{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ATQ3YSCSPPNXWDBJDBPC6P62NZ","short_pith_number":"pith:ATQ3YSCS","schema_version":"1.0","canonical_sha256":"04e1bc48527bdb7b0c29185e2f3fda6e56b68627dfe50f85e10c8b4e11823af8","source":{"kind":"arxiv","id":"2409.20548","version":2},"attestation_state":"computed","paper":{"title":"Robi Butler: Multimodal Remote Interaction with a Household Robot Assistant","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.RO","authors_text":"Anshul Gupta, Anxing Xiao, Cunjun Yu, David Hsu, Kaixin Li, Nuwan Janaka, Tianrun Hu","submitted_at":"2024-09-30T17:49:09Z","abstract_excerpt":"Imagine a future when we can Zoom-call a robot to manage household chores remotely. This work takes one step in this direction. Robi Butler is a new household robot assistant that enables seamless multimodal remote interaction. It allows the human user to monitor its environment from a first-person view, issue voice or text commands, and specify target objects through hand-pointing gestures. At its core, a high-level behavior module, powered by Large Language Models (LLMs), interprets multimodal instructions to generate multistep action plans. Each plan consists of open-vocabulary primitives s"},"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":"2409.20548","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-30T17:49:09Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"d879cf0fadcb8a9637c064295ce8bccd06d07ec19e1ef7bbaae550a6caf4cfcb","abstract_canon_sha256":"2aa2e554ae75171fc3e85c096c67fcdaf6700f4177689a9448b64bd300946494"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:15.649573Z","signature_b64":"0SQlCZc2i4Patwnqvi2qq0o4cRB9TsffEDYvUeRVyo6QcCj2V1ogoOzaaW8WOBcnN3jyrwaipDrt6rKffiR+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04e1bc48527bdb7b0c29185e2f3fda6e56b68627dfe50f85e10c8b4e11823af8","last_reissued_at":"2026-07-05T10:27:15.648957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:15.648957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robi Butler: Multimodal Remote Interaction with a Household Robot Assistant","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.RO","authors_text":"Anshul Gupta, Anxing Xiao, Cunjun Yu, David Hsu, Kaixin Li, Nuwan Janaka, Tianrun Hu","submitted_at":"2024-09-30T17:49:09Z","abstract_excerpt":"Imagine a future when we can Zoom-call a robot to manage household chores remotely. This work takes one step in this direction. Robi Butler is a new household robot assistant that enables seamless multimodal remote interaction. It allows the human user to monitor its environment from a first-person view, issue voice or text commands, and specify target objects through hand-pointing gestures. At its core, a high-level behavior module, powered by Large Language Models (LLMs), interprets multimodal instructions to generate multistep action plans. Each plan consists of open-vocabulary primitives s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20548","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/2409.20548/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":"2409.20548","created_at":"2026-07-05T10:27:15.649024+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.20548v2","created_at":"2026-07-05T10:27:15.649024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20548","created_at":"2026-07-05T10:27:15.649024+00:00"},{"alias_kind":"pith_short_12","alias_value":"ATQ3YSCSPPNX","created_at":"2026-07-05T10:27:15.649024+00:00"},{"alias_kind":"pith_short_16","alias_value":"ATQ3YSCSPPNXWDBJ","created_at":"2026-07-05T10:27:15.649024+00:00"},{"alias_kind":"pith_short_8","alias_value":"ATQ3YSCS","created_at":"2026-07-05T10:27:15.649024+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06537","citing_title":"UniLM-Nav: A Unified Framework for Zero-Shot Last-Mile Navigation","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.26256","citing_title":"Personalizing Embodied Multimodal Large Language Model Agents over Long-term User Interactions","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2602.03433","citing_title":"When control meets large language models: From words to dynamics","ref_index":199,"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":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02487","citing_title":"Visibility-Aware Mobile Grasping in Dynamic Environments","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02487","citing_title":"Visibility-Aware Mobile Grasping in Dynamic Environments","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ATQ3YSCSPPNXWDBJDBPC6P62NZ","json":"https://pith.science/pith/ATQ3YSCSPPNXWDBJDBPC6P62NZ.json","graph_json":"https://pith.science/api/pith-number/ATQ3YSCSPPNXWDBJDBPC6P62NZ/graph.json","events_json":"https://pith.science/api/pith-number/ATQ3YSCSPPNXWDBJDBPC6P62NZ/events.json","paper":"https://pith.science/paper/ATQ3YSCS"},"agent_actions":{"view_html":"https://pith.science/pith/ATQ3YSCSPPNXWDBJDBPC6P62NZ","download_json":"https://pith.science/pith/ATQ3YSCSPPNXWDBJDBPC6P62NZ.json","view_paper":"https://pith.science/paper/ATQ3YSCS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.20548&json=true","fetch_graph":"https://pith.science/api/pith-number/ATQ3YSCSPPNXWDBJDBPC6P62NZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ATQ3YSCSPPNXWDBJDBPC6P62NZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ATQ3YSCSPPNXWDBJDBPC6P62NZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ATQ3YSCSPPNXWDBJDBPC6P62NZ/action/storage_attestation","attest_author":"https://pith.science/pith/ATQ3YSCSPPNXWDBJDBPC6P62NZ/action/author_attestation","sign_citation":"https://pith.science/pith/ATQ3YSCSPPNXWDBJDBPC6P62NZ/action/citation_signature","submit_replication":"https://pith.science/pith/ATQ3YSCSPPNXWDBJDBPC6P62NZ/action/replication_record"}},"created_at":"2026-07-05T10:27:15.649024+00:00","updated_at":"2026-07-05T10:27:15.649024+00:00"}