{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LPEWQCN4Z46LYWFD6KFLPFDEIL","short_pith_number":"pith:LPEWQCN4","canonical_record":{"source":{"id":"2405.03064","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T22:06:42Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"792a93d35ee04f244022584dfdc0c96f36bbb02f59388e6402474a98cd1b2613","abstract_canon_sha256":"41e968d3d113128c8050ff650a63453afba39e7c3aa9c791836a7ed0f247fde7"},"schema_version":"1.0"},"canonical_sha256":"5bc96809bccf3cbc58a3f28ab7946442d1e93ee116acde6a975ac9e3ed246fb8","source":{"kind":"arxiv","id":"2405.03064","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03064","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03064v3","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03064","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"pith_short_12","alias_value":"LPEWQCN4Z46L","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"pith_short_16","alias_value":"LPEWQCN4Z46LYWFD","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"pith_short_8","alias_value":"LPEWQCN4","created_at":"2026-07-05T08:28:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LPEWQCN4Z46LYWFD6KFLPFDEIL","target":"record","payload":{"canonical_record":{"source":{"id":"2405.03064","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T22:06:42Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"792a93d35ee04f244022584dfdc0c96f36bbb02f59388e6402474a98cd1b2613","abstract_canon_sha256":"41e968d3d113128c8050ff650a63453afba39e7c3aa9c791836a7ed0f247fde7"},"schema_version":"1.0"},"canonical_sha256":"5bc96809bccf3cbc58a3f28ab7946442d1e93ee116acde6a975ac9e3ed246fb8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:09.800038Z","signature_b64":"iktd7exmHOUjdlJwzvQK6cif46jiheLnfoax+kWNsVRZOWNfViLtJ+yuC6uUiv0GIoiteZomLtmfC9ocxHoHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bc96809bccf3cbc58a3f28ab7946442d1e93ee116acde6a975ac9e3ed246fb8","last_reissued_at":"2026-07-05T08:28:09.799579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:09.799579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.03064","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"03QPjQB+hjslwffj/UNhqDi+7U/fVkG1GwVvRHRP4qP4SUnhpX2N2Z+r73SbOLBFeN0mjL111g53XONQ7XpqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:11:39.283387Z"},"content_sha256":"39edd05c0690862946c1ed70beae2c56b31ce17c822427b000b4eb4d4a2ef750","schema_version":"1.0","event_id":"sha256:39edd05c0690862946c1ed70beae2c56b31ce17c822427b000b4eb4d4a2ef750"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LPEWQCN4Z46LYWFD6KFLPFDEIL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Gang Wang, Jiahao Yu, Sabrina Yang, Xian Wu, Xinyu Xing, Zelei Cheng","submitted_at":"2024-05-05T22:06:42Z","abstract_excerpt":"Deep reinforcement learning (DRL) is playing an increasingly important role in real-world applications. However, obtaining an optimally performing DRL agent for complex tasks, especially with sparse rewards, remains a significant challenge. The training of a DRL agent can be often trapped in a bottleneck without further progress. In this paper, we propose RICE, an innovative refining scheme for reinforcement learning that incorporates explanation methods to break through the training bottlenecks. The high-level idea of RICE is to construct a new initial state distribution that combines both th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03064","kind":"arxiv","version":3},"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/2405.03064/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":"2026-07-05T08:28:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rcUzPvXF8zH+T2J9lnaO2L5M7GX5dICFLtzGl0yS63IwBW+LIqJla+/Q+cRC5MgCpQDAstTMvkAuqZfzF013Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:11:39.283891Z"},"content_sha256":"44d19da2402c6a1605d7e02fa886b95f1806793424c58763e1a0bdb3e6b3731e","schema_version":"1.0","event_id":"sha256:44d19da2402c6a1605d7e02fa886b95f1806793424c58763e1a0bdb3e6b3731e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LPEWQCN4Z46LYWFD6KFLPFDEIL/bundle.json","state_url":"https://pith.science/pith/LPEWQCN4Z46LYWFD6KFLPFDEIL