{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:N23LRJVU7VCXMHY2TVZFE2XGSA","short_pith_number":"pith:N23LRJVU","canonical_record":{"source":{"id":"2503.16492","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.HC","submitted_at":"2025-03-11T02:30:15Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"d86472266b7d551eb13e436f548a673c811bb4cd929b7c8246d2bd81d5fd8879","abstract_canon_sha256":"716c614b41c3e5724e678de778acf8b50cefd97037c51874355b41ef72394957"},"schema_version":"1.0"},"canonical_sha256":"6eb6b8a6b4fd45761f1a9d72526ae69022bb5be5d87e62a554ab0d40c456cbb5","source":{"kind":"arxiv","id":"2503.16492","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.16492","created_at":"2026-05-20T00:05:27Z"},{"alias_kind":"arxiv_version","alias_value":"2503.16492v3","created_at":"2026-05-20T00:05:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16492","created_at":"2026-05-20T00:05:27Z"},{"alias_kind":"pith_short_12","alias_value":"N23LRJVU7VCX","created_at":"2026-05-20T00:05:27Z"},{"alias_kind":"pith_short_16","alias_value":"N23LRJVU7VCXMHY2","created_at":"2026-05-20T00:05:27Z"},{"alias_kind":"pith_short_8","alias_value":"N23LRJVU","created_at":"2026-05-20T00:05:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:N23LRJVU7VCXMHY2TVZFE2XGSA","target":"record","payload":{"canonical_record":{"source":{"id":"2503.16492","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.HC","submitted_at":"2025-03-11T02:30:15Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"d86472266b7d551eb13e436f548a673c811bb4cd929b7c8246d2bd81d5fd8879","abstract_canon_sha256":"716c614b41c3e5724e678de778acf8b50cefd97037c51874355b41ef72394957"},"schema_version":"1.0"},"canonical_sha256":"6eb6b8a6b4fd45761f1a9d72526ae69022bb5be5d87e62a554ab0d40c456cbb5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:27.838456Z","signature_b64":"rDHeYt5HUmSGd2UdzS0yJU7mL385lXvpulWY4VC4ojc7EXN2MHrFmIaSRV8gqpFmzqiCOlmUMKbZ6HUtasxbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6eb6b8a6b4fd45761f1a9d72526ae69022bb5be5d87e62a554ab0d40c456cbb5","last_reissued_at":"2026-05-20T00:05:27.837644Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:27.837644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.16492","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2gys8efx9MTLnOxmMhrZ8+NhPI8lw9rzovNBpDUkM1XG+xeFom0KAgxXtmGQ/BMINGIm+mI9zpaHL24OPudGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T05:27:26.699694Z"},"content_sha256":"bc1ee440ec02df0eb9bbbf97ad183dbf94ed89188e87f15e55035d3460bbd8de","schema_version":"1.0","event_id":"sha256:bc1ee440ec02df0eb9bbbf97ad183dbf94ed89188e87f15e55035d3460bbd8de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:N23LRJVU7VCXMHY2TVZFE2XGSA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FAM-HRI: Foundation-Model Assisted Multi-Modal Human-Robot Interaction Combining Gaze and Speech","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.HC","authors_text":"Andreas Zell, Benjamin Kiefer, Boya Zhang, Peizheng Li, Shenghai Yuan, Tianchen Deng, Yuzhi Lai","submitted_at":"2025-03-11T02:30:15Z","abstract_excerpt":"ffective Human-Robot Interaction (HRI) is crucial for enhancing accessibility and usability in real-world robotics applications. However, existing solutions often rely on gesture- only or language-only commands, making interaction inefficient and ambiguous, particularly for users with physical impairments. In this paper, we introduce FAM-HRI, an efficient multimodal framework for HRI that integrates language and gaze inputs via foundation models. By leveraging lightweight Meta ARIA glasses, our system captures real-time multimodal signals and utilizes large language models (LLMs) to fuse user "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16492","kind":"arxiv","version":3},"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/2503.16492/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ogC5QKw+vH9cohK0QS1IMTZtMrlBpSliUTBrm/Xd7kadIWz0JyuzSXGGduTW04a6EFmSOHYzJsquvf3FeegoAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T05:27:26.700433Z"},"content_sha256":"fc9d989881af40d4b92662f53544457fcdc945c42ad3242f926b248bc16ba74a","schema_version":"1.0","event_id":"sha256:fc9d989881af40d4b92662f53544457fcdc945c42ad3242f926b248bc16ba74a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N23LRJVU7VCXMHY2TVZFE2XGSA/bundle.json","state_url":"https://pith.science/pith/N23LRJVU7VCXMHY2TVZFE2XGSA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N23LRJVU7VCXMHY2TVZFE2XGSA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-24T05:27:26Z","links":{"resolver":"https://pith.science/pith/N23LRJVU7VCXMHY2TVZFE2XGSA","bundle":"https://pith.science/pith/N23LRJVU7VCXMHY2TVZFE2XGSA/bundle.json","state":"https://pith.science/pith/N23LRJVU7VCXMHY2TVZFE2XGSA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N23LRJVU7VCXMHY2TVZFE2XGSA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N23LRJVU7VCXMHY2TVZFE2XGSA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"716c614b41c3e5724e678de778acf8b50cefd97037c51874355b41ef72394957","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.HC","submitted_at":"2025-03-11T02:30:15Z","title_canon_sha256":"d86472266b7d551eb13e436f548a673c811bb4cd929b7c8246d2bd81d5fd8879"},"schema_version":"1.0","source":{"id":"2503.16492","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.16492","created_at":"2026-05-20T00:05:27Z"},{"alias_kind":"arxiv_version","alias_value":"2503.16492v3","created_at":"2026-05-20T00:05:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16492","created_at":"2026-05-20T00:05:27Z"},{"alias_kind":"pith_short_12","alias_value":"N23LRJVU7VCX","created_at":"2026-05-20T00:05:27Z"},{"alias_kind":"pith_short_16","alias_value":"N23LRJVU7VCXMHY2","created_at":"2026-05-20T00:05:27Z"},{"alias_kind":"pith_short_8","alias_value":"N23LRJVU","created_at":"2026-05-20T00:05:27Z"}],"graph_snapshots":[{"event_id":"sha256:fc9d989881af40d4b92662f53544457fcdc945c42ad3242f926b248bc16ba74a","target":"graph","created_at":"2026-05-20T00:05:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.16492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"ffective Human-Robot Interaction (HRI) is crucial for enhancing accessibility and usability in real-world robotics applications. However, existing solutions often rely on gesture- only or language-only commands, making interaction inefficient and ambiguous, particularly for users with physical impairments. In this paper, we introduce FAM-HRI, an efficient multimodal framework for HRI that integrates language and gaze inputs via foundation models. By leveraging lightweight Meta ARIA glasses, our system captures real-time multimodal signals and utilizes large language models (LLMs) to fuse user ","authors_text":"Andreas Zell, Benjamin Kiefer, Boya Zhang, Peizheng Li, Shenghai Yuan, Tianchen Deng, Yuzhi Lai","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.HC","submitted_at":"2025-03-11T02:30:15Z","title":"FAM-HRI: Foundation-Model Assisted Multi-Modal Human-Robot Interaction Combining Gaze and Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16492","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bc1ee440ec02df0eb9bbbf97ad183dbf94ed89188e87f15e55035d3460bbd8de","target":"record","created_at":"2026-05-20T00:05:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"716c614b41c3e5724e678de778acf8b50cefd97037c51874355b41ef72394957","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.HC","submitted_at":"2025-03-11T02:30:15Z","title_canon_sha256":"d86472266b7d551eb13e436f548a673c811bb4cd929b7c8246d2bd81d5fd8879"},"schema_version":"1.0","source":{"id":"2503.16492","kind":"arxiv","version":3}},"canonical_sha256":"6eb6b8a6b4fd45761f1a9d72526ae69022bb5be5d87e62a554ab0d40c456cbb5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6eb6b8a6b4fd45761f1a9d72526ae69022bb5be5d87e62a554ab0d40c456cbb5","first_computed_at":"2026-05-20T00:05:27.837644Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:27.837644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rDHeYt5HUmSGd2UdzS0yJU7mL385lXvpulWY4VC4ojc7EXN2MHrFmIaSRV8gqpFmzqiCOlmUMKbZ6HUtasxbBw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:27.838456Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.16492","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc1ee440ec02df0eb9bbbf97ad183dbf94ed89188e87f15e55035d3460bbd8de","sha256:fc9d989881af40d4b92662f53544457fcdc945c42ad3242f926b248bc16ba74a"],"state_sha256":"60380cb3ebe3802f659fe9fe156e121faa1424a961497093c697d869f7090995"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n9iUttJrfYf5CjzXYZ5k0YtVc/1ZMSfjQMMUoSlwnv99eJMBU2C+p2XWy1XYf66obKrjbQDp9T1mD/RogFjMCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T05:27:26.704012Z","bundle_sha256":"359a7b3cad4f92f08f4516e97aac16dcda752136a2d20258b39c3f6357b1da8b"}}