{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MAU5NU2NKKKXM4RAWZN5HXPBKJ","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":"10f6158ab0a39f36a7e51cd2c13fb7384f118a2a101be4d4c50b05c2cb0cde9c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T20:59:53Z","title_canon_sha256":"537a801c2e653fa2b6065b95b8526799d1ae8de900f0ba2162d62801485c6985"},"schema_version":"1.0","source":{"id":"2406.06793","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06793","created_at":"2026-07-05T08:29:50Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06793v1","created_at":"2026-07-05T08:29:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06793","created_at":"2026-07-05T08:29:50Z"},{"alias_kind":"pith_short_12","alias_value":"MAU5NU2NKKKX","created_at":"2026-07-05T08:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"MAU5NU2NKKKXM4RA","created_at":"2026-07-05T08:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"MAU5NU2N","created_at":"2026-07-05T08:29:50Z"}],"graph_snapshots":[{"event_id":"sha256:a4eee172ac3f457fefcb7e151e37d141cc24dae66e0413d1316028c90915c6ff","target":"graph","created_at":"2026-07-05T08:29:50Z","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/2406.06793/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the recent advancements in offline RL, no unified algorithm could achieve superior performance across a broad range of tasks. Offline \\textit{value function learning}, in particular, struggles with sparse-reward, long-horizon tasks due to the difficulty of solving credit assignment and extrapolation errors that accumulates as the horizon of the task grows.~On the other hand, models that can perform well in long-horizon tasks are designed specifically for goal-conditioned tasks, which commonly perform worse than value function learning methods on short-horizon, dense-reward scenarios. T","authors_text":"Caglar Gulcehre, Chang Chen, Fei Deng, Junyeob Baek, Kenji Kawaguchi, Sungjin Ahn","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T20:59:53Z","title":"PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06793","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":"sha256:01a516d8b84f0666a178ac64f6f82c721d49b1172419a1095bc9c7b77168d4d0","target":"record","created_at":"2026-07-05T08:29:50Z","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":"10f6158ab0a39f36a7e51cd2c13fb7384f118a2a101be4d4c50b05c2cb0cde9c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T20:59:53Z","title_canon_sha256":"537a801c2e653fa2b6065b95b8526799d1ae8de900f0ba2162d62801485c6985"},"schema_version":"1.0","source":{"id":"2406.06793","kind":"arxiv","version":1}},"canonical_sha256":"6029d6d34d5295767220b65bd3dde1524eba6dcddf4e629d8745a7ef87d9fe06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6029d6d34d5295767220b65bd3dde1524eba6dcddf4e629d8745a7ef87d9fe06","first_computed_at":"2026-07-05T08:29:50.106232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:50.106232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IyXLuVVTD9oikrTmw3f86aj4fkKsT6Gn1sr89J+YSEICisUvRdOGxVFVUC9xN4WMQdfFqxwCHSzEECKJ+xMkDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:50.106630Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06793","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01a516d8b84f0666a178ac64f6f82c721d49b1172419a1095bc9c7b77168d4d0","sha256:a4eee172ac3f457fefcb7e151e37d141cc24dae66e0413d1316028c90915c6ff"],"state_sha256":"08104adcbe73f53f51f36900118bf96a72f0574630b342c9c302851146920896"}