{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:O4QMJCSBVMVPRJKSR5SXWXGSQH","short_pith_number":"pith:O4QMJCSB","canonical_record":{"source":{"id":"2205.15064","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T12:44:56Z","cross_cats_sorted":[],"title_canon_sha256":"b38ba5598350fd493af56a1293a552b8cda1ddac7cff66153e36c294e14c27e5","abstract_canon_sha256":"ce0fe81ab0e74e774e8e1c17e2c7a8a4e0e2b78a0ba4bcaf06ad21b5a7852eeb"},"schema_version":"1.0"},"canonical_sha256":"7720c48a41ab2af8a5528f657b5cd281c2b53906808aa3646ceecf329678ca74","source":{"kind":"arxiv","id":"2205.15064","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15064","created_at":"2026-07-05T04:36:00Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15064v1","created_at":"2026-07-05T04:36:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15064","created_at":"2026-07-05T04:36:00Z"},{"alias_kind":"pith_short_12","alias_value":"O4QMJCSBVMVP","created_at":"2026-07-05T04:36:00Z"},{"alias_kind":"pith_short_16","alias_value":"O4QMJCSBVMVPRJKS","created_at":"2026-07-05T04:36:00Z"},{"alias_kind":"pith_short_8","alias_value":"O4QMJCSB","created_at":"2026-07-05T04:36:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:O4QMJCSBVMVPRJKSR5SXWXGSQH","target":"record","payload":{"canonical_record":{"source":{"id":"2205.15064","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T12:44:56Z","cross_cats_sorted":[],"title_canon_sha256":"b38ba5598350fd493af56a1293a552b8cda1ddac7cff66153e36c294e14c27e5","abstract_canon_sha256":"ce0fe81ab0e74e774e8e1c17e2c7a8a4e0e2b78a0ba4bcaf06ad21b5a7852eeb"},"schema_version":"1.0"},"canonical_sha256":"7720c48a41ab2af8a5528f657b5cd281c2b53906808aa3646ceecf329678ca74","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:00.928451Z","signature_b64":"oUWphsFsmz6eVkfVy9cgjQcXzvjBnD3COsY6kxM0Mgpg8DZAAuKnQPaKNU3EamsXv0jAnodX2Hc1Wk3cq+ziCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7720c48a41ab2af8a5528f657b5cd281c2b53906808aa3646ceecf329678ca74","last_reissued_at":"2026-07-05T04:36:00.927973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:00.927973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.15064","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":"2026-07-05T04:36:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3nfE1iHzsmPt3p031HCEG9Vo8iEyhZbwJxjryn+zkCRZS4ANbZzMjezNqdS9gTIXEnNyUJOgf2PD0A9BrxDYBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T11:48:49.941301Z"},"content_sha256":"f09c5cdcee15981fda672876ee5b762da17cd17455618420865102b7916042ef","schema_version":"1.0","event_id":"sha256:f09c5cdcee15981fda672876ee5b762da17cd17455618420865102b7916042ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:O4QMJCSBVMVPRJKSR5SXWXGSQH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SEREN: Knowing When to Explore and When to Exploit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aivar Sootla, Changmin Yu, David Mguni, Dong Li, Jun Wang, Neil Burgess","submitted_at":"2022-05-30T12:44:56Z","abstract_excerpt":"Efficient reinforcement learning (RL) involves a trade-off between \"exploitative\" actions that maximise expected reward and \"explorative'\" ones that sample unvisited states. To encourage exploration, recent approaches proposed adding stochasticity to actions, separating exploration and exploitation phases, or equating reduction in uncertainty with reward. However, these techniques do not necessarily offer entirely systematic approaches making this trade-off. Here we introduce SElective Reinforcement Exploration Network (SEREN) that poses the exploration-exploitation trade-off as a game between"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15064","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/2205.15064/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":"2026-07-05T04:36:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q3GOZ00eDjgdfeKyDU8rsZkCclwxXWYoX9MQ0uAiQmyo9ukGUtkpXcl1xSTNA3cONRV/UxdNS6kevdpJe2YWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T11:48:49.941688Z"},"content_sha256":"1e31493aeea33351bb5277dcf0596c295b804d85e30927ba083708c8c83c0604","schema_version":"1.0","event_id":"sha256:1e31493aeea33351bb5277dcf0596c295b804d85e30927ba083708c8c83c0604"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O4QMJCSBVMVPRJKSR5SXWXGSQH/bundle.json","state_url":"https://