"state_sha256":"3cad6ed59478e120d731002474fa9a907571b860e3dddf478bbae39b63ced44a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fyT/DqMZ2c9WBxo0Wyny9u03GMpeu+M2y2+xOb+zhlumzOJwzLupVZ/t9wpz26vd7KVs7LWoo+jY+uO57HTcCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T19:46:06.463379Z","bundle_sha256":"155ca2ee7f9cbd40015be664f61d4ea90198f2209d62d49826bb0bb9e66e7913"}}