{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VC4XHWIORUBBNJHGA6MXDSEDLN","short_pith_number":"pith:VC4XHWIO","schema_version":"1.0","canonical_sha256":"a8b973d90e8d0216a4e6079971c8835b670e39c46bb3f861ad87dd0d37786ffd","source":{"kind":"arxiv","id":"2411.19167","version":2},"attestation_state":"computed","paper":{"title":"HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Edward Miller, Fan Zhang, Jade Fountain, Jakob Julian Engel, Linguang Zhang, Pierre Moulon, Prithviraj Banerjee, Richard Newcombe, Robert Wang, Selen Basol, Shangchen Han, Shreyas Hampali, Sindi Shkodrani, Tomas Hodan","submitted_at":"2024-11-28T14:09:42Z","abstract_excerpt":"We introduce HOT3D, a publicly available dataset for egocentric hand and object tracking in 3D. The dataset offers over 833 minutes (3.7M+ images) of recordings that feature 19 subjects interacting with 33 diverse rigid objects. In addition to simple pick-up, observe, and put-down actions, the subjects perform actions typical for a kitchen, office, and living room environment. The recordings include multiple synchronized data streams containing egocentric multi-view RGB/monochrome images, eye gaze signal, scene point clouds, and 3D poses of cameras, hands, and objects. The dataset is recorded "},"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":"2411.19167","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-28T14:09:42Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"12eab15ba2b9d8101bdbb7aca26c4071cd7a67f40a68171fc4b853cadcde620e","abstract_canon_sha256":"c26d9cdcf9cdb02f48457231081343c24631c88eb5c683e0f4b1de2a7551c7f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:12.744006Z","signature_b64":"pE/UTQwYduAmxdGWwTbcD0DhLnf/VCZdmLtoE1ITsH/MPSHrsCh5+cDzD9fgLJU1ppu8cJFXYgNoEM3e4dFKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8b973d90e8d0216a4e6079971c8835b670e39c46bb3f861ad87dd0d37786ffd","last_reissued_at":"2026-07-05T10:56:12.743523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:12.743523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Edward Miller, Fan Zhang, Jade Fountain, Jakob Julian Engel, Linguang Zhang, Pierre Moulon, Prithviraj Banerjee, Richard Newcombe, Robert Wang, Selen Basol, Shangchen Han, Shreyas Hampali, Sindi Shkodrani, Tomas Hodan","submitted_at":"2024-11-28T14:09:42Z","abstract_excerpt":"We introduce HOT3D, a publicly available dataset for egocentric hand and object tracking in 3D. The dataset offers over 833 minutes (3.7M+ images) of recordings that feature 19 subjects interacting with 33 diverse rigid objects. In addition to simple pick-up, observe, and put-down actions, the subjects perform actions typical for a kitchen, office, and living room environment. The recordings include multiple synchronized data streams containing egocentric multi-view RGB/monochrome images, eye gaze signal, scene point clouds, and 3D poses of cameras, hands, and objects. The dataset is recorded "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19167","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/2411.19167/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":"2411.19167","created_at":"2026-07-05T10:56:12.743585+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19167v2","created_at":"2026-07-05T10:56:12.743585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19167","created_at":"2026-07-05T10:56:12.743585+00:00"},{"alias_kind":"pith_short_12","alias_value":"VC4XHWIORUBB","created_at":"2026-07-05T10:56:12.743585+00:00"},{"alias_kind":"pith_short_16","alias_value":"VC4XHWIORUBBNJHG","created_at":"2026-07-05T10:56:12.743585+00:00"},{"alias_kind":"pith_short_8","alias_value":"VC4XHWIO","created_at":"2026-07-05T10:56:12.743585+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06691","citing_title":"CoMind: Understanding Collaborative Human Activity from Multiple Minds and Views","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2607.02075","citing_title":"HandsOnWorld: Unconstrained Egocentric Video Generation with Camera-Disentangled Hand Control","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08057","citing_title":"EgoAERO: Learning Dexterous Manipulation from a Single Egocentric Video without Object Assets","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2505.07813","citing_title":"DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2508.00088","citing_title":"The Monado SLAM Dataset for Egocentric Visual-Inertial Tracking","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2511.12878","citing_title":"Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":192,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03637","citing_title":"Bridging the Embodiment Gap: Disentangled Cross-Embodiment Video Editing","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VC4XHWIORUBBNJHGA6MXDSEDLN","json":"https://pith.science/pith/VC4XHWIORUBBNJHGA6MXDSEDLN.json","graph_json":"https://pith.science/api/pith-number/VC4XHWIORUBBNJHGA6MXDSEDLN/graph.json","events_json":"https://pith.science/api/pith-number/VC4XHWIORUBBNJHGA6MXDSEDLN/events.json","paper":"https://pith.science/paper/VC4XHWIO"},"agent_actions":{"view_html":"https://pith.science/pith/VC4XHWIORUBBNJHGA6MXDSEDLN","download_json":"https://pith.science/pith/VC4XHWIORUBBNJHGA6MXDSEDLN.json","view_paper":"https://pith.science/paper/VC4XHWIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19167&json=true","fetch_graph":"https://pith.science/api/pith-number/VC4XHWIORUBBNJHGA6MXDSEDLN/graph.json","fetch_events":"https://pith.science/api/pith-number/VC4XHWIORUBBNJHGA6MXDSEDLN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VC4XHWIORUBBNJHGA6MXDSEDLN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VC4XHWIORUBBNJHGA6MXDSEDLN/action/storage_attestation","attest_author":"https://pith.science/pith/VC4XHWIORUBBNJHGA6MXDSEDLN/action/author_attestation","sign_citation":"https://pith.science/pith/VC4XHWIORUBBNJHGA6MXDSEDLN/action/citation_signature","submit_replication":"https://pith.science/pith/VC4XHWIORUBBNJHGA6MXDSEDLN/action/replication_record"}},"created_at":"2026-07-05T10:56:12.743585+00:00","updated_at":"2026-07-05T10:56:12.743585+00:00"}