{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TRLBGPV3KK2XFA6DXFOYEDJJTJ","short_pith_number":"pith:TRLBGPV3","canonical_record":{"source":{"id":"2110.05038","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T07:09:14Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"ad606edaa6cee0b713ba2e051e4c8457dfe47623089f6fad383b791008c18bd3","abstract_canon_sha256":"bc91bf895cd78a4c1fae0cae70c03eb070540a1640a7ab3e2db59a46ae3256f1"},"schema_version":"1.0"},"canonical_sha256":"9c56133ebb52b57283c3b95d820d299a648b416e55f22bb610d060aa4cddce4b","source":{"kind":"arxiv","id":"2110.05038","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.05038","created_at":"2026-07-05T04:28:52Z"},{"alias_kind":"arxiv_version","alias_value":"2110.05038v3","created_at":"2026-07-05T04:28:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05038","created_at":"2026-07-05T04:28:52Z"},{"alias_kind":"pith_short_12","alias_value":"TRLBGPV3KK2X","created_at":"2026-07-05T04:28:52Z"},{"alias_kind":"pith_short_16","alias_value":"TRLBGPV3KK2XFA6D","created_at":"2026-07-05T04:28:52Z"},{"alias_kind":"pith_short_8","alias_value":"TRLBGPV3","created_at":"2026-07-05T04:28:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TRLBGPV3KK2XFA6DXFOYEDJJTJ","target":"record","payload":{"canonical_record":{"source":{"id":"2110.05038","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T07:09:14Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"ad606edaa6cee0b713ba2e051e4c8457dfe47623089f6fad383b791008c18bd3","abstract_canon_sha256":"bc91bf895cd78a4c1fae0cae70c03eb070540a1640a7ab3e2db59a46ae3256f1"},"schema_version":"1.0"},"canonical_sha256":"9c56133ebb52b57283c3b95d820d299a648b416e55f22bb610d060aa4cddce4b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:52.994837Z","signature_b64":"mnuYgLc+4ArrNBdjnzOqR5iKmcV5vSjdh1XF+z1hfnZbVe2AtnafTPwE9ZR7zR3kG7cwKwwywFPWuefauF2jBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c56133ebb52b57283c3b95d820d299a648b416e55f22bb610d060aa4cddce4b","last_reissued_at":"2026-07-05T04:28:52.994359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:52.994359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.05038","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:28:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z2VaVOiS/gNoO6LT0Qkd3cOJm9hjrx+QGKA0YSpwNHeSji7lAF1UYXO+nmUGmqtW9sG50QTFeAjAQ0YNSh8iDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:11:48.316505Z"},"content_sha256":"42add2dec722181d63aa516ac39355cf17f17dc2a031fc28eeea011a5997dfeb","schema_version":"1.0","event_id":"sha256:42add2dec722181d63aa516ac39355cf17f17dc2a031fc28eeea011a5997dfeb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TRLBGPV3KK2XFA6DXFOYEDJJTJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Ruslan Salakhutdinov, Tianwei Ni","submitted_at":"2021-10-11T07:09:14Z","abstract_excerpt":"Many problems in RL, such as meta-RL, robust RL, generalization in RL, and temporal credit assignment, can be cast as POMDPs. In theory, simply augmenting model-free RL with memory-based architectures, such as recurrent neural networks, provides a general approach to solving all types of POMDPs. However, prior work has found that such recurrent model-free RL methods tend to perform worse than more specialized algorithms that are designed for specific types of POMDPs. This paper revisits this claim. We find that careful architecture and hyperparameter decisions can often yield a recurrent model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05038","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/2110.05038/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":"2026-07-05T04:28:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YE3EhRfaxaNVNJaUFTQpoRQ0kh2dEguHI3+ax41I9Vo8OpzrZt7VZHS8X8TWJIb0g+fth1it50Ko+VwP/I9JBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:11:48.317234Z"},"content_sha256":"3561c6113da97792d4234c311b64c224cec0b17558b51c2ef305dc76941cdfec","schema_version":"1.0","event_id":"sha256:3561c6113da97792d4234c311b64c224cec0b17558b51c2ef305dc76941cdfec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TRLBGPV3KK2XFA6DXFOYEDJJTJ/bundle.json","state_url":"https://pith.science/pith/TRLBGPV3KK2XFA6DXFOYEDJJTJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TRLBGPV3KK2XFA6DXFOYEDJJTJ/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":"2026-08-08T11:11:48Z","links":{"resolver":"https://pith.science/pith/TRLBGPV3KK2XFA6DXFOYEDJJTJ","bundle":"https://pith.science/pith/TRLBGPV3KK2XFA6DXFOYEDJJTJ/bundle.json","state":"https://pith.science/pith/TRLBGPV3KK2XFA6DXFOYEDJJTJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TRLBGPV3KK2XFA6DXFOYEDJJTJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TRLBGPV3KK2XFA6DXFOYEDJJTJ","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":"bc91bf895cd78a4c1fae0cae70c03eb070540a1640a7ab3e2db59a46ae3256f1","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T07:09:14Z","title_canon_sha256":"ad606edaa6cee0b713ba2e051e4c8457dfe47623089f6fad383b791008c18bd3"},"schema_version":"1.0","source":{"id":"2110.05038","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.05038","created_at":"2026-07-05T04:28:52Z"},{"alias_kind":"arxiv_version","alias_value":"2110.05038v3","created_at":"2026-07-05T04:28:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05038","created_at":"2026-07-05T04:28:52Z"},{"alias_kind":"pith_short_12","alias_value":"TRLBGPV3KK2X","created_at":"2026-07-05T04:28:52Z"},{"alias_kind":"pith_short_16","alias_value":"TRLBGPV3KK2XFA6D","created_at":"2026-07-05T04:28:52Z"},{"alias_kind":"pith_short_8","alias_value":"TRLBGPV3","created_at":"2026-07-05T04:28:52Z"}],"graph_snapshots":[{"event_id":"sha256:3561c6113da97792d4234c311b64c224cec0b17558b51c2ef305dc76941cdfec","target":"graph","created_at":"2026-07-05T04:28:52Z","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/2110.05038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many problems in RL, such as meta-RL, robust RL, generalization in RL, and temporal credit assignment, can be cast as POMDPs. In theory, simply augmenting model-free RL with memory-based architectures, such as recurrent neural networks, provides a general approach to solving all types of POMDPs. However, prior work has found that such recurrent model-free RL methods tend to perform worse than more specialized algorithms that are designed for specific types of POMDPs. This paper revisits this claim. We find that careful architecture and hyperparameter decisions can often yield a recurrent model","authors_text":"Benjamin Eysenbach, Ruslan Salakhutdinov, Tianwei Ni","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T07:09:14Z","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05038","kind":"arxiv","version":3},"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":"sha256:42add2dec722181d63aa516ac39355cf17f17dc2a031fc28eeea011a5997dfeb","target":"record","created_at":"2026-07-05T04:28:52Z","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":"bc91bf895cd78a4c1fae0cae70c03eb070540a1640a7ab3e2db59a46ae3256f1","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T07:09:14Z","title_canon_sha256":"ad606edaa6cee0b713ba2e051e4c8457dfe47623089f6fad383b791008c18bd3"},"schema_version":"1.0","source":{"id":"2110.05038","kind":"arxiv","version":3}},"canonical_sha256":"9c56133ebb52b57283c3b95d820d299a648b416e55f22bb610d060aa4cddce4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c56133ebb52b57283c3b95d820d299a648b416e55f22bb610d060aa4cddce4b","first_computed_at":"2026-07-05T04:28:52.994359Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:28:52.994359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mnuYgLc+4ArrNBdjnzOqR5iKmcV5vSjdh1XF+z1hfnZbVe2AtnafTPwE9ZR7zR3kG7cwKwwywFPWuefauF2jBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:28:52.994837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.05038","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42add2dec722181d63aa516ac39355cf17f17dc2a031fc28eeea011a5997dfeb","sha256:3561c6113da97792d4234c311b64c224cec0b17558b51c2ef305dc76941cdfec"],"state_sha256":"f78dcadb44ec68ac35d59b17e901bc9529560b9ff6f35ce98b622645353a2a58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A9enpyP6n58BqO/239C9kZtic28ExwbEbM6eFeGfV2As7RBg767R7cXfTiIztsjh4Jul5e7iKbHIg0qBVv/LAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:11:48.322725Z","bundle_sha256":"fd0319e77e25f2ec410030f334c754ca7e798378fd87e39f59505b6d74bf7afc"}}