{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KLB32CVUVMIQANKPWWZZD4KLKU","short_pith_number":"pith:KLB32CVU","schema_version":"1.0","canonical_sha256":"52c3bd0ab4ab1100354fb5b391f14b5538a4bfcf943a2c93d0a67abbd872d6f1","source":{"kind":"arxiv","id":"2410.06237","version":1},"attestation_state":"computed","paper":{"title":"BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Albert Yu, Roberto Mart\\'in-Mart\\'in, Rutav Shah, Yifeng Zhu, Yuke Zhu","submitted_at":"2024-10-08T17:52:29Z","abstract_excerpt":"To operate at a building scale, service robots must perform very long-horizon mobile manipulation tasks by navigating to different rooms, accessing different floors, and interacting with a wide and unseen range of everyday objects. We refer to these tasks as Building-wide Mobile Manipulation. To tackle these inherently long-horizon tasks, we introduce BUMBLE, a unified Vision-Language Model (VLM)-based framework integrating open-world RGBD perception, a wide spectrum of gross-to-fine motor skills, and dual-layered memory. Our extensive evaluation (90+ hours) indicates that BUMBLE outperforms m"},"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":"2410.06237","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-08T17:52:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"18ff0fdb92af2efb0e7f2fe844e45c64456389f997e17deb5ce7f0a4969851de","abstract_canon_sha256":"2f82383129402b813d06dc3e6ef1bb3086b70745399a25ee58891a804d0a5a42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:58.405796Z","signature_b64":"yohPXw2+2tr/ZCVSHcap5HfdC0vbrV9v8Vm9qUDHx9HGiMsLY20N0qvMG/aGLkBAWf0wBdGmV/EcPTjlKo/BCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52c3bd0ab4ab1100354fb5b391f14b5538a4bfcf943a2c93d0a67abbd872d6f1","last_reissued_at":"2026-07-05T09:17:58.405338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:58.405338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Albert Yu, Roberto Mart\\'in-Mart\\'in, Rutav Shah, Yifeng Zhu, Yuke Zhu","submitted_at":"2024-10-08T17:52:29Z","abstract_excerpt":"To operate at a building scale, service robots must perform very long-horizon mobile manipulation tasks by navigating to different rooms, accessing different floors, and interacting with a wide and unseen range of everyday objects. We refer to these tasks as Building-wide Mobile Manipulation. To tackle these inherently long-horizon tasks, we introduce BUMBLE, a unified Vision-Language Model (VLM)-based framework integrating open-world RGBD perception, a wide spectrum of gross-to-fine motor skills, and dual-layered memory. Our extensive evaluation (90+ hours) indicates that BUMBLE outperforms m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06237","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/2410.06237/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":"2410.06237","created_at":"2026-07-05T09:17:58.405404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.06237v1","created_at":"2026-07-05T09:17:58.405404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06237","created_at":"2026-07-05T09:17:58.405404+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLB32CVUVMIQ","created_at":"2026-07-05T09:17:58.405404+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLB32CVUVMIQANKP","created_at":"2026-07-05T09:17:58.405404+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLB32CVU","created_at":"2026-07-05T09:17:58.405404+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":70,"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":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00943","citing_title":"ARIS: Agentic and Relationship Intelligence System for Social Robots","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KLB32CVUVMIQANKPWWZZD4KLKU","json":"https://pith.science/pith/KLB32CVUVMIQANKPWWZZD4KLKU.json","graph_json":"https://pith.science/api/pith-number/KLB32CVUVMIQANKPWWZZD4KLKU/graph.json","events_json":"https://pith.science/api/pith-number/KLB32CVUVMIQANKPWWZZD4KLKU/events.json","paper":"https://pith.science/paper/KLB32CVU"},"agent_actions":{"view_html":"https://pith.science/pith/KLB32CVUVMIQANKPWWZZD4KLKU","download_json":"https://pith.science/pith/KLB32CVUVMIQANKPWWZZD4KLKU.json","view_paper":"https://pith.science/paper/KLB32CVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.06237&json=true","fetch_graph":"https://pith.science/api/pith-number/KLB32CVUVMIQANKPWWZZD4KLKU/graph.json","fetch_events":"https://pith.science/api/pith-number/KLB32CVUVMIQANKPWWZZD4KLKU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLB32CVUVMIQANKPWWZZD4KLKU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLB32CVUVMIQANKPWWZZD4KLKU/action/storage_attestation","attest_author":"https://pith.science/pith/KLB32CVUVMIQANKPWWZZD4KLKU/action/author_attestation","sign_citation":"https://pith.science/pith/KLB32CVUVMIQANKPWWZZD4KLKU/action/citation_signature","submit_replication":"https://pith.science/pith/KLB32CVUVMIQANKPWWZZD4KLKU/action/replication_record"}},"created_at":"2026-07-05T09:17:58.405404+00:00","updated_at":"2026-07-05T09:17:58.405404+00:00"}