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LPEWQCN4Z46LYWFD6KFLPFDEIL/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":"2026-08-08T23:11:39Z","links":{"resolver":"https://pith.science/pith/LPEWQCN4Z46LYWFD6KFLPFDEIL","bundle":"https://pith.science/pith/LPEWQCN4Z46LYWFD6KFLPFDEIL/bundle.json","state":"https://pith.science/pith/LPEWQCN4Z46LYWFD6KFLPFDEIL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LPEWQCN4Z46LYWFD6KFLPFDEIL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LPEWQCN4Z46LYWFD6KFLPFDEIL","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":"41e968d3d113128c8050ff650a63453afba39e7c3aa9c791836a7ed0f247fde7","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T22:06:42Z","title_canon_sha256":"792a93d35ee04f244022584dfdc0c96f36bbb02f59388e6402474a98cd1b2613"},"schema_version":"1.0","source":{"id":"2405.03064","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03064","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03064v3","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03064","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"pith_short_12","alias_value":"LPEWQCN4Z46L","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"pith_short_16","alias_value":"LPEWQCN4Z46LYWFD","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"pith_short_8","alias_value":"LPEWQCN4","created_at":"2026-07-05T08:28:09Z"}],"graph_snapshots":[{"event_id":"sha256:44d19da2402c6a1605d7e02fa886b95f1806793424c58763e1a0bdb3e6b3731e","target":"graph","created_at":"2026-07-05T08:28:09Z","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/2405.03064/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (DRL) is playing an increasingly important role in real-world applications. However, obtaining an optimally performing DRL agent for complex tasks, especially with sparse rewards, remains a significant challenge. The training of a DRL agent can be often trapped in a bottleneck without further progress. In this paper, we propose RICE, an innovative refining scheme for reinforcement learning that incorporates explanation methods to break through the training bottlenecks. The high-level idea of RICE is to construct a new initial state distribution that combines both th","authors_text":"Gang Wang, Jiahao Yu, Sabrina Yang, Xian Wu, Xinyu Xing, Zelei Cheng","cross_cats":["cs.AI","cs.CR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T22:06:42Z","title":"RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03064","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":"sha256:39edd05c0690862946c1ed70beae2c56b31ce17c822427b000b4eb4d4a2ef750","target":"record","created_at":"2026-07-05T08:28:09Z","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":"41e968d3d113128c8050ff650a63453afba39e7c3aa9c791836a7ed0f247fde7","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T22:06:42Z","title_canon_sha256":"792a93d35ee04f244022584dfdc0c96f36bbb02f59388e6402474a98cd1b2613"},"schema_version":"1.0","source":{"id":"2405.03064","kind":"arxiv","version":3}},"canonical_sha256":"5bc96809bccf3cbc58a3f28ab7946442d1e93ee116acde6a975ac9e3ed246fb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bc96809bccf3cbc58a3f28ab7946442d1e93ee116acde6a975ac9e3ed246fb8","first_computed_at":"2026-07-05T08:28:09.799579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:09.799579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iktd7exmHOUjdlJwzvQK6cif46jiheLnfoax+kWNsVRZOWNfViLtJ+yuC6uUiv0GIoiteZomLtmfC9ocxHoHCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:09.800038Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.03064","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39edd05c0690862946c1ed70beae2c56b31ce17c822427b000b4eb4d4a2ef750","sha256:44d19da2402c6a1605d7e02fa886b95f1806793424c58763e1a0bdb3e6b3731e"],"state_sha256":"12d6874c28e342055d4df7a323b4b35f71cd0a4712b8208d5060962dbc31a94b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eTrYMxOOUSAB07nAyxlL/P5Muj2aZNvOEr5YJ6LZenGIv7Eyu5bwFgVQKboSbdgtSpgO10dj7neuMR7z2hjmBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:11:39.288740Z","bundle_sha256":"c0396b07dab68748d3a22229585247279fc6e38199ef46eba17c58096a73ba36"}}