{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TPWEDELAKBECIUWEQEPAA4GZYK","short_pith_number":"pith:TPWEDELA","schema_version":"1.0","canonical_sha256":"9bec41916050482452c4811e0070d9c295651e1fccc5c4093bc8897096a6acb8","source":{"kind":"arxiv","id":"2410.09686","version":2},"attestation_state":"computed","paper":{"title":"Generalization of Compositional Tasks with Logical Specification via Implicit Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Duo Xu, Faramarz Fekri","submitted_at":"2024-10-13T00:57:10Z","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"},"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":"2410.09686","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-13T00:57:10Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"a00efba17e2bc99cfc950c2b59e922cfd9212d54907a4a50b2131c35393fe2b6","abstract_canon_sha256":"b8322c6679edc14b07031d8bf92e6befc9f6f0c640eda06bea9ff8a9ff5fdb74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:22.146597Z","signature_b64":"GYGSWB3lySUNxKGPj91OPMRb7m2+ladjjf0Paa2o2MYsMMhPsisIAAhoCqf83YNDK/rdwHXYGY52lNNfsVfbCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bec41916050482452c4811e0070d9c295651e1fccc5c4093bc8897096a6acb8","last_reissued_at":"2026-07-05T09:30:22.146180Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:22.146180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization of Compositional Tasks with Logical Specification via Implicit Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Duo Xu, Faramarz Fekri","submitted_at":"2024-10-13T00:57:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09686","kind":"arxiv","version":2},"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/2410.09686/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":"2410.09686","created_at":"2026-07-05T09:30:22.146233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09686v2","created_at":"2026-07-05T09:30:22.146233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09686","created_at":"2026-07-05T09:30:22.146233+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPWEDELAKBEC","created_at":"2026-07-05T09:30:22.146233+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPWEDELAKBECIUWE","created_at":"2026-07-05T09:30:22.146233+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPWEDELA","created_at":"2026-07-05T09:30:22.146233+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08972","citing_title":"Atomic-to-Compositional Generalization for Mobile Agents with A New Benchmark and Scheduling System","ref_index":73,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TPWEDELAKBECIUWEQEPAA4GZYK","json":"https://pith.science/pith/TPWEDELAKBECIUWEQEPAA4GZYK.json","graph_json":"https://pith.science/api/pith-number/TPWEDELAKBECIUWEQEPAA4GZYK/graph.json","events_json":"https://pith.science/api/pith-number/TPWEDELAKBECIUWEQEPAA4GZYK/events.json","paper":"https://pith.science/paper/TPWEDELA"},"agent_actions":{"view_html":"https://pith.science/pith/TPWEDELAKBECIUWEQEPAA4GZYK","download_json":"https://pith.science/pith/TPWEDELAKBECIUWEQEPAA4GZYK.json","view_paper":"https://pith.science/paper/TPWEDELA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09686&json=true","fetch_graph":"https://pith.science/api/pith-number/TPWEDELAKBECIUWEQEPAA4GZYK/graph.json","fetch_events":"https://pith.science/api/pith-number/TPWEDELAKBECIUWEQEPAA4GZYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPWEDELAKBECIUWEQEPAA4GZYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPWEDELAKBECIUWEQEPAA4GZYK/action/storage_attestation","attest_author":"https://pith.science/pith/TPWEDELAKBECIUWEQEPAA4GZYK/action/author_attestation","sign_citation":"https://pith.science/pith/TPWEDELAKBECIUWEQEPAA4GZYK/action/citation_signature","submit_replication":"https://pith.science/pith/TPWEDELAKBECIUWEQEPAA4GZYK/action/replication_record"}},"created_at":"2026-07-05T09:30:22.146233+00:00","updated_at":"2026-07-05T09:30:22.146233+00:00"}