{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DAEE52BJGFTEB46IEXEW3NRXAY","short_pith_number":"pith:DAEE52BJ","schema_version":"1.0","canonical_sha256":"18084ee829316640f3c825c96db637062c2e17bb9e7b5e1e732a9109cc40270c","source":{"kind":"arxiv","id":"2306.16688","version":3},"attestation_state":"computed","paper":{"title":"SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DC","authors_text":"Guangju Wang, Huanchen Zhang, Jiaxuan Gao, Wei Fu, Yi Wu, Zhiyu Mei","submitted_at":"2023-06-29T05:16:25Z","abstract_excerpt":"The ever-growing complexity of reinforcement learning (RL) tasks demands a distributed system to efficiently generate and process a massive amount of data. However, existing open-source libraries suffer from various limitations, which impede their practical use in challenging scenarios where large-scale training is necessary. In this paper, we present a novel abstraction on the dataflows of RL training, which unifies diverse RL training applications into a general framework. Following this abstraction, we develop a scalable, efficient, and extensible distributed RL system called ReaLlyScalable"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2306.16688","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-06-29T05:16:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"852a3aa412c3672ed6750c0040ca61be7e5f1088bf696088469579c65c4be4a2","abstract_canon_sha256":"54087a525b3d7501e8b4b62d4b9456474836113fc807dcfe460ac5b2dace9e8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:55.362239Z","signature_b64":"sR4EnPdBNbI3FyUB6F5Lrfgpznv7YQjHH+Urlwxs8UL9GKb2/H28nKCvdNBVMuPLJNWnMNizGVzDB5oum+KfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18084ee829316640f3c825c96db637062c2e17bb9e7b5e1e732a9109cc40270c","last_reissued_at":"2026-07-05T08:34:55.361817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:55.361817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DC","authors_text":"Guangju Wang, Huanchen Zhang, Jiaxuan Gao, Wei Fu, Yi Wu, Zhiyu Mei","submitted_at":"2023-06-29T05:16:25Z","abstract_excerpt":"The ever-growing complexity of reinforcement learning (RL) tasks demands a distributed system to efficiently generate and process a massive amount of data. However, existing open-source libraries suffer from various limitations, which impede their practical use in challenging scenarios where large-scale training is necessary. In this paper, we present a novel abstraction on the dataflows of RL training, which unifies diverse RL training applications into a general framework. Following this abstraction, we develop a scalable, efficient, and extensible distributed RL system called ReaLlyScalable"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16688","kind":"arxiv","version":3},"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/2306.16688/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.16688","created_at":"2026-07-05T08:34:55.361872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.16688v3","created_at":"2026-07-05T08:34:55.361872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16688","created_at":"2026-07-05T08:34:55.361872+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAEE52BJGFTE","created_at":"2026-07-05T08:34:55.361872+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAEE52BJGFTEB46I","created_at":"2026-07-05T08:34:55.361872+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAEE52BJ","created_at":"2026-07-05T08:34:55.361872+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DAEE52BJGFTEB46IEXEW3NRXAY","json":"https://pith.science/pith/DAEE52BJGFTEB46IEXEW3NRXAY.json","graph_json":"https://pith.science/api/pith-number/DAEE52BJGFTEB46IEXEW3NRXAY/graph.json","events_json":"https://pith.science/api/pith-number/DAEE52BJGFTEB46IEXEW3NRXAY/events.json","paper":"https://pith.science/paper/DAEE52BJ"},"agent_actions":{"view_html":"https://pith.science/pith/DAEE52BJGFTEB46IEXEW3NRXAY","download_json":"https://pith.science/pith/DAEE52BJGFTEB46IEXEW3NRXAY.json","view_paper":"https://pith.science/paper/DAEE52BJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.16688&json=true","fetch_graph":"https://pith.science/api/pith-number/DAEE52BJGFTEB46IEXEW3NRXAY/graph.json","fetch_events":"https://pith.science/api/pith-number/DAEE52BJGFTEB46IEXEW3NRXAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAEE52BJGFTEB46IEXEW3NRXAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAEE52BJGFTEB46IEXEW3NRXAY/action/storage_attestation","attest_author":"https://pith.science/pith/DAEE52BJGFTEB46IEXEW3NRXAY/action/author_attestation","sign_citation":"https://pith.science/pith/DAEE52BJGFTEB46IEXEW3NRXAY/action/citation_signature","submit_replication":"https://pith.science/pith/DAEE52BJGFTEB46IEXEW3NRXAY/action/replication_record"}},"created_at":"2026-07-05T08:34:55.361872+00:00","updated_at":"2026-07-05T08:34:55.361872+00:00"}