{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:64UDHF4TTS3NPHIGXOL6HNTFYC","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":"99420e10cc72170e6bbfcc3a0686055203ac70dcc76c2bb424ec7a29a5145b1f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-02T11:08:05Z","title_canon_sha256":"d2eb357735de76772b197d56ac646ca330c968e6fee3f04c93885561bd9329a0"},"schema_version":"1.0","source":{"id":"2305.01322","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.01322","created_at":"2026-07-05T08:15:10Z"},{"alias_kind":"arxiv_version","alias_value":"2305.01322v3","created_at":"2026-07-05T08:15:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01322","created_at":"2026-07-05T08:15:10Z"},{"alias_kind":"pith_short_12","alias_value":"64UDHF4TTS3N","created_at":"2026-07-05T08:15:10Z"},{"alias_kind":"pith_short_16","alias_value":"64UDHF4TTS3NPHIG","created_at":"2026-07-05T08:15:10Z"},{"alias_kind":"pith_short_8","alias_value":"64UDHF4T","created_at":"2026-07-05T08:15:10Z"}],"graph_snapshots":[{"event_id":"sha256:8c06ae5ae4526b12e53cec4e34fd0dd08544ee331b329d67a1e0620422fa8f09","target":"graph","created_at":"2026-07-05T08:15:10Z","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/2305.01322/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most exploration research on reinforcement learning (RL) has paid attention to `the way of exploration', which is `how to explore'. The other exploration research, `when to explore', has not been the main focus of RL exploration research. The issue of `when' of a monolithic exploration in the usual RL exploration behaviour binds an exploratory action to an exploitational action of an agent. Recently, a non-monolithic exploration research has emerged to examine the mode-switching exploration behaviour of humans and animals. The ultimate purpose of our research is to enable an agent to decide wh","authors_text":"Christy Liang, Farookh Hussain, Jaeyoon Kim, Junyu Xuan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-02T11:08:05Z","title":"An Autonomous Non-monolithic Agent with Multi-mode Exploration based on Options Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01322","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":"sha256:7be71c4f137d67f4e9687649399190af5f75bd1a7eb7845ee0d61003114f66c7","target":"record","created_at":"2026-07-05T08:15:10Z","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":"99420e10cc72170e6bbfcc3a0686055203ac70dcc76c2bb424ec7a29a5145b1f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-02T11:08:05Z","title_canon_sha256":"d2eb357735de76772b197d56ac646ca330c968e6fee3f04c93885561bd9329a0"},"schema_version":"1.0","source":{"id":"2305.01322","kind":"arxiv","version":3}},"canonical_sha256":"f7283397939cb6d79d06bb97e3b665c08e20425785510aa98e7fe24335027991","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7283397939cb6d79d06bb97e3b665c08e20425785510aa98e7fe24335027991","first_computed_at":"2026-07-05T08:15:10.585840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:10.585840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GXPBOEufkYgjuZw+Wbw43oLErWq05epb+lAi6JF851w4Y3Eu6y0rMlGGX8O8m5rwexMT8L/iaRkK74L8o0mVAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:10.586203Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.01322","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7be71c4f137d67f4e9687649399190af5f75bd1a7eb7845ee0d61003114f66c7","sha256:8c06ae5ae4526b12e53cec4e34fd0dd08544ee331b329d67a1e0620422fa8f09"],"state_sha256":"19f1380653d10315bb151ed2eff1aec54ce00386db73766a3a643f3d4c4ca03c"}