{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JCWMPMMUYCZNLTC2DACSFDCB7Y","short_pith_number":"pith:JCWMPMMU","schema_version":"1.0","canonical_sha256":"48acc7b194c0b2d5cc5a1805228c41fe1f840a13854a1698415db93a9cd46577","source":{"kind":"arxiv","id":"2406.09598","version":1},"attestation_state":"computed","paper":{"title":"Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Edward Miller, Fan Zhang, Jade Fountain, Jakob Julian Engel, Pierre Moulon, Prithviraj Banerjee, Richard Newcombe, Robert Wang, Selen Basol, Shreyas Hampali, Sindi Shkodrani, Tomas Hodan","submitted_at":"2024-06-13T21:38:17Z","abstract_excerpt":"We introduce HOT3D, a publicly available dataset for egocentric hand and object tracking in 3D. The dataset offers over 833 minutes (more than 3.7M images) of multi-view RGB/monochrome image streams showing 19 subjects interacting with 33 diverse rigid objects, multi-modal signals such as eye gaze or scene point clouds, as well as comprehensive ground truth annotations including 3D poses of objects, hands, and cameras, and 3D models of hands and objects. In addition to simple pick-up/observe/put-down actions, HOT3D contains scenarios resembling typical actions in a kitchen, office, and living "},"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":"2406.09598","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T21:38:17Z","cross_cats_sorted":[],"title_canon_sha256":"f30a7a7476bb87cc46b264f207a0a4042680c87b8e0bea54ecbc9d2746678c8d","abstract_canon_sha256":"24e560f8ec64242eb549483404f9c7be34f0108cef12c2e3cbda91c40b77d135"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:56.718494Z","signature_b64":"LTHesJ6W461W+wdte6pSVTnE8juq0rWtp2kYOafAkgQba39yE/hoi2Aics5Opm2ZTYH9Ay2RCMn/jn4UewwaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48acc7b194c0b2d5cc5a1805228c41fe1f840a13854a1698415db93a9cd46577","last_reissued_at":"2026-07-05T08:31:56.718004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:56.718004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Edward Miller, Fan Zhang, Jade Fountain, Jakob Julian Engel, Pierre Moulon, Prithviraj Banerjee, Richard Newcombe, Robert Wang, Selen Basol, Shreyas Hampali, Sindi Shkodrani, Tomas Hodan","submitted_at":"2024-06-13T21:38:17Z","abstract_excerpt":"We introduce HOT3D, a publicly available dataset for egocentric hand and object tracking in 3D. The dataset offers over 833 minutes (more than 3.7M images) of multi-view RGB/monochrome image streams showing 19 subjects interacting with 33 diverse rigid objects, multi-modal signals such as eye gaze or scene point clouds, as well as comprehensive ground truth annotations including 3D poses of objects, hands, and cameras, and 3D models of hands and objects. In addition to simple pick-up/observe/put-down actions, HOT3D contains scenarios resembling typical actions in a kitchen, office, and living "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09598","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/2406.09598/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":"2406.09598","created_at":"2026-07-05T08:31:56.718060+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09598v1","created_at":"2026-07-05T08:31:56.718060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09598","created_at":"2026-07-05T08:31:56.718060+00:00"},{"alias_kind":"pith_short_12","alias_value":"JCWMPMMUYCZN","created_at":"2026-07-05T08:31:56.718060+00:00"},{"alias_kind":"pith_short_16","alias_value":"JCWMPMMUYCZNLTC2","created_at":"2026-07-05T08:31:56.718060+00:00"},{"alias_kind":"pith_short_8","alias_value":"JCWMPMMU","created_at":"2026-07-05T08:31:56.718060+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06468","citing_title":"EgoPolice: A Benchmark for Egocentric Video Understanding in High-Stakes Police Body-Worn Camera Footage","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.24934","citing_title":"HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05925","citing_title":"DexSynRefine: Synthesizing and Refining Human-Object Interaction Motion for Physically Feasible Dexterous Robot Actions","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15195","citing_title":"VGGT-$\\Omega$","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2507.12440","citing_title":"EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15753","citing_title":"Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18553","citing_title":"StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16797","citing_title":"EgoKit: Towards Unified Low-Cost Egocentric Data Collection with Heterogeneous Devices","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28045","citing_title":"Event6D: Event-based Novel Object 6D Pose Tracking","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03305","citing_title":"HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12498","citing_title":"EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05925","citing_title":"DexSynRefine: Synthesizing and Refining Human-Object Interaction Motion for Physically Feasible Dexterous Robot Actions","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07607","citing_title":"EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JCWMPMMUYCZNLTC2DACSFDCB7Y","json":"https://pith.science/pith/JCWMPMMUYCZNLTC2DACSFDCB7Y.json","graph_json":"https://pith.science/api/pith-number/JCWMPMMUYCZNLTC2DACSFDCB7Y/graph.json","events_json":"https://pith.science/api/pith-number/JCWMPMMUYCZNLTC2DACSFDCB7Y/events.json","paper":"https://pith.science/paper/JCWMPMMU"},"agent_actions":{"view_html":"https://pith.science/pith/JCWMPMMUYCZNLTC2DACSFDCB7Y","download_json":"https://pith.science/pith/JCWMPMMUYCZNLTC2DACSFDCB7Y.json","view_paper":"https://pith.science/paper/JCWMPMMU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09598&json=true","fetch_graph":"https://pith.science/api/pith-number/JCWMPMMUYCZNLTC2DACSFDCB7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/JCWMPMMUYCZNLTC2DACSFDCB7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JCWMPMMUYCZNLTC2DACSFDCB7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JCWMPMMUYCZNLTC2DACSFDCB7Y/action/storage_attestation","attest_author":"https://pith.science/pith/JCWMPMMUYCZNLTC2DACSFDCB7Y/action/author_attestation","sign_citation":"https://pith.science/pith/JCWMPMMUYCZNLTC2DACSFDCB7Y/action/citation_signature","submit_replication":"https://pith.science/pith/JCWMPMMUYCZNLTC2DACSFDCB7Y/action/replication_record"}},"created_at":"2026-07-05T08:31:56.718060+00:00","updated_at":"2026-07-05T08:31:56.718060+00:00"}