{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QU4R2H375VV2M3UHY4ZHBIR4TT","short_pith_number":"pith:QU4R2H37","canonical_record":{"source":{"id":"1910.01055","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-02T16:22:29Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"e06a2f774ad0d49015b1d5739e17acfa888ac1ed103c63e59ed9e304e39e0ca9","abstract_canon_sha256":"5d6e4564601f9fdb0df5fb9e9d36d2b092785d69fb117055b6f302a70e74252f"},"schema_version":"1.0"},"canonical_sha256":"85391d1f7fed6ba66e87c73270a23c9cf04bb9bbed7b5c6f0fe38dec74e80934","source":{"kind":"arxiv","id":"1910.01055","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.01055","created_at":"2026-07-05T05:15:33Z"},{"alias_kind":"arxiv_version","alias_value":"1910.01055v6","created_at":"2026-07-05T05:15:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.01055","created_at":"2026-07-05T05:15:33Z"},{"alias_kind":"pith_short_12","alias_value":"QU4R2H375VV2","created_at":"2026-07-05T05:15:33Z"},{"alias_kind":"pith_short_16","alias_value":"QU4R2H375VV2M3UH","created_at":"2026-07-05T05:15:33Z"},{"alias_kind":"pith_short_8","alias_value":"QU4R2H37","created_at":"2026-07-05T05:15:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QU4R2H375VV2M3UHY4ZHBIR4TT","target":"record","payload":{"canonical_record":{"source":{"id":"1910.01055","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-02T16:22:29Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"e06a2f774ad0d49015b1d5739e17acfa888ac1ed103c63e59ed9e304e39e0ca9","abstract_canon_sha256":"5d6e4564601f9fdb0df5fb9e9d36d2b092785d69fb117055b6f302a70e74252f"},"schema_version":"1.0"},"canonical_sha256":"85391d1f7fed6ba66e87c73270a23c9cf04bb9bbed7b5c6f0fe38dec74e80934","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:33.081845Z","signature_b64":"lIpEEQm8LwMxj7Tv41P3te26nzZPBPvDtZLHtoI0H7/7aujXwNccXKOs9BJXce/NUX6E/7Ta/dXz3+9hh9FrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85391d1f7fed6ba66e87c73270a23c9cf04bb9bbed7b5c6f0fe38dec74e80934","last_reissued_at":"2026-07-05T05:15:33.081320Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:33.081320Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.01055","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:15:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qNp4lLN25kNv/4zb/cpm6EOXM/gCD5tV/LOUukCJsl4fiNkRcrGLz/H3ET6gfQkRNGDXS3dgPIr6RGA3eIN8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:44:43.190221Z"},"content_sha256":"e48fd1d7c83aeca5610b91e92c8f2a65093883120090bbf0bc4a7d0e4f0a320d","schema_version":"1.0","event_id":"sha256:e48fd1d7c83aeca5610b91e92c8f2a65093883120090bbf0bc4a7d0e4f0a320d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QU4R2H375VV2M3UHY4ZHBIR4TT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"QuaRL: Quantization for Fast and Environmentally Sustainable Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Aleksandra Faust, Gabriel Barth-Maron, Maximilian Lam, Sharad Chitlangia, Srivatsan Krishnan, Vijay Janapa Reddi, Zishen Wan","submitted_at":"2019-10-02T16:22:29Z","abstract_excerpt":"Deep reinforcement learning continues to show tremendous potential in achieving task-level autonomy, however, its computational and energy demands remain prohibitively high. In this paper, we tackle this problem by applying quantization to reinforcement learning. To that end, we introduce a novel Reinforcement Learning (RL) training paradigm, \\textit{ActorQ}, to speed up actor-learner distributed RL training. \\textit{ActorQ} leverages 8-bit quantized actors to speed up data collection without affecting learning convergence. Our quantized distributed RL training system, \\textit{ActorQ}, demonst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.01055","kind":"arxiv","version":6},"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/1910.01055/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":"2026-07-05T05:15:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1SfH6yIPVaJ656woqyn4au+pMkTLYDFJuC479Xy3BUHPp3trK6UnKKK2i4NRvy90PmgeXLWhfOBankTAORwtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:44:43.190741Z"},"content_sha256":"ecaece86e855d1ffbf200cfdb69606bffa10adf24d4fc5bd1c0fcfa5757bf800","schema_version":"1.0","event_id":"sha256:ecaece86e855d1ffbf200cfdb69606bffa10adf24d4fc5bd1c0fcfa5757bf800"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QU4R2H375VV2M3UHY4ZHBIR4TT/bundle.json","state_url":"https://