{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YEGMRQJVPHQBTVB6YFHMFUH5WH","short_pith_number":"pith:YEGMRQJV","schema_version":"1.0","canonical_sha256":"c10cc8c13579e019d43ec14ec2d0fdb1e7e17f1a283aaa51ff82a45b3fc284a1","source":{"kind":"arxiv","id":"2403.02274","version":1},"attestation_state":"computed","paper":{"title":"NatSGD: A Dataset with Speech, Gestures, and Demonstrations for Robot Learning in Natural Human-Robot Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Cornelia Fermuller, Ge Gao, Saketh Banagiri, Snehesh Shrestha, Yantian Zha, Yiannis Aloimonos","submitted_at":"2024-03-04T18:02:41Z","abstract_excerpt":"Recent advancements in multimodal Human-Robot Interaction (HRI) datasets have highlighted the fusion of speech and gesture, expanding robots' capabilities to absorb explicit and implicit HRI insights. However, existing speech-gesture HRI datasets often focus on elementary tasks, like object pointing and pushing, revealing limitations in scaling to intricate domains and prioritizing human command data over robot behavior records. To bridge these gaps, we introduce NatSGD, a multimodal HRI dataset encompassing human commands through speech and gestures that are natural, synchronized with robot b"},"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":"2403.02274","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-04T18:02:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1a5b8164c4e9e2ad8c0cf1c0a451f5b84a125f5a180b0317f2785d422e84abe4","abstract_canon_sha256":"a107d7f0cd1cad373f79d61cd160c4ce64e9b46d55e4e2f12eb6852608e6d55f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:58.748110Z","signature_b64":"u9xs+i4TSpPwjfbYAXDS1S3rErIjI3EdhDoaYfV6To4grV5WpLfESzJq6PUOb6mGC1n2dQiamMX3eymTOysmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c10cc8c13579e019d43ec14ec2d0fdb1e7e17f1a283aaa51ff82a45b3fc284a1","last_reissued_at":"2026-07-05T07:51:58.747624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:58.747624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NatSGD: A Dataset with Speech, Gestures, and Demonstrations for Robot Learning in Natural Human-Robot Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Cornelia Fermuller, Ge Gao, Saketh Banagiri, Snehesh Shrestha, Yantian Zha, Yiannis Aloimonos","submitted_at":"2024-03-04T18:02:41Z","abstract_excerpt":"Recent advancements in multimodal Human-Robot Interaction (HRI) datasets have highlighted the fusion of speech and gesture, expanding robots' capabilities to absorb explicit and implicit HRI insights. However, existing speech-gesture HRI datasets often focus on elementary tasks, like object pointing and pushing, revealing limitations in scaling to intricate domains and prioritizing human command data over robot behavior records. To bridge these gaps, we introduce NatSGD, a multimodal HRI dataset encompassing human commands through speech and gestures that are natural, synchronized with robot b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02274","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/2403.02274/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":"2403.02274","created_at":"2026-07-05T07:51:58.747684+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02274v1","created_at":"2026-07-05T07:51:58.747684+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02274","created_at":"2026-07-05T07:51:58.747684+00:00"},{"alias_kind":"pith_short_12","alias_value":"YEGMRQJVPHQB","created_at":"2026-07-05T07:51:58.747684+00:00"},{"alias_kind":"pith_short_16","alias_value":"YEGMRQJVPHQBTVB6","created_at":"2026-07-05T07:51:58.747684+00:00"},{"alias_kind":"pith_short_8","alias_value":"YEGMRQJV","created_at":"2026-07-05T07:51:58.747684+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03855","citing_title":"Evaluating Generative Models as Interactive Emergent Representations of Human-Like Collaborative Behavior","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03855","citing_title":"Evaluating Generative Models as Interactive Emergent Representations of Human-Like Collaborative Behavior","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YEGMRQJVPHQBTVB6YFHMFUH5WH","json":"https://pith.science/pith/YEGMRQJVPHQBTVB6YFHMFUH5WH.json","graph_json":"https://pith.science/api/pith-number/YEGMRQJVPHQBTVB6YFHMFUH5WH/graph.json","events_json":"https://pith.science/api/pith-number/YEGMRQJVPHQBTVB6YFHMFUH5WH/events.json","paper":"https://pith.science/paper/YEGMRQJV"},"agent_actions":{"view_html":"https://pith.science/pith/YEGMRQJVPHQBTVB6YFHMFUH5WH","download_json":"https://pith.science/pith/YEGMRQJVPHQBTVB6YFHMFUH5WH.json","view_paper":"https://pith.science/paper/YEGMRQJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02274&json=true","fetch_graph":"https://pith.science/api/pith-number/YEGMRQJVPHQBTVB6YFHMFUH5WH/graph.json","fetch_events":"https://pith.science/api/pith-number/YEGMRQJVPHQBTVB6YFHMFUH5WH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YEGMRQJVPHQBTVB6YFHMFUH5WH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YEGMRQJVPHQBTVB6YFHMFUH5WH/action/storage_attestation","attest_author":"https://pith.science/pith/YEGMRQJVPHQBTVB6YFHMFUH5WH/action/author_attestation","sign_citation":"https://pith.science/pith/YEGMRQJVPHQBTVB6YFHMFUH5WH/action/citation_signature","submit_replication":"https://pith.science/pith/YEGMRQJVPHQBTVB6YFHMFUH5WH/action/replication_record"}},"created_at":"2026-07-05T07:51:58.747684+00:00","updated_at":"2026-07-05T07:51:58.747684+00:00"}