{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6ISX2AFVVK5AKPFCDDI7P7HZGR","short_pith_number":"pith:6ISX2AFV","schema_version":"1.0","canonical_sha256":"f2257d00b5aaba053ca218d1f7fcf934543b50af4357b0d740680a0865a13baf","source":{"kind":"arxiv","id":"2504.05225","version":1},"attestation_state":"computed","paper":{"title":"Vision-Language Model Predictive Control for Manipulation Planning and Trajectory Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Donghui Mao, Jiaming Chen, Ran Song, Wei Pan, Wei Zhang, Wentao Zhao, Ziyu Meng","submitted_at":"2025-04-07T16:13:09Z","abstract_excerpt":"Model Predictive Control (MPC) is a widely adopted control paradigm that leverages predictive models to estimate future system states and optimize control inputs accordingly. However, while MPC excels in planning and control, it lacks the capability for environmental perception, leading to failures in complex and unstructured scenarios. To address this limitation, we introduce Vision-Language Model Predictive Control (VLMPC), a robotic manipulation planning framework that integrates the perception power of vision-language models (VLMs) with MPC. VLMPC utilizes a conditional action sampling mod"},"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":"2504.05225","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-07T16:13:09Z","cross_cats_sorted":[],"title_canon_sha256":"2a1cd62eeea7824a303a86a438a1cfc48ebdec63a67f1785e8b42e7267f936c1","abstract_canon_sha256":"24f420b44b24d8d4ba2810d15f67350ab56feaad170d6ec87e26f1047b8968bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:35.966043Z","signature_b64":"PlPNIGmNAVLfeYlLqXtKTb80q9JXJusC+iK2IcX3XMi0gdfoA6bfNocym+9pnlVja1uiYJ5yb54Mw1KgXa/5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2257d00b5aaba053ca218d1f7fcf934543b50af4357b0d740680a0865a13baf","last_reissued_at":"2026-07-05T10:45:35.965584Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:35.965584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-Language Model Predictive Control for Manipulation Planning and Trajectory Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Donghui Mao, Jiaming Chen, Ran Song, Wei Pan, Wei Zhang, Wentao Zhao, Ziyu Meng","submitted_at":"2025-04-07T16:13:09Z","abstract_excerpt":"Model Predictive Control (MPC) is a widely adopted control paradigm that leverages predictive models to estimate future system states and optimize control inputs accordingly. However, while MPC excels in planning and control, it lacks the capability for environmental perception, leading to failures in complex and unstructured scenarios. To address this limitation, we introduce Vision-Language Model Predictive Control (VLMPC), a robotic manipulation planning framework that integrates the perception power of vision-language models (VLMs) with MPC. VLMPC utilizes a conditional action sampling mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05225","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/2504.05225/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":"2504.05225","created_at":"2026-07-05T10:45:35.965642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.05225v1","created_at":"2026-07-05T10:45:35.965642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05225","created_at":"2026-07-05T10:45:35.965642+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ISX2AFVVK5A","created_at":"2026-07-05T10:45:35.965642+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ISX2AFVVK5AKPFC","created_at":"2026-07-05T10:45:35.965642+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ISX2AFV","created_at":"2026-07-05T10:45:35.965642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07974","citing_title":"PRISM: PRior-guided Imagination Sampling in world Models","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ISX2AFVVK5AKPFCDDI7P7HZGR","json":"https://pith.science/pith/6ISX2AFVVK5AKPFCDDI7P7HZGR.json","graph_json":"https://pith.science/api/pith-number/6ISX2AFVVK5AKPFCDDI7P7HZGR/graph.json","events_json":"https://pith.science/api/pith-number/6ISX2AFVVK5AKPFCDDI7P7HZGR/events.json","paper":"https://pith.science/paper/6ISX2AFV"},"agent_actions":{"view_html":"https://pith.science/pith/6ISX2AFVVK5AKPFCDDI7P7HZGR","download_json":"https://pith.science/pith/6ISX2AFVVK5AKPFCDDI7P7HZGR.json","view_paper":"https://pith.science/paper/6ISX2AFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.05225&json=true","fetch_graph":"https://pith.science/api/pith-number/6ISX2AFVVK5AKPFCDDI7P7HZGR/graph.json","fetch_events":"https://pith.science/api/pith-number/6ISX2AFVVK5AKPFCDDI7P7HZGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ISX2AFVVK5AKPFCDDI7P7HZGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ISX2AFVVK5AKPFCDDI7P7HZGR/action/storage_attestation","attest_author":"https://pith.science/pith/6ISX2AFVVK5AKPFCDDI7P7HZGR/action/author_attestation","sign_citation":"https://pith.science/pith/6ISX2AFVVK5AKPFCDDI7P7HZGR/action/citation_signature","submit_replication":"https://pith.science/pith/6ISX2AFVVK5AKPFCDDI7P7HZGR/action/replication_record"}},"created_at":"2026-07-05T10:45:35.965642+00:00","updated_at":"2026-07-05T10:45:35.965642+00:00"}