{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SXMGO4WUE3C4LY6ZNRMCXMEK5K","short_pith_number":"pith:SXMGO4WU","schema_version":"1.0","canonical_sha256":"95d86772d426c5c5e3d96c582bb08aeabb15f8e7dd4f9cfc7895ed1bd0847a09","source":{"kind":"arxiv","id":"2507.17379","version":1},"attestation_state":"computed","paper":{"title":"Language-Conditioned Open-Vocabulary Mobile Manipulation with Pretrained Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Dong Zhou, Guanghui Sun, Junqiao Wang, Shen Tan, Xiangyu Shao","submitted_at":"2025-07-23T10:23:15Z","abstract_excerpt":"Open-vocabulary mobile manipulation (OVMM) that involves the handling of novel and unseen objects across different workspaces remains a significant challenge for real-world robotic applications. In this paper, we propose a novel Language-conditioned Open-Vocabulary Mobile Manipulation framework, named LOVMM, incorporating the large language model (LLM) and vision-language model (VLM) to tackle various mobile manipulation tasks in household environments. Our approach is capable of solving various OVMM tasks with free-form natural language instructions (e.g. \"toss the food boxes on the office ro"},"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":"2507.17379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-23T10:23:15Z","cross_cats_sorted":[],"title_canon_sha256":"813d76c5e3c742ddaa5fa2c206686a414d8b0e126ff835aa63ea3ba3087fd019","abstract_canon_sha256":"f62bc9eab13fa815e41911782a574cdbb8fb23a85952c14e7cebd7f811af1ea0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:06.577563Z","signature_b64":"elo0r9+sEn5Zb7S+E9i9IVbENVhG7jeCTzSvo8USJyM4ca7BnZ2pp+TnySbyuJC2Ny7WlDl5oOCa1W+3ETWCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95d86772d426c5c5e3d96c582bb08aeabb15f8e7dd4f9cfc7895ed1bd0847a09","last_reissued_at":"2026-07-05T11:42:06.576932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:06.576932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-Conditioned Open-Vocabulary Mobile Manipulation with Pretrained Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Dong Zhou, Guanghui Sun, Junqiao Wang, Shen Tan, Xiangyu Shao","submitted_at":"2025-07-23T10:23:15Z","abstract_excerpt":"Open-vocabulary mobile manipulation (OVMM) that involves the handling of novel and unseen objects across different workspaces remains a significant challenge for real-world robotic applications. In this paper, we propose a novel Language-conditioned Open-Vocabulary Mobile Manipulation framework, named LOVMM, incorporating the large language model (LLM) and vision-language model (VLM) to tackle various mobile manipulation tasks in household environments. Our approach is capable of solving various OVMM tasks with free-form natural language instructions (e.g. \"toss the food boxes on the office ro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17379","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/2507.17379/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":"2507.17379","created_at":"2026-07-05T11:42:06.577013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.17379v1","created_at":"2026-07-05T11:42:06.577013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17379","created_at":"2026-07-05T11:42:06.577013+00:00"},{"alias_kind":"pith_short_12","alias_value":"SXMGO4WUE3C4","created_at":"2026-07-05T11:42:06.577013+00:00"},{"alias_kind":"pith_short_16","alias_value":"SXMGO4WUE3C4LY6Z","created_at":"2026-07-05T11:42:06.577013+00:00"},{"alias_kind":"pith_short_8","alias_value":"SXMGO4WU","created_at":"2026-07-05T11:42:06.577013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12910","citing_title":"Bounding Boxes as Goals: Language-Conditioned Grasping via Neuro-Symbolic Planning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26256","citing_title":"Personalizing Embodied Multimodal Large Language Model Agents over Long-term User Interactions","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SXMGO4WUE3C4LY6ZNRMCXMEK5K","json":"https://pith.science/pith/SXMGO4WUE3C4LY6ZNRMCXMEK5K.json","graph_json":"https://pith.science/api/pith-number/SXMGO4WUE3C4LY6ZNRMCXMEK5K/graph.json","events_json":"https://pith.science/api/pith-number/SXMGO4WUE3C4LY6ZNRMCXMEK5K/events.json","paper":"https://pith.science/paper/SXMGO4WU"},"agent_actions":{"view_html":"https://pith.science/pith/SXMGO4WUE3C4LY6ZNRMCXMEK5K","download_json":"https://pith.science/pith/SXMGO4WUE3C4LY6ZNRMCXMEK5K.json","view_paper":"https://pith.science/paper/SXMGO4WU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.17379&json=true","fetch_graph":"https://pith.science/api/pith-number/SXMGO4WUE3C4LY6ZNRMCXMEK5K/graph.json","fetch_events":"https://pith.science/api/pith-number/SXMGO4WUE3C4LY6ZNRMCXMEK5K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SXMGO4WUE3C4LY6ZNRMCXMEK5K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SXMGO4WUE3C4LY6ZNRMCXMEK5K/action/storage_attestation","attest_author":"https://pith.science/pith/SXMGO4WUE3C4LY6ZNRMCXMEK5K/action/author_attestation","sign_citation":"https://pith.science/pith/SXMGO4WUE3C4LY6ZNRMCXMEK5K/action/citation_signature","submit_replication":"https://pith.science/pith/SXMGO4WUE3C4LY6ZNRMCXMEK5K/action/replication_record"}},"created_at":"2026-07-05T11:42:06.577013+00:00","updated_at":"2026-07-05T11:42:06.577013+00:00"}