{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HHOBWKYZP55DPNBTU3TQNQNLHA","short_pith_number":"pith:HHOBWKYZ","schema_version":"1.0","canonical_sha256":"39dc1b2b197f7a37b433a6e706c1ab3808b7e656118928521e4459a7dc8c3e44","source":{"kind":"arxiv","id":"2406.05572","version":2},"attestation_state":"computed","paper":{"title":"Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Aidan Curtis, Jing Cao, Leslie Pack Kaelbling, Nishanth Kumar, Tom\\'as Lozano-P\\'erez","submitted_at":"2024-06-08T20:56:14Z","abstract_excerpt":"Recent developments in pretrained large language models (LLMs) applied to robotics have demonstrated their capacity for sequencing a set of discrete skills to achieve open-ended goals in simple robotic tasks. In this paper, we examine the topic of LLM planning for a set of continuously parameterized skills whose execution must avoid violations of a set of kinematic, geometric, and physical constraints. We prompt the LLM to output code for a function with open parameters, which, together with environmental constraints, can be viewed as a Continuous Constraint Satisfaction Problem (CCSP). This C"},"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":"2406.05572","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-08T20:56:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f46dd8e397ba4b2ac89e065bd71501b8c83c58db01989fb6c14926d225560a0","abstract_canon_sha256":"271f36bc668bab1533edbb9246c9cb63c17bcfa0c5625c7efc401d20b50cb848"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:53.773931Z","signature_b64":"vecuWK3plfoZUdLRZdSs+MjuWSOW7Zq/zACQkbj2ceSnFg2eaWB0hcogq7TrftBzRWtyYBCnzp6t48kR7L9wAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39dc1b2b197f7a37b433a6e706c1ab3808b7e656118928521e4459a7dc8c3e44","last_reissued_at":"2026-07-05T09:03:53.773460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:53.773460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Aidan Curtis, Jing Cao, Leslie Pack Kaelbling, Nishanth Kumar, Tom\\'as Lozano-P\\'erez","submitted_at":"2024-06-08T20:56:14Z","abstract_excerpt":"Recent developments in pretrained large language models (LLMs) applied to robotics have demonstrated their capacity for sequencing a set of discrete skills to achieve open-ended goals in simple robotic tasks. In this paper, we examine the topic of LLM planning for a set of continuously parameterized skills whose execution must avoid violations of a set of kinematic, geometric, and physical constraints. We prompt the LLM to output code for a function with open parameters, which, together with environmental constraints, can be viewed as a Continuous Constraint Satisfaction Problem (CCSP). This C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05572","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/2406.05572/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":"2406.05572","created_at":"2026-07-05T09:03:53.773517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05572v2","created_at":"2026-07-05T09:03:53.773517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05572","created_at":"2026-07-05T09:03:53.773517+00:00"},{"alias_kind":"pith_short_12","alias_value":"HHOBWKYZP55D","created_at":"2026-07-05T09:03:53.773517+00:00"},{"alias_kind":"pith_short_16","alias_value":"HHOBWKYZP55DPNBT","created_at":"2026-07-05T09:03:53.773517+00:00"},{"alias_kind":"pith_short_8","alias_value":"HHOBWKYZ","created_at":"2026-07-05T09:03:53.773517+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/HHOBWKYZP55DPNBTU3TQNQNLHA","json":"https://pith.science/pith/HHOBWKYZP55DPNBTU3TQNQNLHA.json","graph_json":"https://pith.science/api/pith-number/HHOBWKYZP55DPNBTU3TQNQNLHA/graph.json","events_json":"https://pith.science/api/pith-number/HHOBWKYZP55DPNBTU3TQNQNLHA/events.json","paper":"https://pith.science/paper/HHOBWKYZ"},"agent_actions":{"view_html":"https://pith.science/pith/HHOBWKYZP55DPNBTU3TQNQNLHA","download_json":"https://pith.science/pith/HHOBWKYZP55DPNBTU3TQNQNLHA.json","view_paper":"https://pith.science/paper/HHOBWKYZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05572&json=true","fetch_graph":"https://pith.science/api/pith-number/HHOBWKYZP55DPNBTU3TQNQNLHA/graph.json","fetch_events":"https://pith.science/api/pith-number/HHOBWKYZP55DPNBTU3TQNQNLHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HHOBWKYZP55DPNBTU3TQNQNLHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HHOBWKYZP55DPNBTU3TQNQNLHA/action/storage_attestation","attest_author":"https://pith.science/pith/HHOBWKYZP55DPNBTU3TQNQNLHA/action/author_attestation","sign_citation":"https://pith.science/pith/HHOBWKYZP55DPNBTU3TQNQNLHA/action/citation_signature","submit_replication":"https://pith.science/pith/HHOBWKYZP55DPNBTU3TQNQNLHA/action/replication_record"}},"created_at":"2026-07-05T09:03:53.773517+00:00","updated_at":"2026-07-05T09:03:53.773517+00:00"}