{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:27GMHLQBN2APYZG2O2V3ADLHQH","short_pith_number":"pith:27GMHLQB","canonical_record":{"source":{"id":"1910.06591","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-10-15T08:32:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5984f47e2c40a1660128c981ce535b5993d2694347299ca62dab910d5a61621a","abstract_canon_sha256":"6a0238353fad412e2d54f046053ee512ce6e5b10dbf2d2d9dcfb300beb4c2b14"},"schema_version":"1.0"},"canonical_sha256":"d7ccc3ae016e80fc64da76abb00d6781c6d0ac3264719ad44d0e617ac3dcab52","source":{"kind":"arxiv","id":"1910.06591","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.06591","created_at":"2026-07-05T00:39:39Z"},{"alias_kind":"arxiv_version","alias_value":"1910.06591v2","created_at":"2026-07-05T00:39:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.06591","created_at":"2026-07-05T00:39:39Z"},{"alias_kind":"pith_short_12","alias_value":"27GMHLQBN2AP","created_at":"2026-07-05T00:39:39Z"},{"alias_kind":"pith_short_16","alias_value":"27GMHLQBN2APYZG2","created_at":"2026-07-05T00:39:39Z"},{"alias_kind":"pith_short_8","alias_value":"27GMHLQB","created_at":"2026-07-05T00:39:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:27GMHLQBN2APYZG2O2V3ADLHQH","target":"record","payload":{"canonical_record":{"source":{"id":"1910.06591","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-10-15T08:32:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5984f47e2c40a1660128c981ce535b5993d2694347299ca62dab910d5a61621a","abstract_canon_sha256":"6a0238353fad412e2d54f046053ee512ce6e5b10dbf2d2d9dcfb300beb4c2b14"},"schema_version":"1.0"},"canonical_sha256":"d7ccc3ae016e80fc64da76abb00d6781c6d0ac3264719ad44d0e617ac3dcab52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:39:39.021656Z","signature_b64":"/UJyAwC/NtBHsqblMZz9ZBgvAIYLAbFerps2vnPQk5yZojWtLF+KvRuHCvqLc0E6YVEvaMAk8CkYD1B5SdKhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7ccc3ae016e80fc64da76abb00d6781c6d0ac3264719ad44d0e617ac3dcab52","last_reissued_at":"2026-07-05T00:39:39.021125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:39:39.021125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.06591","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":"2026-07-05T00:39:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"On5sAtqvH3XBMHPCr3GaX779uYCSZt0O49YjrWYxoNGHUdwgKNdcrCuJ9c8ID2xmKTHEwHw+baEoGJnGwdGRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:02:53.137690Z"},"content_sha256":"5bd8f366a23f2f5b1f92b92179685edfbe506996e94d6698ba86005062f79f3d","schema_version":"1.0","event_id":"sha256:5bd8f366a23f2f5b1f92b92179685edfbe506996e94d6698ba86005062f79f3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:27GMHLQBN2APYZG2O2V3ADLHQH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ke Wang, Lasse Espeholt, Marcin Michalski, Piotr Stanczyk, Rapha\\\"el Marinier","submitted_at":"2019-10-15T08:32:45Z","abstract_excerpt":"We present a modern scalable reinforcement learning agent called SEED (Scalable, Efficient Deep-RL). By effectively utilizing modern accelerators, we show that it is not only possible to train on millions of frames per second but also to lower the cost of experiments compared to current methods. We achieve this with a simple architecture that features centralized inference and an optimized communication layer. SEED adopts two state of the art distributed algorithms, IMPALA/V-trace (policy gradients) and R2D2 (Q-learning), and is evaluated on Atari-57, DeepMind Lab and Google Research Football."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.06591","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.06591/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:39:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZXMm/uRSnaLQxzoQXYBQrUloWMPx6RZhKylbcdKYKsL3ZoIM9VeJSGQ/qSi/mwNfkzyIEFhSJ9LDvfBPZ54EAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:02:53.138051Z"},"content_sha256":"725fed8a08adf85b5e596c1dd26770ea3e741578b887d8f2c47e7ea4fb874b5b","schema_version":"1.0","event_id":"sha256:725fed8a08adf85b5e596c1dd26770ea3e741578b887d8f2c47e7ea4fb874b5b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/27GMHLQBN2APYZG2O2V3ADLHQH/bundle.json","state_url":"https://pith.science/pith/27GMHLQBN2APYZG2O2V3