{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GQVEZEGV7YOJP5HJPC2OTMGCXW","short_pith_number":"pith:GQVEZEGV","schema_version":"1.0","canonical_sha256":"342a4c90d5fe1c97f4e978b4e9b0c2bd9cec247d49956e1652e66605aabdd106","source":{"kind":"arxiv","id":"2401.17217","version":2},"attestation_state":"computed","paper":{"title":"GazeGPT: Augmenting Human Capabilities using Gaze-contingent Contextual AI for Smart Eyewear","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.HC","authors_text":"Gordon Wetzstein, J. Gabriel Buckmaster, Kevin C. Boyle, Nitish Padmanaban, Robert Konrad","submitted_at":"2024-01-30T18:02:44Z","abstract_excerpt":"Multimodal large language models (LMMs) excel in world knowledge and problem-solving abilities. Through the use of a world-facing camera and contextual AI, emerging smart accessories aim to provide a seamless interface between humans and LMMs. Yet, these wearable computing systems lack an understanding of the user's attention. We introduce GazeGPT as a new user interaction paradigm for contextual AI. GazeGPT uses eye tracking to help the LMM understand which object in the world-facing camera view a user is paying attention to. Using extensive user evaluations, we show that this gaze-contingent"},"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":"2401.17217","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.HC","submitted_at":"2024-01-30T18:02:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c32bdc954a5c81f329b762ef610eb6b3b2d8e99628c5772f812c87c96b50aacf","abstract_canon_sha256":"2b2b923d057bb2b79b98f9831d6c198816abfeb6a62586ce4da9e24d04be2048"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:35.050038Z","signature_b64":"2g9fWXh5DtCTvOgr0ZEGdrtzRHEq7T/vBHsfXptyHDueLvXha9nuEUSqAjEOvv4TGhXo8wpUIhfs9nakBywvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"342a4c90d5fe1c97f4e978b4e9b0c2bd9cec247d49956e1652e66605aabdd106","last_reissued_at":"2026-07-05T07:39:35.049631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:35.049631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GazeGPT: Augmenting Human Capabilities using Gaze-contingent Contextual AI for Smart Eyewear","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.HC","authors_text":"Gordon Wetzstein, J. Gabriel Buckmaster, Kevin C. Boyle, Nitish Padmanaban, Robert Konrad","submitted_at":"2024-01-30T18:02:44Z","abstract_excerpt":"Multimodal large language models (LMMs) excel in world knowledge and problem-solving abilities. Through the use of a world-facing camera and contextual AI, emerging smart accessories aim to provide a seamless interface between humans and LMMs. Yet, these wearable computing systems lack an understanding of the user's attention. We introduce GazeGPT as a new user interaction paradigm for contextual AI. GazeGPT uses eye tracking to help the LMM understand which object in the world-facing camera view a user is paying attention to. Using extensive user evaluations, we show that this gaze-contingent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17217","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/2401.17217/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":"2401.17217","created_at":"2026-07-05T07:39:35.049687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17217v2","created_at":"2026-07-05T07:39:35.049687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17217","created_at":"2026-07-05T07:39:35.049687+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQVEZEGV7YOJ","created_at":"2026-07-05T07:39:35.049687+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQVEZEGV7YOJP5HJ","created_at":"2026-07-05T07:39:35.049687+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQVEZEGV","created_at":"2026-07-05T07:39:35.049687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00445","citing_title":"Gaze-Informed Proactive AI Assistance for Children's Picture Exploration","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03774","citing_title":"AmbientEye: A Dataset for Pupil Segmentation under Natural Ambient Infrared Illumination","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24456","citing_title":"EgoProx: Evaluating MLLMs on Egocentric 3D Proximity Reasoning Across a Cognitive Hierarchy","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2503.16548","citing_title":"SemanticScanpath: Combining Gaze and Speech for Situated Human-Robot Interaction Using LLMs","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2505.24848","citing_title":"Reading Recognition in the Wild","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2511.19629","citing_title":"SkillSight: Efficient First-Person Skill Assessment with Gaze","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03486","citing_title":"VisionClaw: Always-On AI Agents through Smart Glasses","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07859","citing_title":"EyeCue: Driver Cognitive Distraction Detection via Gaze-Empowered Egocentric Video Understanding","ref_index":97,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQVEZEGV7YOJP5HJPC2OTMGCXW","json":"https://pith.science/pith/GQVEZEGV7YOJP5HJPC2OTMGCXW.json","graph_json":"https://pith.science/api/pith-number/GQVEZEGV7YOJP5HJPC2OTMGCXW/graph.json","events_json":"https://pith.science/api/pith-number/GQVEZEGV7YOJP5HJPC2OTMGCXW/events.json","paper":"https://pith.science/paper/GQVEZEGV"},"agent_actions":{"view_html":"https://pith.science/pith/GQVEZEGV7YOJP5HJPC2OTMGCXW","download_json":"https://pith.science/pith/GQVEZEGV7YOJP5HJPC2OTMGCXW.json","view_paper":"https://pith.science/paper/GQVEZEGV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17217&json=true","fetch_graph":"https://pith.science/api/pith-number/GQVEZEGV7YOJP5HJPC2OTMGCXW/graph.json","fetch_events":"https://pith.science/api/pith-number/GQVEZEGV7YOJP5HJPC2OTMGCXW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQVEZEGV7YOJP5HJPC2OTMGCXW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQVEZEGV7YOJP5HJPC2OTMGCXW/action/storage_attestation","attest_author":"https://pith.science/pith/GQVEZEGV7YOJP5HJPC2OTMGCXW/action/author_attestation","sign_citation":"https://pith.science/pith/GQVEZEGV7YOJP5HJPC2OTMGCXW/action/citation_signature","submit_replication":"https://pith.science/pith/GQVEZEGV7YOJP5HJPC2OTMGCXW/action/replication_record"}},"created_at":"2026-07-05T07:39:35.049687+00:00","updated_at":"2026-07-05T07:39:35.049687+00:00"}