{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NOR3RKEX24VKEEP6BUZLVBKCJW","short_pith_number":"pith:NOR3RKEX","canonical_record":{"source":{"id":"2104.01655","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-04T17:56:34Z","cross_cats_sorted":[],"title_canon_sha256":"ee6c060ac714c012232e04819620e63c7f8c391d1efc17cbd111d3b35360c0bf","abstract_canon_sha256":"d452a5dd6231572054bb270cdd34538686c11c12799f163b5b1d4ef0b8d26f1b"},"schema_version":"1.0"},"canonical_sha256":"6ba3b8a897d72aa211fe0d32ba85424db085ed9fcf8eb6665569609ed2ce9786","source":{"kind":"arxiv","id":"2104.01655","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.01655","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"arxiv_version","alias_value":"2104.01655v1","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01655","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"pith_short_12","alias_value":"NOR3RKEX24VK","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"NOR3RKEX24VKEEP6","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"NOR3RKEX","created_at":"2026-07-05T02:29:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NOR3RKEX24VKEEP6BUZLVBKCJW","target":"record","payload":{"canonical_record":{"source":{"id":"2104.01655","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-04T17:56:34Z","cross_cats_sorted":[],"title_canon_sha256":"ee6c060ac714c012232e04819620e63c7f8c391d1efc17cbd111d3b35360c0bf","abstract_canon_sha256":"d452a5dd6231572054bb270cdd34538686c11c12799f163b5b1d4ef0b8d26f1b"},"schema_version":"1.0"},"canonical_sha256":"6ba3b8a897d72aa211fe0d32ba85424db085ed9fcf8eb6665569609ed2ce9786","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:02.310227Z","signature_b64":"38E6s6odMlqv0D/BnPguKHryNID0W1IF0atRU+8yYUZf0f1bAR777IXr0pjq4oUhjLgs7d65OdwrD4I4j3IJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ba3b8a897d72aa211fe0d32ba85424db085ed9fcf8eb6665569609ed2ce9786","last_reissued_at":"2026-07-05T02:29:02.309865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:02.309865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.01655","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:29:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mevr69IlY39sF2DefgOVPVc4zHVzNPWwM25C4OLRZhlLfPMljDgEAhnCxacnx5288To3tRpGsQSsYFWo+sj0Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:59:42.617846Z"},"content_sha256":"62a1dbfe29cb7e19637bbd7bfc95ea353b7040c910f743922fa6a51221f0fdab","schema_version":"1.0","event_id":"sha256:62a1dbfe29cb7e19637bbd7bfc95ea353b7040c910f743922fa6a51221f0fdab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NOR3RKEX24VKEEP6BUZLVBKCJW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Emilio Parisotto, Ruslan Salakhutdinov","submitted_at":"2021-04-04T17:56:34Z","abstract_excerpt":"Many real-world applications such as robotics provide hard constraints on power and compute that limit the viable model complexity of Reinforcement Learning (RL) agents. Similarly, in many distributed RL settings, acting is done on un-accelerated hardware such as CPUs, which likewise restricts model size to prevent intractable experiment run times. These \"actor-latency\" constrained settings present a major obstruction to the scaling up of model complexity that has recently been extremely successful in supervised learning. To be able to utilize large model capacity while still operating within "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01655","kind":"arxiv","version":1},"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/2104.01655/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":"2026-07-05T02:29:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zhzvPas/MCe3iWJbAlwtbCls5oCn+/UBInaByoObFBxtn847i4QD3YI+hiW1+yWpmy3CFbwyVgV8qnkQL/sxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:59:42.618845Z"},"content_sha256":"9a3fcbb6896c49fd7968dfbf2286420b699b2ee1f675bf7bf3ce476d8c507774","schema_version":"1.0","event_id":"sha256:9a3fcbb6896c49fd7968dfbf2286420b699b2ee1f675bf7bf3ce476d8c507774"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NOR3RKEX24VKEEP6BUZLVBKCJW/bundle.json","state_url":"https://pith.science/pith/NOR3RKEX24VKEEP6BUZLVBKCJW