{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SDLQ6PBFRJOKP2MTXJFDNRTML5","short_pith_number":"pith:SDLQ6PBF","canonical_record":{"source":{"id":"2608.05111","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T17:44:52Z","cross_cats_sorted":[],"title_canon_sha256":"701010c2c040fa1a986a10310f5f3ebf1d64fadc09ecfe2faf1faf5aaf8205f3","abstract_canon_sha256":"32cc30160b53b4147f24c8f29c0ce7e186524fc0d357330d9e20b5bac2538595"},"schema_version":"1.0"},"canonical_sha256":"90d70f3c258a5ca7e993ba4a36c66c5f547f5109e6a74bbd8afc1abf5c3a2068","source":{"kind":"arxiv","id":"2608.05111","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05111","created_at":"2026-08-06T01:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05111v1","created_at":"2026-08-06T01:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05111","created_at":"2026-08-06T01:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"SDLQ6PBFRJOK","created_at":"2026-08-06T01:49:13Z"},{"alias_kind":"pith_short_16","alias_value":"SDLQ6PBFRJOKP2MT","created_at":"2026-08-06T01:49:13Z"},{"alias_kind":"pith_short_8","alias_value":"SDLQ6PBF","created_at":"2026-08-06T01:49:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SDLQ6PBFRJOKP2MTXJFDNRTML5","target":"record","payload":{"canonical_record":{"source":{"id":"2608.05111","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T17:44:52Z","cross_cats_sorted":[],"title_canon_sha256":"701010c2c040fa1a986a10310f5f3ebf1d64fadc09ecfe2faf1faf5aaf8205f3","abstract_canon_sha256":"32cc30160b53b4147f24c8f29c0ce7e186524fc0d357330d9e20b5bac2538595"},"schema_version":"1.0"},"canonical_sha256":"90d70f3c258a5ca7e993ba4a36c66c5f547f5109e6a74bbd8afc1abf5c3a2068","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:49:13.236926Z","signature_b64":"w+oiRswXDjFOprUfzKYNxCIbB9k6dVDvF46LWStgJQ/7hH1p9JgnchwKAiFZtt2egI/LF5lsu8QTxJWD+r91CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90d70f3c258a5ca7e993ba4a36c66c5f547f5109e6a74bbd8afc1abf5c3a2068","last_reissued_at":"2026-08-06T01:49:13.235423Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:49:13.235423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.05111","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":"2026-08-06T01:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X+OA8tDosMq7UexWxn8+ZpwNqMMFzyE6B62/dbSV8qw7pFfLsdfnt1MPWvJdH5L9iuP1Vz5hFc3Ab3MHfNLACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:57:35.175111Z"},"content_sha256":"e42869312bb1e023233bb8f62ba394007f9a515ae51e5df1e4108b110bc486c7","schema_version":"1.0","event_id":"sha256:e42869312bb1e023233bb8f62ba394007f9a515ae51e5df1e4108b110bc486c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SDLQ6PBFRJOKP2MTXJFDNRTML5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward Structure Shapes the Interaction Between Episodic Exploration and Neural Memory in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Henrik I. Christensen, Jai Malegaonkar, Rohan Patil","submitted_at":"2026-08-05T17:44:52Z","abstract_excerpt":"In partially observable reinforcement learning, agents face a dual bottleneck: they must explore to encounter rewarding states and retain that experience in memory to optimize their policies. Exploration bonuses and memory architectures are traditionally evaluated in isolation, leaving their interaction unmeasured, and standard notions of sparse reward conflate temporal signal density with what the reward actually supervises. We present a controlled study crossing episodic exploration bonuses with diverse neural memory architectures across three environments that vary how the content of memory"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05111","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/2608.05111/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":"2026-08-06T01:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eQVO+3QmbUwsOrLtwNsWlw1YJq8Ua9VdC8e8BfV/MLlbtKcSyV4TxbpypYLwu2nfYz8lIoS5n7/FynI4i0bJDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:57:35.175631Z"},"content_sha256":"4481981d18e87f0dae07e99b9f5d99dff085d15f66f1afc26d3e16c8a54985dd","schema_version":"1.0","event_id":"sha256:4481981d18e87f0dae07e99b9f5d99dff085d15f66f1afc26d3e16c8a54985dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SDLQ6PBFRJOKP2MTXJFDNRTML5/bundle.json","state_url":"https://pith.science/