{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4GXAGS5VNMNOOBKHSD2XVYKLUK","short_pith_number":"pith:4GXAGS5V","canonical_record":{"source":{"id":"2006.00979","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-01T14:38:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3728a25b97c0e13fddefe6ffd7b65043cc21891a7f25b05d47b662ec0282d141","abstract_canon_sha256":"f415c29859066693f8f3388426b8dd9b8e37f7aefb6c94048fa2d25de393a5bf"},"schema_version":"1.0"},"canonical_sha256":"e1ae034bb56b1ae7054790f57ae14ba2b8857a82710cac8bfdc8e84c9a22440b","source":{"kind":"arxiv","id":"2006.00979","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.00979","created_at":"2026-07-05T04:59:10Z"},{"alias_kind":"arxiv_version","alias_value":"2006.00979v2","created_at":"2026-07-05T04:59:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.00979","created_at":"2026-07-05T04:59:10Z"},{"alias_kind":"pith_short_12","alias_value":"4GXAGS5VNMNO","created_at":"2026-07-05T04:59:10Z"},{"alias_kind":"pith_short_16","alias_value":"4GXAGS5VNMNOOBKH","created_at":"2026-07-05T04:59:10Z"},{"alias_kind":"pith_short_8","alias_value":"4GXAGS5V","created_at":"2026-07-05T04:59:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4GXAGS5VNMNOOBKHSD2XVYKLUK","target":"record","payload":{"canonical_record":{"source":{"id":"2006.00979","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-01T14:38:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3728a25b97c0e13fddefe6ffd7b65043cc21891a7f25b05d47b662ec0282d141","abstract_canon_sha256":"f415c29859066693f8f3388426b8dd9b8e37f7aefb6c94048fa2d25de393a5bf"},"schema_version":"1.0"},"canonical_sha256":"e1ae034bb56b1ae7054790f57ae14ba2b8857a82710cac8bfdc8e84c9a22440b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:59:10.504928Z","signature_b64":"ysWFzH1HMPAXQPPsVhlsKhFVBTXDnekT3tIv0QUDkudTGs7EzBAlEbEBJJNjass+jFqEq/5BQaCSdreb/YkeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1ae034bb56b1ae7054790f57ae14ba2b8857a82710cac8bfdc8e84c9a22440b","last_reissued_at":"2026-07-05T04:59:10.504288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:59:10.504288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.00979","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":"2026-07-05T04:59:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BuemVWcoA3bjr6lZpLM4Zm0Xxmm1mdWIuFbpQ7ZxoYBGifxmoDqgXe4MLNc3evw+f5lIX2SlutrRBEUEjIN0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:32:03.147942Z"},"content_sha256":"84dea38c8aa7b77c8477c6204792d8f9509a826902bb062a1b533e3f0aa1e6c9","schema_version":"1.0","event_id":"sha256:84dea38c8aa7b77c8477c6204792d8f9509a826902bb062a1b533e3f0aa1e6c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4GXAGS5VNMNOOBKHSD2XVYKLUK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Acme: A Research Framework for Distributed Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abbas Abdolmaleki, Abe Friesen, Albin Cassirer, Alexis Jacq, Alex Novikov, Andrew Cowie, Anton Raichuk, Bilal Piot, Bobak Shahriari, Caglar Gulcehre, Damien Vincent, Danila Sinopalnikov, Fan Yang, Feryal Behbahani, Gabriel Barth-Maron, Gabriel Dulac-Arnold, Johan Ferret, John Aslanides, Kate Baumli, L\\'eonard Hussenot, Manu Orsini, Matthew W. Hoffman, Nando de Freitas, Nikola Momchev, Nino Vieillard, Olivier Pietquin, Piotr Sta\\'nczyk, Robert Dadashi, Ruba Haroun, Sabela Ramos, Sarah Henderson, Sergio G\\'omez Colmenarejo, Serkan Cabi, Sertan Girgin, Seyed Kamyar Seyed Ghasemipour, Srivatsan Srinivasan, Tamara Norman, Tom Le Paine, Ziyu Wang","submitted_at":"2020-06-01T14:38:52Z","abstract_excerpt":"Deep reinforcement learning (RL) has led to many recent and groundbreaking advances. However, these advances have often come at the cost of both increased scale in the underlying architectures being trained as well as increased complexity of the RL algorithms used to train them. These increases have in turn made it more difficult for researchers to rapidly prototype new ideas or reproduce published RL algorithms. To address these concerns this work describes Acme, a framework for constructing novel RL algorithms that is specifically designed to enable agents that are built using simple, modula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.00979","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/2006.00979/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":"2026-07-05T04:59:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQbJ4Pywq1oRE0mpJYvs+iocRMWAH5zKnMB23rIS+WHSZ0CEZkeD+p79KKVfaK0Gldz7TVnh6QSNsbHExD+hDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:32:03.148630Z"},"content_sha256":"2ff19e026f7a204224c7c4581db1e31ab27169621ac67bed9c7474d52a5fb573","schema_version":"1.0","event_id":"sha256:2ff19e026f7a204224c7c4581db1e31ab27169621ac67bed9c7474d52a5fb573"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4GXAGS5VNMNOOBKHSD2XVYKLUK/bundle.json","state_url":"https://pith.science/pith/4GXAGS5VNMNOOBKHSD2XVYKLUK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4GXAGS5VNMNOOBKHSD2XVYKLUK/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":"2026-08-18T15:32:03Z","links":{"resolver":"https://pith.science/pith/4GXAGS5VNMNOOBKHSD2XVYKLUK","bundle":"https://pith.science/pith/4GXAGS5VNMNOOBKHSD2XVYKLUK/bundle.json","state":"https://pith.science/pith/4GXAGS5VNMNOOBKHSD2XVYKLUK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4GXAGS5VNMNOOBKHSD2XVYKLUK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4GXAGS5VNMNOOBKHSD2XVYKLUK","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":"f415c29859066693f8f3388426b8dd9b8e37f7aefb6c94048fa2d25de393a5bf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-01T14:38:52Z","title_canon_sha256":"3728a25b97c0e13fddefe6ffd7b65043cc21891a7f25b05d47b662ec0282d141"},"schema_version":"1.0","source":{"id":"2006.00979","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.00979","created_at":"2026-07-05T04:59:10Z"},{"alias_kind":"arxiv_version","alias_value":"2006.00979v2","created_at":"2026-07-05T04:59:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.00979","created_at":"2026-07-05T04:59:10Z"},{"alias_kind":"pith_short_12","alias_value":"4GXAGS5VNMNO","created_at":"2026-07-05T04:59:10Z"},{"alias_kind":"pith_short_16","alias_value":"4GXAGS5VNMNOOBKH","created_at":"2026-07-05T04:59:10Z"},{"alias_kind":"pith_short_8","alias_value":"4GXAGS5V","created_at":"2026-07-05T04:59:10Z"}],"graph_snapshots":[{"event_id":"sha256:2ff19e026f7a204224c7c4581db1e31ab27169621ac67bed9c7474d52a5fb573","target":"graph","created_at":"2026-07-05T04:59:10Z","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/2006.00979/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (RL) has led to many recent and groundbreaking advances. However, these advances have often come at the cost of both increased scale in the underlying architectures being trained as well as increased complexity of the RL algorithms used to train them. These increases have in turn made it more difficult for researchers to rapidly prototype new ideas or reproduce published RL algorithms. To address these concerns this work describes Acme, a framework for constructing novel RL algorithms that is specifically designed to enable agents that are built using simple, modula","authors_text":"Abbas Abdolmaleki, Abe Friesen, Albin Cassirer, Alexis Jacq, Alex Novikov, Andrew Cowie, Anton Raichuk, Bilal Piot, Bobak Shahriari, Caglar Gulcehre, Damien Vincent, Danila Sinopalnikov, Fan Yang, Feryal Behbahani, Gabriel Barth-Maron, Gabriel Dulac-Arnold, Johan Ferret, John Aslanides, Kate Baumli, L\\'eonard Hussenot, Manu Orsini, Matthew W. Hoffman, Nando de Freitas, Nikola Momchev, Nino Vieillard, Olivier Pietquin, Piotr Sta\\'nczyk, Robert Dadashi, Ruba Haroun, Sabela Ramos, Sarah Henderson, Sergio G\\'omez Colmenarejo, Serkan Cabi, Sertan Girgin, Seyed Kamyar Seyed Ghasemipour, Srivatsan Srinivasan, Tamara Norman, Tom Le Paine, Ziyu Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-01T14:38:52Z","title":"Acme: A Research Framework for Distributed Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.00979","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":"sha256:84dea38c8aa7b77c8477c6204792d8f9509a826902bb062a1b533e3f0aa1e6c9","target":"record","created_at":"2026-07-05T04:59:10Z","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":"f415c29859066693f8f3388426b8dd9b8e37f7aefb6c94048fa2d25de393a5bf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-01T14:38:52Z","title_canon_sha256":"3728a25b97c0e13fddefe6ffd7b65043cc21891a7f25b05d47b662ec0282d141"},"schema_version":"1.0","source":{"id":"2006.00979","kind":"arxiv","version":2}},"canonical_sha256":"e1ae034bb56b1ae7054790f57ae14ba2b8857a82710cac8bfdc8e84c9a22440b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1ae034bb56b1ae7054790f57ae14ba2b8857a82710cac8bfdc8e84c9a22440b","first_computed_at":"2026-07-05T04:59:10.504288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:59:10.504288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ysWFzH1HMPAXQPPsVhlsKhFVBTXDnekT3tIv0QUDkudTGs7EzBAlEbEBJJNjass+jFqEq/5BQaCSdreb/YkeDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:59:10.504928Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.00979","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84dea38c8aa7b77c8477c6204792d8f9509a826902bb062a1b533e3f0aa1e6c9","sha256:2ff19e026f7a204224c7c4581db1e31ab27169621ac67bed9c7474d52a5fb573"],"state_sha256":"73fa8c8a27bbc62d0e682c7cccaf3ff986a0d01b0e4e24a4312b261c2f79ef7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KeQgrTxo+2bXy8SV1IYsz18cE72rbs4Po39moA2Dm/xUj+jIy9VILf/NYlU0N3IT0c5eitP2Eq3MIJ8AarOjCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T15:32:03.154329Z","bundle_sha256":"e229c11cbabf455d06dabc2848c45fbee6a74ce08676929bef0d67323ab6b6e9"}}