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NOR3RKEX24VKEEP6BUZLVBKCJW/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":"2026-08-07T15:59:42Z","links":{"resolver":"https://pith.science/pith/NOR3RKEX24VKEEP6BUZLVBKCJW","bundle":"https://pith.science/pith/NOR3RKEX24VKEEP6BUZLVBKCJW/bundle.json","state":"https://pith.science/pith/NOR3RKEX24VKEEP6BUZLVBKCJW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NOR3RKEX24VKEEP6BUZLVBKCJW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NOR3RKEX24VKEEP6BUZLVBKCJW","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":"d452a5dd6231572054bb270cdd34538686c11c12799f163b5b1d4ef0b8d26f1b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-04T17:56:34Z","title_canon_sha256":"ee6c060ac714c012232e04819620e63c7f8c391d1efc17cbd111d3b35360c0bf"},"schema_version":"1.0","source":{"id":"2104.01655","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.01655","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"arxiv_version","alias_value":"2104.01655v1","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01655","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"pith_short_12","alias_value":"NOR3RKEX24VK","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"NOR3RKEX24VKEEP6","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"NOR3RKEX","created_at":"2026-07-05T02:29:02Z"}],"graph_snapshots":[{"event_id":"sha256:9a3fcbb6896c49fd7968dfbf2286420b699b2ee1f675bf7bf3ce476d8c507774","target":"graph","created_at":"2026-07-05T02:29:02Z","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/2104.01655/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many real-world applications such as robotics provide hard constraints on power and compute that limit the viable model complexity of Reinforcement Learning (RL) agents. Similarly, in many distributed RL settings, acting is done on un-accelerated hardware such as CPUs, which likewise restricts model size to prevent intractable experiment run times. These \"actor-latency\" constrained settings present a major obstruction to the scaling up of model complexity that has recently been extremely successful in supervised learning. To be able to utilize large model capacity while still operating within ","authors_text":"Emilio Parisotto, Ruslan Salakhutdinov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-04T17:56:34Z","title":"Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01655","kind":"arxiv","version":1},"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":"sha256:62a1dbfe29cb7e19637bbd7bfc95ea353b7040c910f743922fa6a51221f0fdab","target":"record","created_at":"2026-07-05T02:29:02Z","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":"d452a5dd6231572054bb270cdd34538686c11c12799f163b5b1d4ef0b8d26f1b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-04T17:56:34Z","title_canon_sha256":"ee6c060ac714c012232e04819620e63c7f8c391d1efc17cbd111d3b35360c0bf"},"schema_version":"1.0","source":{"id":"2104.01655","kind":"arxiv","version":1}},"canonical_sha256":"6ba3b8a897d72aa211fe0d32ba85424db085ed9fcf8eb6665569609ed2ce9786","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ba3b8a897d72aa211fe0d32ba85424db085ed9fcf8eb6665569609ed2ce9786","first_computed_at":"2026-07-05T02:29:02.309865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:29:02.309865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"38E6s6odMlqv0D/BnPguKHryNID0W1IF0atRU+8yYUZf0f1bAR777IXr0pjq4oUhjLgs7d65OdwrD4I4j3IJAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:29:02.310227Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.01655","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62a1dbfe29cb7e19637bbd7bfc95ea353b7040c910f743922fa6a51221f0fdab","sha256:9a3fcbb6896c49fd7968dfbf2286420b699b2ee1f675bf7bf3ce476d8c507774"],"state_sha256":"bdd1fb00ef97655752e8ada663c0098f9d4b3578f28915eb79f45ad8e83d8953"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qb3NFxxW+24ANMGALjWK/5vLIkWAjIEn+hx1fRmkuwhNJjp6N0qSmlm4h05em5Pv38M5NxCuGmVfNEjKkLpEAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:59:42.677587Z","bundle_sha256":"7534c05ddce157c51abb406fd14bb5d2501c11877298dd34cb6ad4a9287a6bbd"}}