pith/SDLQ6PBFRJOKP2MTXJFDNRTML5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SDLQ6PBFRJOKP2MTXJFDNRTML5/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":"2026-08-07T00:57:35Z","links":{"resolver":"https://pith.science/pith/SDLQ6PBFRJOKP2MTXJFDNRTML5","bundle":"https://pith.science/pith/SDLQ6PBFRJOKP2MTXJFDNRTML5/bundle.json","state":"https://pith.science/pith/SDLQ6PBFRJOKP2MTXJFDNRTML5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SDLQ6PBFRJOKP2MTXJFDNRTML5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SDLQ6PBFRJOKP2MTXJFDNRTML5","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":"32cc30160b53b4147f24c8f29c0ce7e186524fc0d357330d9e20b5bac2538595","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T17:44:52Z","title_canon_sha256":"701010c2c040fa1a986a10310f5f3ebf1d64fadc09ecfe2faf1faf5aaf8205f3"},"schema_version":"1.0","source":{"id":"2608.05111","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05111","created_at":"2026-08-06T01:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05111v1","created_at":"2026-08-06T01:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05111","created_at":"2026-08-06T01:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"SDLQ6PBFRJOK","created_at":"2026-08-06T01:49:13Z"},{"alias_kind":"pith_short_16","alias_value":"SDLQ6PBFRJOKP2MT","created_at":"2026-08-06T01:49:13Z"},{"alias_kind":"pith_short_8","alias_value":"SDLQ6PBF","created_at":"2026-08-06T01:49:13Z"}],"graph_snapshots":[{"event_id":"sha256:4481981d18e87f0dae07e99b9f5d99dff085d15f66f1afc26d3e16c8a54985dd","target":"graph","created_at":"2026-08-06T01:49:13Z","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/2608.05111/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In partially observable reinforcement learning, agents face a dual bottleneck: they must explore to encounter rewarding states and retain that experience in memory to optimize their policies. Exploration bonuses and memory architectures are traditionally evaluated in isolation, leaving their interaction unmeasured, and standard notions of sparse reward conflate temporal signal density with what the reward actually supervises. We present a controlled study crossing episodic exploration bonuses with diverse neural memory architectures across three environments that vary how the content of memory","authors_text":"Henrik I. Christensen, Jai Malegaonkar, Rohan Patil","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T17:44:52Z","title":"Reward Structure Shapes the Interaction Between Episodic Exploration and Neural Memory in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05111","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:e42869312bb1e023233bb8f62ba394007f9a515ae51e5df1e4108b110bc486c7","target":"record","created_at":"2026-08-06T01:49:13Z","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":"32cc30160b53b4147f24c8f29c0ce7e186524fc0d357330d9e20b5bac2538595","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T17:44:52Z","title_canon_sha256":"701010c2c040fa1a986a10310f5f3ebf1d64fadc09ecfe2faf1faf5aaf8205f3"},"schema_version":"1.0","source":{"id":"2608.05111","kind":"arxiv","version":1}},"canonical_sha256":"90d70f3c258a5ca7e993ba4a36c66c5f547f5109e6a74bbd8afc1abf5c3a2068","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90d70f3c258a5ca7e993ba4a36c66c5f547f5109e6a74bbd8afc1abf5c3a2068","first_computed_at":"2026-08-06T01:49:13.235423Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:49:13.235423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w+oiRswXDjFOprUfzKYNxCIbB9k6dVDvF46LWStgJQ/7hH1p9JgnchwKAiFZtt2egI/LF5lsu8QTxJWD+r91CQ==","signature_status":"signed_v1","signed_at":"2026-08-06T01:49:13.236926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.05111","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e42869312bb1e023233bb8f62ba394007f9a515ae51e5df1e4108b110bc486c7","sha256:4481981d18e87f0dae07e99b9f5d99dff085d15f66f1afc26d3e16c8a54985dd"],"state_sha256":"78bcd77ed1a8faf5d9c0d807a6303beadc561086b01fdb4ff63ca3dfe70c4f4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CkkCwoV7Qen5DAA8VbHCSqZZ0gwIjOQS38zDeo1lk4HmEI5IQaloTvskQIzPwtpJjg2zMsh/XqCA0m+1RvWSCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:57:35.179342Z","bundle_sha256":"728bad950f4d4c0c57875091b43666d7f3db71caff876596bbffe20143d8da4f"}}