pith.science/pith/O4QMJCSBVMVPRJKSR5SXWXGSQH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O4QMJCSBVMVPRJKSR5SXWXGSQH/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":"2026-07-13T11:48:49Z","links":{"resolver":"https://pith.science/pith/O4QMJCSBVMVPRJKSR5SXWXGSQH","bundle":"https://pith.science/pith/O4QMJCSBVMVPRJKSR5SXWXGSQH/bundle.json","state":"https://pith.science/pith/O4QMJCSBVMVPRJKSR5SXWXGSQH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O4QMJCSBVMVPRJKSR5SXWXGSQH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:O4QMJCSBVMVPRJKSR5SXWXGSQH","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":"ce0fe81ab0e74e774e8e1c17e2c7a8a4e0e2b78a0ba4bcaf06ad21b5a7852eeb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T12:44:56Z","title_canon_sha256":"b38ba5598350fd493af56a1293a552b8cda1ddac7cff66153e36c294e14c27e5"},"schema_version":"1.0","source":{"id":"2205.15064","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15064","created_at":"2026-07-05T04:36:00Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15064v1","created_at":"2026-07-05T04:36:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15064","created_at":"2026-07-05T04:36:00Z"},{"alias_kind":"pith_short_12","alias_value":"O4QMJCSBVMVP","created_at":"2026-07-05T04:36:00Z"},{"alias_kind":"pith_short_16","alias_value":"O4QMJCSBVMVPRJKS","created_at":"2026-07-05T04:36:00Z"},{"alias_kind":"pith_short_8","alias_value":"O4QMJCSB","created_at":"2026-07-05T04:36:00Z"}],"graph_snapshots":[{"event_id":"sha256:1e31493aeea33351bb5277dcf0596c295b804d85e30927ba083708c8c83c0604","target":"graph","created_at":"2026-07-05T04:36:00Z","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/2205.15064/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient reinforcement learning (RL) involves a trade-off between \"exploitative\" actions that maximise expected reward and \"explorative'\" ones that sample unvisited states. To encourage exploration, recent approaches proposed adding stochasticity to actions, separating exploration and exploitation phases, or equating reduction in uncertainty with reward. However, these techniques do not necessarily offer entirely systematic approaches making this trade-off. Here we introduce SElective Reinforcement Exploration Network (SEREN) that poses the exploration-exploitation trade-off as a game between","authors_text":"Aivar Sootla, Changmin Yu, David Mguni, Dong Li, Jun Wang, Neil Burgess","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T12:44:56Z","title":"SEREN: Knowing When to Explore and When to Exploit"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15064","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:f09c5cdcee15981fda672876ee5b762da17cd17455618420865102b7916042ef","target":"record","created_at":"2026-07-05T04:36:00Z","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":"ce0fe81ab0e74e774e8e1c17e2c7a8a4e0e2b78a0ba4bcaf06ad21b5a7852eeb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T12:44:56Z","title_canon_sha256":"b38ba5598350fd493af56a1293a552b8cda1ddac7cff66153e36c294e14c27e5"},"schema_version":"1.0","source":{"id":"2205.15064","kind":"arxiv","version":1}},"canonical_sha256":"7720c48a41ab2af8a5528f657b5cd281c2b53906808aa3646ceecf329678ca74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7720c48a41ab2af8a5528f657b5cd281c2b53906808aa3646ceecf329678ca74","first_computed_at":"2026-07-05T04:36:00.927973Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:36:00.927973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oUWphsFsmz6eVkfVy9cgjQcXzvjBnD3COsY6kxM0Mgpg8DZAAuKnQPaKNU3EamsXv0jAnodX2Hc1Wk3cq+ziCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:36:00.928451Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.15064","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f09c5cdcee15981fda672876ee5b762da17cd17455618420865102b7916042ef","sha256:1e31493aeea33351bb5277dcf0596c295b804d85e30927ba083708c8c83c0604"],"state_sha256":"2edace031494210c20d2075ec1734e55d348438e456823af7e7b40cf6bf29f88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4xM1C/KkK2GSMOKlrgbBDddRpymSgzTY3MAiWgfDJNkS7R3LrFYKy2LaNLi2KK1MHJFFiPXaVXx0qmd1XCv1Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T11:48:49.943682Z","bundle_sha256":"14ee20a4628648681c99cfe8c20dfc35b717e4fdc31aff5f2827829a54e44bde"}}