{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AR4TMWBE374PW2ZO3CMSVEIAN5","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":"a2ae74dc996c7f04d04976662c7975bae6bd04d9c9b7a259747bc0ae4a50b7d9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T03:35:13Z","title_canon_sha256":"3328269df6096d1f71be26d4fb99a69220561d38072160173ab2aa701eec29f4"},"schema_version":"1.0","source":{"id":"2606.00151","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00151","created_at":"2026-06-02T01:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00151v1","created_at":"2026-06-02T01:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00151","created_at":"2026-06-02T01:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"AR4TMWBE374P","created_at":"2026-06-02T01:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"AR4TMWBE374PW2ZO","created_at":"2026-06-02T01:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"AR4TMWBE","created_at":"2026-06-02T01:03:19Z"}],"graph_snapshots":[{"event_id":"sha256:7e36328dffe3fadbbd5526e025f8134523099c4190450c5c5794455dcdce7d35","target":"graph","created_at":"2026-06-02T01:03:19Z","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/2606.00151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning (RL), agents benefit from exploration only because they repeatedly encounter similar states: trying different actions can improve performance or reduce uncertainty; without such retries, a greedy policy is optimal. We formalize this intuition with ReMax, an objective that evaluates a policy by the expected maximum return over $M$ samples, where $M$ is a positive integer, while accounting for return uncertainty. Optimizing this objective induces stochastic exploration as an emergent property, without explicit bonus terms. For efficient policy optimization, we derive a ","authors_text":"Paavo Parmas, Shin Ishii, Soichiro Nishimori, Sotetsu Koyamada, Tadashi Kozuno, Toshinori Kitamura, Yutaka Matsuo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T03:35:13Z","title":"Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00151","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":"sha256:7034d970bd8de8c0cbb640ad4b0c8b8396217717026178c3f80ec557a4514fa1","target":"record","created_at":"2026-06-02T01:03:19Z","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":"a2ae74dc996c7f04d04976662c7975bae6bd04d9c9b7a259747bc0ae4a50b7d9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T03:35:13Z","title_canon_sha256":"3328269df6096d1f71be26d4fb99a69220561d38072160173ab2aa701eec29f4"},"schema_version":"1.0","source":{"id":"2606.00151","kind":"arxiv","version":1}},"canonical_sha256":"0479365824dff8fb6b2ed8992a91006f79e5a3c9b946a0616855ee25b842ffdb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0479365824dff8fb6b2ed8992a91006f79e5a3c9b946a0616855ee25b842ffdb","first_computed_at":"2026-06-02T01:03:19.893727Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:19.893727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F93mnCoMiyQnBCyT/TL43y0mYeUwcA4a6Uce+50B20Ys3KFyj5PLHtiYmD9EjRjb7v+qVJ3jsBMaYRHn0O2+AA==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:19.894141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00151","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7034d970bd8de8c0cbb640ad4b0c8b8396217717026178c3f80ec557a4514fa1","sha256:7e36328dffe3fadbbd5526e025f8134523099c4190450c5c5794455dcdce7d35"],"state_sha256":"599b88353f9e3bd38171affd4ec6d2a779430bd4d46763dc66e994ffcf32e7a8"}