{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MAU5NU2NKKKXM4RAWZN5HXPBKJ","short_pith_number":"pith:MAU5NU2N","schema_version":"1.0","canonical_sha256":"6029d6d34d5295767220b65bd3dde1524eba6dcddf4e629d8745a7ef87d9fe06","source":{"kind":"arxiv","id":"2406.06793","version":1},"attestation_state":"computed","paper":{"title":"PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Caglar Gulcehre, Chang Chen, Fei Deng, Junyeob Baek, Kenji Kawaguchi, Sungjin Ahn","submitted_at":"2024-06-10T20:59:53Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.06793","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T20:59:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"537a801c2e653fa2b6065b95b8526799d1ae8de900f0ba2162d62801485c6985","abstract_canon_sha256":"10f6158ab0a39f36a7e51cd2c13fb7384f118a2a101be4d4c50b05c2cb0cde9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:50.106630Z","signature_b64":"IyXLuVVTD9oikrTmw3f86aj4fkKsT6Gn1sr89J+YSEICisUvRdOGxVFVUC9xN4WMQdfFqxwCHSzEECKJ+xMkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6029d6d34d5295767220b65bd3dde1524eba6dcddf4e629d8745a7ef87d9fe06","last_reissued_at":"2026-07-05T08:29:50.106232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:50.106232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Caglar Gulcehre, Chang Chen, Fei Deng, Junyeob Baek, Kenji Kawaguchi, Sungjin Ahn","submitted_at":"2024-06-10T20:59:53Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06793","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/2406.06793/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.06793","created_at":"2026-07-05T08:29:50.106295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06793v1","created_at":"2026-07-05T08:29:50.106295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06793","created_at":"2026-07-05T08:29:50.106295+00:00"},{"alias_kind":"pith_short_12","alias_value":"MAU5NU2NKKKX","created_at":"2026-07-05T08:29:50.106295+00:00"},{"alias_kind":"pith_short_16","alias_value":"MAU5NU2NKKKXM4RA","created_at":"2026-07-05T08:29:50.106295+00:00"},{"alias_kind":"pith_short_8","alias_value":"MAU5NU2N","created_at":"2026-07-05T08:29:50.106295+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MAU5NU2NKKKXM4RAWZN5HXPBKJ","json":"https://pith.science/pith/MAU5NU2NKKKXM4RAWZN5HXPBKJ.json","graph_json":"https://pith.science/api/pith-number/MAU5NU2NKKKXM4RAWZN5HXPBKJ/graph.json","events_json":"https://pith.science/api/pith-number/MAU5NU2NKKKXM4RAWZN5HXPBKJ/events.json","paper":"https://pith.science/paper/MAU5NU2N"},"agent_actions":{"view_html":"https://pith.science/pith/MAU5NU2NKKKXM4RAWZN5HXPBKJ","download_json":"https://pith.science/pith/MAU5NU2NKKKXM4RAWZN5HXPBKJ.json","view_paper":"https://pith.science/paper/MAU5NU2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06793&json=true","fetch_graph":"https://pith.science/api/pith-number/MAU5NU2NKKKXM4RAWZN5HXPBKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/MAU5NU2NKKKXM4RAWZN5HXPBKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MAU5NU2NKKKXM4RAWZN5HXPBKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MAU5NU2NKKKXM4RAWZN5HXPBKJ/action/storage_attestation","attest_author":"https://pith.science/pith/MAU5NU2NKKKXM4RAWZN5HXPBKJ/action/author_attestation","sign_citation":"https://pith.science/pith/MAU5NU2NKKKXM4RAWZN5HXPBKJ/action/citation_signature","submit_replication":"https://pith.science/pith/MAU5NU2NKKKXM4RAWZN5HXPBKJ/action/replication_record"}},"created_at":"2026-07-05T08:29:50.106295+00:00","updated_at":"2026-07-05T08:29:50.106295+00:00"}