{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UST4TBA75M5BNCVN5NG7RBO3JC","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":"015aab8ef4e532bd0f40c83e53acb5d4dfc3f5770e473c340088b3df5bf29671","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T06:51:51Z","title_canon_sha256":"bfe491c2b711527fdaf44af58c357339a5f1e5894be2405c1db0ef98f8668ccb"},"schema_version":"1.0","source":{"id":"2305.13741","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13741","created_at":"2026-07-05T06:12:56Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13741v1","created_at":"2026-07-05T06:12:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13741","created_at":"2026-07-05T06:12:56Z"},{"alias_kind":"pith_short_12","alias_value":"UST4TBA75M5B","created_at":"2026-07-05T06:12:56Z"},{"alias_kind":"pith_short_16","alias_value":"UST4TBA75M5BNCVN","created_at":"2026-07-05T06:12:56Z"},{"alias_kind":"pith_short_8","alias_value":"UST4TBA7","created_at":"2026-07-05T06:12:56Z"}],"graph_snapshots":[{"event_id":"sha256:2328f0155edcff9c5542984ac23c8d64a6b2418fa5c3a361696a3d40d804c0d9","target":"graph","created_at":"2026-07-05T06:12:56Z","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/2305.13741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tasks that involve interaction with various targets are called multi-target tasks. When applying general reinforcement learning approaches for such tasks, certain targets that are difficult to access or interact with may be neglected throughout the course of training - a predicament we call Under-explored Target Problem (UTP). To address this problem, we propose L-SA (Learning by adaptive Sampling and Active querying) framework that includes adaptive sampling and active querying. In the L-SA framework, adaptive sampling dynamically samples targets with the highest increase of success rates at ","authors_text":"Byoung-Tak Zhang, Hyundo Lee, Kibeom Kim, Minsu Lee, Min Whoo Lee, Moonheon Lee","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T06:51:51Z","title":"L-SA: Learning Under-Explored Targets in Multi-Target Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13741","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:b6a9e8eff1e01f4ebd6cf31f10afc8a8fa477a894b4a50769c3614d962d35da2","target":"record","created_at":"2026-07-05T06:12:56Z","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":"015aab8ef4e532bd0f40c83e53acb5d4dfc3f5770e473c340088b3df5bf29671","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T06:51:51Z","title_canon_sha256":"bfe491c2b711527fdaf44af58c357339a5f1e5894be2405c1db0ef98f8668ccb"},"schema_version":"1.0","source":{"id":"2305.13741","kind":"arxiv","version":1}},"canonical_sha256":"a4a7c9841feb3a168aadeb4df885db48abc48b96903836e2013df03461609495","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4a7c9841feb3a168aadeb4df885db48abc48b96903836e2013df03461609495","first_computed_at":"2026-07-05T06:12:56.951911Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:56.951911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wnahqITfiRavAUe8JZUw6H5WWYYQi5WFVHtsc1hO1BuOSPvxf/6npVS6POWI2ZiPyRrfD95PIrPQDzu2uGR4AA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:56.952379Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13741","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6a9e8eff1e01f4ebd6cf31f10afc8a8fa477a894b4a50769c3614d962d35da2","sha256:2328f0155edcff9c5542984ac23c8d64a6b2418fa5c3a361696a3d40d804c0d9"],"state_sha256":"8fcfa13d5ced12fb65a92009fc3f2f4a08576ddaac985f0fbe78db2fd35bbbd4"}