{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TPWEDELAKBECIUWEQEPAA4GZYK","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":"b8322c6679edc14b07031d8bf92e6befc9f6f0c640eda06bea9ff8a9ff5fdb74","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-13T00:57:10Z","title_canon_sha256":"a00efba17e2bc99cfc950c2b59e922cfd9212d54907a4a50b2131c35393fe2b6"},"schema_version":"1.0","source":{"id":"2410.09686","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09686","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09686v2","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09686","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"pith_short_12","alias_value":"TPWEDELAKBEC","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"TPWEDELAKBECIUWE","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"TPWEDELA","created_at":"2026-07-05T09:30:22Z"}],"graph_snapshots":[{"event_id":"sha256:462de175a4ed0b1e822139b3f787e6d29114e188828ed58280ce02ffb49c864b","target":"graph","created_at":"2026-07-05T09:30:22Z","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/2410.09686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we address the challenge of learning generalizable policies for compositional tasks defined by logical specifications. These tasks consist of multiple temporally extended sub-tasks. Due to the sub-task inter-dependencies and sparse reward issue in long-horizon tasks, existing reinforcement learning (RL) approaches, such as task-conditioned and goal-conditioned policies, continue to struggle with slow convergence and sub-optimal performance in generalizing to compositional tasks. To overcome these limitations, we introduce a new hierarchical RL framework that enhances the efficie","authors_text":"Duo Xu, Faramarz Fekri","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-13T00:57:10Z","title":"Generalization of Compositional Tasks with Logical Specification via Implicit Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09686","kind":"arxiv","version":2},"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:b556d4200334bbef173fc45e9a6ad92131e9af2817e479884d4995b25fa8104c","target":"record","created_at":"2026-07-05T09:30:22Z","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":"b8322c6679edc14b07031d8bf92e6befc9f6f0c640eda06bea9ff8a9ff5fdb74","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-13T00:57:10Z","title_canon_sha256":"a00efba17e2bc99cfc950c2b59e922cfd9212d54907a4a50b2131c35393fe2b6"},"schema_version":"1.0","source":{"id":"2410.09686","kind":"arxiv","version":2}},"canonical_sha256":"9bec41916050482452c4811e0070d9c295651e1fccc5c4093bc8897096a6acb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9bec41916050482452c4811e0070d9c295651e1fccc5c4093bc8897096a6acb8","first_computed_at":"2026-07-05T09:30:22.146180Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:22.146180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GYGSWB3lySUNxKGPj91OPMRb7m2+ladjjf0Paa2o2MYsMMhPsisIAAhoCqf83YNDK/rdwHXYGY52lNNfsVfbCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:22.146597Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.09686","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b556d4200334bbef173fc45e9a6ad92131e9af2817e479884d4995b25fa8104c","sha256:462de175a4ed0b1e822139b3f787e6d29114e188828ed58280ce02ffb49c864b"],"state_sha256":"031024519f50145dc8f4c9e987ba2a7b58b884feeccbd4e7ef983ce45ea7c2c3"}