{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FSC52N3ZHRVZZTHXPP7PRCZ2HL","short_pith_number":"pith:FSC52N3Z","canonical_record":{"source":{"id":"2605.16318","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T22:18:05Z","cross_cats_sorted":[],"title_canon_sha256":"84f566658af9e869be9c6f7be4ba6aea696b54980e0843c7fda03e9e2484ba5c","abstract_canon_sha256":"7e34bcf283186585db78c346d881f7b1edce0b84fb9aa030c54aeed339d6be3e"},"schema_version":"1.0"},"canonical_sha256":"2c85dd37793c6b9cccf77bfef88b3a3afcfa4a376f59adb1299c563c97c19af1","source":{"kind":"arxiv","id":"2605.16318","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16318","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16318v1","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16318","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"pith_short_12","alias_value":"FSC52N3ZHRVZ","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"pith_short_16","alias_value":"FSC52N3ZHRVZZTHX","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"pith_short_8","alias_value":"FSC52N3Z","created_at":"2026-05-20T00:02:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FSC52N3ZHRVZZTHXPP7PRCZ2HL","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16318","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T22:18:05Z","cross_cats_sorted":[],"title_canon_sha256":"84f566658af9e869be9c6f7be4ba6aea696b54980e0843c7fda03e9e2484ba5c","abstract_canon_sha256":"7e34bcf283186585db78c346d881f7b1edce0b84fb9aa030c54aeed339d6be3e"},"schema_version":"1.0"},"canonical_sha256":"2c85dd37793c6b9cccf77bfef88b3a3afcfa4a376f59adb1299c563c97c19af1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:16.712871Z","signature_b64":"Azr8MU3tln7R/tFaGGjMxBu2X5ZtGYTgxffT2lLaOoPMqyaiQdZSMLLo03shNDtdcGumI64CnKlqWfJf162MBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c85dd37793c6b9cccf77bfef88b3a3afcfa4a376f59adb1299c563c97c19af1","last_reissued_at":"2026-05-20T00:02:16.712032Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:16.712032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16318","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":"2026-05-20T00:02:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SvOrFpEEDcDbS53Vd98AC7OdfMrhabfooh7VTC2UfxpdQx/he0Su0lCu1i1AW9Exh9Et5uiMcBp6uvUPvhilAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T17:02:34.489662Z"},"content_sha256":"cc98a13fdce3fe786374ec47dca189e1924d22f759d6d899efa6e8b3deed22fe","schema_version":"1.0","event_id":"sha256:cc98a13fdce3fe786374ec47dca189e1924d22f759d6d899efa6e8b3deed22fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FSC52N3ZHRVZZTHXPP7PRCZ2HL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam White, Martha White, Matthew Schlegel, Volodymyr Tkachuk","submitted_at":"2026-05-04T22:18:05Z","abstract_excerpt":"Building and maintaining state to learn policies and value functions is critical for deploying reinforcement learning (RL) agents in the real world. Recurrent neural networks (RNNs) have become a key point of interest for the state-building problem, and several large-scale reinforcement learning agents incorporate recurrent networks. While RNNs have become a mainstay in many RL applications, many key design choices and implementation details responsible for performance improvements are often not reported. In this work, we discuss one axis on which RNN architectures can be (and have been) modif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16318","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/2605.16318/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":"2026-05-20T00:02:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZPH50DHh9Vovsdr50d+E59/WnxcufykIamDcxjXj5UJ8toepu4X9++fTNWmqr+wycDANU5M87YuT1urL9tOIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T17:02:34.490038Z"},"content_sha256":"3e5612ed01662fa4c12ccbebea67eb52e6579c9a9e9ad8c76092927b16c32755","schema_version":"1.0","event_id":"sha256:3e5612ed01662fa4c12ccbebea67eb52e6579c9a9e9ad8c76092927b16c32755"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FSC52N3ZHRVZZTHXPP7PRCZ2HL/bundle.json","state_url":"https://pith.science/pith/FSC52N3ZHRVZZTHXPP7PRCZ2HL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FSC52N3ZHRVZZTHXPP7PRCZ2HL/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":"2026-05-21T17:02:34Z","links":{"resolver":"https://pith.science/pith/FSC52N3ZHRVZZTHXPP7PRCZ2HL","bundle":"https://pith.science/pith/FSC52N3ZHRVZZTHXPP7PRCZ2HL/bundle.json","state":"https://pith.science/pith/FSC52N3ZHRVZZTHXPP7PRCZ2HL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FSC52N3ZHRVZZTHXPP7PRCZ2HL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FSC52N3ZHRVZZTHXPP7PRCZ2HL","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":"7e34bcf283186585db78c346d881f7b1edce0b84fb9aa030c54aeed339d6be3e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T22:18:05Z","title_canon_sha256":"84f566658af9e869be9c6f7be4ba6aea696b54980e0843c7fda03e9e2484ba5c"},"schema_version":"1.0","source":{"id":"2605.16318","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16318","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16318v1","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16318","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"pith_short_12","alias_value":"FSC52N3ZHRVZ","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"pith_short_16","alias_value":"FSC52N3ZHRVZZTHX","created_at":"2026-05-20T00:02:16Z"},{"alias_kind":"pith_short_8","alias_value":"FSC52N3Z","created_at":"2026-05-20T00:02:16Z"}],"graph_snapshots":[{"event_id":"sha256:3e5612ed01662fa4c12ccbebea67eb52e6579c9a9e9ad8c76092927b16c32755","target":"graph","created_at":"2026-05-20T00:02:16Z","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/2605.16318/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building and maintaining state to learn policies and value functions is critical for deploying reinforcement learning (RL) agents in the real world. Recurrent neural networks (RNNs) have become a key point of interest for the state-building problem, and several large-scale reinforcement learning agents incorporate recurrent networks. While RNNs have become a mainstay in many RL applications, many key design choices and implementation details responsible for performance improvements are often not reported. In this work, we discuss one axis on which RNN architectures can be (and have been) modif","authors_text":"Adam White, Martha White, Matthew Schlegel, Volodymyr Tkachuk","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T22:18:05Z","title":"Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16318","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:cc98a13fdce3fe786374ec47dca189e1924d22f759d6d899efa6e8b3deed22fe","target":"record","created_at":"2026-05-20T00:02:16Z","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":"7e34bcf283186585db78c346d881f7b1edce0b84fb9aa030c54aeed339d6be3e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T22:18:05Z","title_canon_sha256":"84f566658af9e869be9c6f7be4ba6aea696b54980e0843c7fda03e9e2484ba5c"},"schema_version":"1.0","source":{"id":"2605.16318","kind":"arxiv","version":1}},"canonical_sha256":"2c85dd37793c6b9cccf77bfef88b3a3afcfa4a376f59adb1299c563c97c19af1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c85dd37793c6b9cccf77bfef88b3a3afcfa4a376f59adb1299c563c97c19af1","first_computed_at":"2026-05-20T00:02:16.712032Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:16.712032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Azr8MU3tln7R/tFaGGjMxBu2X5ZtGYTgxffT2lLaOoPMqyaiQdZSMLLo03shNDtdcGumI64CnKlqWfJf162MBw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:16.712871Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16318","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc98a13fdce3fe786374ec47dca189e1924d22f759d6d899efa6e8b3deed22fe","sha256:3e5612ed01662fa4c12ccbebea67eb52e6579c9a9e9ad8c76092927b16c32755"],"state_sha256":"c2701ad4a87d15ba83a80f279f11fe349c6e128a70d597cbbe00ffff5972c0b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eaDMCFm2IUDBISWX9SAGuOadaQdyAyQN4OG2bHTEs2IyZ5+vRpA1tif8mOG6yUHeDfYY24UCfF4P0UfTc95eAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T17:02:34.492235Z","bundle_sha256":"c02f22bba51ce4db36aaf4fdb70dc733efd9c34d4ace1619f1fcd8739ee4886f"}}