ADLHQH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/27GMHLQBN2APYZG2O2V3ADLHQH/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":"2026-07-05T09:02:53Z","links":{"resolver":"https://pith.science/pith/27GMHLQBN2APYZG2O2V3ADLHQH","bundle":"https://pith.science/pith/27GMHLQBN2APYZG2O2V3ADLHQH/bundle.json","state":"https://pith.science/pith/27GMHLQBN2APYZG2O2V3ADLHQH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/27GMHLQBN2APYZG2O2V3ADLHQH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:27GMHLQBN2APYZG2O2V3ADLHQH","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":"6a0238353fad412e2d54f046053ee512ce6e5b10dbf2d2d9dcfb300beb4c2b14","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-10-15T08:32:45Z","title_canon_sha256":"5984f47e2c40a1660128c981ce535b5993d2694347299ca62dab910d5a61621a"},"schema_version":"1.0","source":{"id":"1910.06591","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.06591","created_at":"2026-07-05T00:39:39Z"},{"alias_kind":"arxiv_version","alias_value":"1910.06591v2","created_at":"2026-07-05T00:39:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.06591","created_at":"2026-07-05T00:39:39Z"},{"alias_kind":"pith_short_12","alias_value":"27GMHLQBN2AP","created_at":"2026-07-05T00:39:39Z"},{"alias_kind":"pith_short_16","alias_value":"27GMHLQBN2APYZG2","created_at":"2026-07-05T00:39:39Z"},{"alias_kind":"pith_short_8","alias_value":"27GMHLQB","created_at":"2026-07-05T00:39:39Z"}],"graph_snapshots":[{"event_id":"sha256:725fed8a08adf85b5e596c1dd26770ea3e741578b887d8f2c47e7ea4fb874b5b","target":"graph","created_at":"2026-07-05T00:39:39Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1910.06591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a modern scalable reinforcement learning agent called SEED (Scalable, Efficient Deep-RL). By effectively utilizing modern accelerators, we show that it is not only possible to train on millions of frames per second but also to lower the cost of experiments compared to current methods. We achieve this with a simple architecture that features centralized inference and an optimized communication layer. SEED adopts two state of the art distributed algorithms, IMPALA/V-trace (policy gradients) and R2D2 (Q-learning), and is evaluated on Atari-57, DeepMind Lab and Google Research Football.","authors_text":"Ke Wang, Lasse Espeholt, Marcin Michalski, Piotr Stanczyk, Rapha\\\"el Marinier","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-10-15T08:32:45Z","title":"SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.06591","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":"sha256:5bd8f366a23f2f5b1f92b92179685edfbe506996e94d6698ba86005062f79f3d","target":"record","created_at":"2026-07-05T00:39:39Z","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":"6a0238353fad412e2d54f046053ee512ce6e5b10dbf2d2d9dcfb300beb4c2b14","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-10-15T08:32:45Z","title_canon_sha256":"5984f47e2c40a1660128c981ce535b5993d2694347299ca62dab910d5a61621a"},"schema_version":"1.0","source":{"id":"1910.06591","kind":"arxiv","version":2}},"canonical_sha256":"d7ccc3ae016e80fc64da76abb00d6781c6d0ac3264719ad44d0e617ac3dcab52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7ccc3ae016e80fc64da76abb00d6781c6d0ac3264719ad44d0e617ac3dcab52","first_computed_at":"2026-07-05T00:39:39.021125Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:39:39.021125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/UJyAwC/NtBHsqblMZz9ZBgvAIYLAbFerps2vnPQk5yZojWtLF+KvRuHCvqLc0E6YVEvaMAk8CkYD1B5SdKhCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:39:39.021656Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.06591","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bd8f366a23f2f5b1f92b92179685edfbe506996e94d6698ba86005062f79f3d","sha256:725fed8a08adf85b5e596c1dd26770ea3e741578b887d8f2c47e7ea4fb874b5b"],"state_sha256":"2aca5b396e68c6d71b0e0e61026a225beb80b391f1327455f6dd4cde01dd279d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RgbvrpeYGO+43rRWJAtmE7LLurxi/yQfJgJN4uHoUdwLwsDYb4/OQbkKYeBTyKmROPfLvwFEYdyj4aOY9lIHCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T09:02:53.139816Z","bundle_sha256":"22dbf200e517ddcdbc8582a63334a4231acbf70766b31c8e6d37f2ab2f4dee26"}}