pith.science/pith/QU4R2H375VV2M3UHY4ZHBIR4TT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QU4R2H375VV2M3UHY4ZHBIR4TT/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":"2026-08-18T11:44:43Z","links":{"resolver":"https://pith.science/pith/QU4R2H375VV2M3UHY4ZHBIR4TT","bundle":"https://pith.science/pith/QU4R2H375VV2M3UHY4ZHBIR4TT/bundle.json","state":"https://pith.science/pith/QU4R2H375VV2M3UHY4ZHBIR4TT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QU4R2H375VV2M3UHY4ZHBIR4TT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QU4R2H375VV2M3UHY4ZHBIR4TT","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":"5d6e4564601f9fdb0df5fb9e9d36d2b092785d69fb117055b6f302a70e74252f","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-02T16:22:29Z","title_canon_sha256":"e06a2f774ad0d49015b1d5739e17acfa888ac1ed103c63e59ed9e304e39e0ca9"},"schema_version":"1.0","source":{"id":"1910.01055","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.01055","created_at":"2026-07-05T05:15:33Z"},{"alias_kind":"arxiv_version","alias_value":"1910.01055v6","created_at":"2026-07-05T05:15:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.01055","created_at":"2026-07-05T05:15:33Z"},{"alias_kind":"pith_short_12","alias_value":"QU4R2H375VV2","created_at":"2026-07-05T05:15:33Z"},{"alias_kind":"pith_short_16","alias_value":"QU4R2H375VV2M3UH","created_at":"2026-07-05T05:15:33Z"},{"alias_kind":"pith_short_8","alias_value":"QU4R2H37","created_at":"2026-07-05T05:15:33Z"}],"graph_snapshots":[{"event_id":"sha256:ecaece86e855d1ffbf200cfdb69606bffa10adf24d4fc5bd1c0fcfa5757bf800","target":"graph","created_at":"2026-07-05T05:15:33Z","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/1910.01055/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning continues to show tremendous potential in achieving task-level autonomy, however, its computational and energy demands remain prohibitively high. In this paper, we tackle this problem by applying quantization to reinforcement learning. To that end, we introduce a novel Reinforcement Learning (RL) training paradigm, \\textit{ActorQ}, to speed up actor-learner distributed RL training. \\textit{ActorQ} leverages 8-bit quantized actors to speed up data collection without affecting learning convergence. Our quantized distributed RL training system, \\textit{ActorQ}, demonst","authors_text":"Aleksandra Faust, Gabriel Barth-Maron, Maximilian Lam, Sharad Chitlangia, Srivatsan Krishnan, Vijay Janapa Reddi, Zishen Wan","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-02T16:22:29Z","title":"QuaRL: Quantization for Fast and Environmentally Sustainable Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.01055","kind":"arxiv","version":6},"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:e48fd1d7c83aeca5610b91e92c8f2a65093883120090bbf0bc4a7d0e4f0a320d","target":"record","created_at":"2026-07-05T05:15:33Z","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":"5d6e4564601f9fdb0df5fb9e9d36d2b092785d69fb117055b6f302a70e74252f","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-02T16:22:29Z","title_canon_sha256":"e06a2f774ad0d49015b1d5739e17acfa888ac1ed103c63e59ed9e304e39e0ca9"},"schema_version":"1.0","source":{"id":"1910.01055","kind":"arxiv","version":6}},"canonical_sha256":"85391d1f7fed6ba66e87c73270a23c9cf04bb9bbed7b5c6f0fe38dec74e80934","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85391d1f7fed6ba66e87c73270a23c9cf04bb9bbed7b5c6f0fe38dec74e80934","first_computed_at":"2026-07-05T05:15:33.081320Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:33.081320Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lIpEEQm8LwMxj7Tv41P3te26nzZPBPvDtZLHtoI0H7/7aujXwNccXKOs9BJXce/NUX6E/7Ta/dXz3+9hh9FrCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:33.081845Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.01055","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e48fd1d7c83aeca5610b91e92c8f2a65093883120090bbf0bc4a7d0e4f0a320d","sha256:ecaece86e855d1ffbf200cfdb69606bffa10adf24d4fc5bd1c0fcfa5757bf800"],"state_sha256":"c75534e2dc6077fffa0ad101871d593418c2eb8a27812da9dee1f5d914d92a5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JVVhxr4+DUk2TQBrEWtG8EZ0kSNuMVn2eJYYGcE1n1NCvl2cU79rnT7saFerUSofthU6a7RjtE/l9kMSKXfzDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T11:44:43.194624Z","bundle_sha256":"98a8a990941449da21e0467c51806dfcd62546634fe948b2366f3a438adb09d5"}}