{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VTIF4C5BK5VGTTU3T5QSQILXES","short_pith_number":"pith:VTIF4C5B","schema_version":"1.0","canonical_sha256":"acd05e0ba1576a69ce9b9f6128217724afdf5741c6a31e5e9ee0ddc48b600822","source":{"kind":"arxiv","id":"2406.18115","version":1},"attestation_state":"computed","paper":{"title":"Open-vocabulary Mobile Manipulation in Unseen Dynamic Environments with 3D Semantic Maps","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Dicong Qiu, Hui Xiong, Junwei Liang, Wenzong Ma, Zhenfu Pan","submitted_at":"2024-06-26T07:06:42Z","abstract_excerpt":"Open-Vocabulary Mobile Manipulation (OVMM) is a crucial capability for autonomous robots, especially when faced with the challenges posed by unknown and dynamic environments. This task requires robots to explore and build a semantic understanding of their surroundings, generate feasible plans to achieve manipulation goals, adapt to environmental changes, and comprehend natural language instructions from humans. To address these challenges, we propose a novel framework that leverages the zero-shot detection and grounded recognition capabilities of pretraining visual-language models (VLMs) combi"},"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":"2406.18115","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-26T07:06:42Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"c16ff72194a2c27ecc4628482b4b2d5536afea1302a24cc24077f613d3b5f335","abstract_canon_sha256":"3b8f844e75799772f1b0672b72c1ed7909ac4b7ea7ae39876c64244b59abecc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:55.404786Z","signature_b64":"3j3G+J0QPS3Ym2Tq6Yl4Wyusdu2rT8bW5fDeoBIwP/zRYZlvcIG00ZipXYYWv0h1I0Jl+uVKmHDofufq/KZjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acd05e0ba1576a69ce9b9f6128217724afdf5741c6a31e5e9ee0ddc48b600822","last_reissued_at":"2026-07-05T08:36:55.404451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:55.404451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-vocabulary Mobile Manipulation in Unseen Dynamic Environments with 3D Semantic Maps","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Dicong Qiu, Hui Xiong, Junwei Liang, Wenzong Ma, Zhenfu Pan","submitted_at":"2024-06-26T07:06:42Z","abstract_excerpt":"Open-Vocabulary Mobile Manipulation (OVMM) is a crucial capability for autonomous robots, especially when faced with the challenges posed by unknown and dynamic environments. This task requires robots to explore and build a semantic understanding of their surroundings, generate feasible plans to achieve manipulation goals, adapt to environmental changes, and comprehend natural language instructions from humans. To address these challenges, we propose a novel framework that leverages the zero-shot detection and grounded recognition capabilities of pretraining visual-language models (VLMs) combi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18115","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/2406.18115/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":"2406.18115","created_at":"2026-07-05T08:36:55.404506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18115v1","created_at":"2026-07-05T08:36:55.404506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18115","created_at":"2026-07-05T08:36:55.404506+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTIF4C5BK5VG","created_at":"2026-07-05T08:36:55.404506+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTIF4C5BK5VGTTU3","created_at":"2026-07-05T08:36:55.404506+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTIF4C5B","created_at":"2026-07-05T08:36:55.404506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.16054","citing_title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2502.19417","citing_title":"Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25323","citing_title":"ANCHOR: A Physically Grounded Closed-Loop Framework for Robust Home-Service Mobile Manipulation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VTIF4C5BK5VGTTU3T5QSQILXES","json":"https://pith.science/pith/VTIF4C5BK5VGTTU3T5QSQILXES.json","graph_json":"https://pith.science/api/pith-number/VTIF4C5BK5VGTTU3T5QSQILXES/graph.json","events_json":"https://pith.science/api/pith-number/VTIF4C5BK5VGTTU3T5QSQILXES/events.json","paper":"https://pith.science/paper/VTIF4C5B"},"agent_actions":{"view_html":"https://pith.science/pith/VTIF4C5BK5VGTTU3T5QSQILXES","download_json":"https://pith.science/pith/VTIF4C5BK5VGTTU3T5QSQILXES.json","view_paper":"https://pith.science/paper/VTIF4C5B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18115&json=true","fetch_graph":"https://pith.science/api/pith-number/VTIF4C5BK5VGTTU3T5QSQILXES/graph.json","fetch_events":"https://pith.science/api/pith-number/VTIF4C5BK5VGTTU3T5QSQILXES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTIF4C5BK5VGTTU3T5QSQILXES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTIF4C5BK5VGTTU3T5QSQILXES/action/storage_attestation","attest_author":"https://pith.science/pith/VTIF4C5BK5VGTTU3T5QSQILXES/action/author_attestation","sign_citation":"https://pith.science/pith/VTIF4C5BK5VGTTU3T5QSQILXES/action/citation_signature","submit_replication":"https://pith.science/pith/VTIF4C5BK5VGTTU3T5QSQILXES/action/replication_record"}},"created_at":"2026-07-05T08:36:55.404506+00:00","updated_at":"2026-07-05T08:36:55.404506+00:00"}