{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JCM7JATM6LPDZH4II44P27INEZ","short_pith_number":"pith:JCM7JATM","schema_version":"1.0","canonical_sha256":"4899f4826cf2de3c9f884738fd7d0d264ab7474242295310404026e4ae4bb603","source":{"kind":"arxiv","id":"2403.18760","version":2},"attestation_state":"computed","paper":{"title":"MLDT: Multi-Level Decomposition for Complex Long-Horizon Robotic Task Planning with Open-Source Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Guilin Qi, Jiatao Zhang, Jie Ren, Jun Shao, LanLing Tang, Nan Hu, Wei Song, Yike Wu","submitted_at":"2024-03-27T16:58:20Z","abstract_excerpt":"In the realm of data-driven AI technology, the application of open-source large language models (LLMs) in robotic task planning represents a significant milestone. Recent robotic task planning methods based on open-source LLMs typically leverage vast task planning datasets to enhance models' planning abilities. While these methods show promise, they struggle with complex long-horizon tasks, which require comprehending more context and generating longer action sequences. This paper addresses this limitation by proposing MLDT, theMulti-Level Decomposition Task planning method. This method innova"},"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":"2403.18760","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-03-27T16:58:20Z","cross_cats_sorted":[],"title_canon_sha256":"43fd2aa62304f70cb06f5a3fba135f2cfc36e0fdf40f85c0b718f9cce13f0af7","abstract_canon_sha256":"aad94c07430dc8843a65d3f387f049207ca4e539f8454e07bc0afab884bc1974"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:11.767212Z","signature_b64":"6A3BJ5SlB09B1cb+sUxfxdUSfME6DB4Crcrb7tSFQqZfo/H2sHW6hzT0s4rwLbsmzMfR365iG5u9XJvS/1/qCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4899f4826cf2de3c9f884738fd7d0d264ab7474242295310404026e4ae4bb603","last_reissued_at":"2026-07-05T08:03:11.766598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:11.766598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MLDT: Multi-Level Decomposition for Complex Long-Horizon Robotic Task Planning with Open-Source Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Guilin Qi, Jiatao Zhang, Jie Ren, Jun Shao, LanLing Tang, Nan Hu, Wei Song, Yike Wu","submitted_at":"2024-03-27T16:58:20Z","abstract_excerpt":"In the realm of data-driven AI technology, the application of open-source large language models (LLMs) in robotic task planning represents a significant milestone. Recent robotic task planning methods based on open-source LLMs typically leverage vast task planning datasets to enhance models' planning abilities. While these methods show promise, they struggle with complex long-horizon tasks, which require comprehending more context and generating longer action sequences. This paper addresses this limitation by proposing MLDT, theMulti-Level Decomposition Task planning method. This method innova"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18760","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/2403.18760/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":"2403.18760","created_at":"2026-07-05T08:03:11.766693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.18760v2","created_at":"2026-07-05T08:03:11.766693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18760","created_at":"2026-07-05T08:03:11.766693+00:00"},{"alias_kind":"pith_short_12","alias_value":"JCM7JATM6LPD","created_at":"2026-07-05T08:03:11.766693+00:00"},{"alias_kind":"pith_short_16","alias_value":"JCM7JATM6LPDZH4I","created_at":"2026-07-05T08:03:11.766693+00:00"},{"alias_kind":"pith_short_8","alias_value":"JCM7JATM","created_at":"2026-07-05T08:03:11.766693+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/JCM7JATM6LPDZH4II44P27INEZ","json":"https://pith.science/pith/JCM7JATM6LPDZH4II44P27INEZ.json","graph_json":"https://pith.science/api/pith-number/JCM7JATM6LPDZH4II44P27INEZ/graph.json","events_json":"https://pith.science/api/pith-number/JCM7JATM6LPDZH4II44P27INEZ/events.json","paper":"https://pith.science/paper/JCM7JATM"},"agent_actions":{"view_html":"https://pith.science/pith/JCM7JATM6LPDZH4II44P27INEZ","download_json":"https://pith.science/pith/JCM7JATM6LPDZH4II44P27INEZ.json","view_paper":"https://pith.science/paper/JCM7JATM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.18760&json=true","fetch_graph":"https://pith.science/api/pith-number/JCM7JATM6LPDZH4II44P27INEZ/graph.json","fetch_events":"https://pith.science/api/pith-number/JCM7JATM6LPDZH4II44P27INEZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JCM7JATM6LPDZH4II44P27INEZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JCM7JATM6LPDZH4II44P27INEZ/action/storage_attestation","attest_author":"https://pith.science/pith/JCM7JATM6LPDZH4II44P27INEZ/action/author_attestation","sign_citation":"https://pith.science/pith/JCM7JATM6LPDZH4II44P27INEZ/action/citation_signature","submit_replication":"https://pith.science/pith/JCM7JATM6LPDZH4II44P27INEZ/action/replication_record"}},"created_at":"2026-07-05T08:03:11.766693+00:00","updated_at":"2026-07-05T08:03:11.766693+00:00"}