{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SGTUIY46X5HN4B43PW4PEROVB7","short_pith_number":"pith:SGTUIY46","schema_version":"1.0","canonical_sha256":"91a744639ebf4ede079b7db8f245d50fe0c5513a3524ad5df0f121313e79c8c7","source":{"kind":"arxiv","id":"2312.05251","version":1},"attestation_state":"computed","paper":{"title":"Reconstructing Hands in 3D with Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angjoo Kanazawa, Dandan Shan, David Fouhey, Georgios Pavlakos, Ilija Radosavovic, Jitendra Malik","submitted_at":"2023-12-08T18:59:07Z","abstract_excerpt":"We present an approach that can reconstruct hands in 3D from monocular input. Our approach for Hand Mesh Recovery, HaMeR, follows a fully transformer-based architecture and can analyze hands with significantly increased accuracy and robustness compared to previous work. The key to HaMeR's success lies in scaling up both the data used for training and the capacity of the deep network for hand reconstruction. For training data, we combine multiple datasets that contain 2D or 3D hand annotations. For the deep model, we use a large scale Vision Transformer architecture. Our final model consistentl"},"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":"2312.05251","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-08T18:59:07Z","cross_cats_sorted":[],"title_canon_sha256":"ad80e7a7a2caf3950696c0099c47261e65b19bc1115b3405c5f1f1ca953495ec","abstract_canon_sha256":"40da1a998f81e19262c0958727cc8e30cc2a9eb198bbfd35011a1e22d16a3b54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:59.125929Z","signature_b64":"IHI1LMuqJiwyIRu7My3+yYxM2Qlh0muBkezxSNv/Hj0xjAJEtSM59hhiFn6mNa25pNVDbGetE6VGFGmcCAXhAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91a744639ebf4ede079b7db8f245d50fe0c5513a3524ad5df0f121313e79c8c7","last_reissued_at":"2026-07-05T07:21:59.125529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:59.125529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reconstructing Hands in 3D with Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angjoo Kanazawa, Dandan Shan, David Fouhey, Georgios Pavlakos, Ilija Radosavovic, Jitendra Malik","submitted_at":"2023-12-08T18:59:07Z","abstract_excerpt":"We present an approach that can reconstruct hands in 3D from monocular input. Our approach for Hand Mesh Recovery, HaMeR, follows a fully transformer-based architecture and can analyze hands with significantly increased accuracy and robustness compared to previous work. The key to HaMeR's success lies in scaling up both the data used for training and the capacity of the deep network for hand reconstruction. For training data, we combine multiple datasets that contain 2D or 3D hand annotations. For the deep model, we use a large scale Vision Transformer architecture. Our final model consistentl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05251","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/2312.05251/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":"2312.05251","created_at":"2026-07-05T07:21:59.125583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.05251v1","created_at":"2026-07-05T07:21:59.125583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05251","created_at":"2026-07-05T07:21:59.125583+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGTUIY46X5HN","created_at":"2026-07-05T07:21:59.125583+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGTUIY46X5HN4B43","created_at":"2026-07-05T07:21:59.125583+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGTUIY46","created_at":"2026-07-05T07:21:59.125583+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02075","citing_title":"HandsOnWorld: Unconstrained Egocentric Video Generation with Camera-Disentangled Hand Control","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2405.20330","citing_title":"OmniHands: Towards Robust 4D Hand Mesh Recovery via A Versatile Transformer","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07331","citing_title":"RoSHI: A Versatile Robot-oriented Suit for Human Data In-the-Wild","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SGTUIY46X5HN4B43PW4PEROVB7","json":"https://pith.science/pith/SGTUIY46X5HN4B43PW4PEROVB7.json","graph_json":"https://pith.science/api/pith-number/SGTUIY46X5HN4B43PW4PEROVB7/graph.json","events_json":"https://pith.science/api/pith-number/SGTUIY46X5HN4B43PW4PEROVB7/events.json","paper":"https://pith.science/paper/SGTUIY46"},"agent_actions":{"view_html":"https://pith.science/pith/SGTUIY46X5HN4B43PW4PEROVB7","download_json":"https://pith.science/pith/SGTUIY46X5HN4B43PW4PEROVB7.json","view_paper":"https://pith.science/paper/SGTUIY46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.05251&json=true","fetch_graph":"https://pith.science/api/pith-number/SGTUIY46X5HN4B43PW4PEROVB7/graph.json","fetch_events":"https://pith.science/api/pith-number/SGTUIY46X5HN4B43PW4PEROVB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGTUIY46X5HN4B43PW4PEROVB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGTUIY46X5HN4B43PW4PEROVB7/action/storage_attestation","attest_author":"https://pith.science/pith/SGTUIY46X5HN4B43PW4PEROVB7/action/author_attestation","sign_citation":"https://pith.science/pith/SGTUIY46X5HN4B43PW4PEROVB7/action/citation_signature","submit_replication":"https://pith.science/pith/SGTUIY46X5HN4B43PW4PEROVB7/action/replication_record"}},"created_at":"2026-07-05T07:21:59.125583+00:00","updated_at":"2026-07-05T07:21:59.125583+00:00"}