{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TWWF7BBQXM7R4FQJGMKOA2ZQUO","short_pith_number":"pith:TWWF7BBQ","schema_version":"1.0","canonical_sha256":"9dac5f8430bb3f1e16093314e06b30a3af5af46ce04884ea8d876e4ab7c91344","source":{"kind":"arxiv","id":"2412.02690","version":2},"attestation_state":"computed","paper":{"title":"FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cem Keskin, Chaerin Min, Kefan Chen, Linguang Zhang, Shreyas Hampali, Srinath Sridhar","submitted_at":"2024-12-03T18:58:19Z","abstract_excerpt":"Despite remarkable progress in image generation models, generating realistic hands remains a persistent challenge due to their complex articulation, varying viewpoints, and frequent occlusions. We present FoundHand, a large-scale domain-specific diffusion model for synthesizing single and dual hand images. To train our model, we introduce FoundHand-10M, a large-scale hand dataset with 2D keypoints and segmentation mask annotations. Our insight is to use 2D hand keypoints as a universal representation that encodes both hand articulation and camera viewpoint. FoundHand learns from image pairs to"},"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":"2412.02690","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T18:58:19Z","cross_cats_sorted":[],"title_canon_sha256":"c6c5ea466a660d05c245076b8ef89814e828d15cd6deb77f0480d648a7b931e0","abstract_canon_sha256":"eb3eceeec1c3cfc53796e5454955f7686e1aab8f9553e4778945e9620f77ab77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:37.273334Z","signature_b64":"McY+ywJMeJpMGyOI0hMXqBjlBwL1mjUW7WSLEflWceurpl+D4vOSOlpK2FzOBW7jMISVetjKtWkxwgiKyA/4Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dac5f8430bb3f1e16093314e06b30a3af5af46ce04884ea8d876e4ab7c91344","last_reissued_at":"2026-07-05T09:44:37.272823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:37.272823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cem Keskin, Chaerin Min, Kefan Chen, Linguang Zhang, Shreyas Hampali, Srinath Sridhar","submitted_at":"2024-12-03T18:58:19Z","abstract_excerpt":"Despite remarkable progress in image generation models, generating realistic hands remains a persistent challenge due to their complex articulation, varying viewpoints, and frequent occlusions. We present FoundHand, a large-scale domain-specific diffusion model for synthesizing single and dual hand images. To train our model, we introduce FoundHand-10M, a large-scale hand dataset with 2D keypoints and segmentation mask annotations. Our insight is to use 2D hand keypoints as a universal representation that encodes both hand articulation and camera viewpoint. FoundHand learns from image pairs to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02690","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/2412.02690/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":"2412.02690","created_at":"2026-07-05T09:44:37.272882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02690v2","created_at":"2026-07-05T09:44:37.272882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02690","created_at":"2026-07-05T09:44:37.272882+00:00"},{"alias_kind":"pith_short_12","alias_value":"TWWF7BBQXM7R","created_at":"2026-07-05T09:44:37.272882+00:00"},{"alias_kind":"pith_short_16","alias_value":"TWWF7BBQXM7R4FQJ","created_at":"2026-07-05T09:44:37.272882+00:00"},{"alias_kind":"pith_short_8","alias_value":"TWWF7BBQ","created_at":"2026-07-05T09:44:37.272882+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TWWF7BBQXM7R4FQJGMKOA2ZQUO","json":"https://pith.science/pith/TWWF7BBQXM7R4FQJGMKOA2ZQUO.json","graph_json":"https://pith.science/api/pith-number/TWWF7BBQXM7R4FQJGMKOA2ZQUO/graph.json","events_json":"https://pith.science/api/pith-number/TWWF7BBQXM7R4FQJGMKOA2ZQUO/events.json","paper":"https://pith.science/paper/TWWF7BBQ"},"agent_actions":{"view_html":"https://pith.science/pith/TWWF7BBQXM7R4FQJGMKOA2ZQUO","download_json":"https://pith.science/pith/TWWF7BBQXM7R4FQJGMKOA2ZQUO.json","view_paper":"https://pith.science/paper/TWWF7BBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02690&json=true","fetch_graph":"https://pith.science/api/pith-number/TWWF7BBQXM7R4FQJGMKOA2ZQUO/graph.json","fetch_events":"https://pith.science/api/pith-number/TWWF7BBQXM7R4FQJGMKOA2ZQUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TWWF7BBQXM7R4FQJGMKOA2ZQUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TWWF7BBQXM7R4FQJGMKOA2ZQUO/action/storage_attestation","attest_author":"https://pith.science/pith/TWWF7BBQXM7R4FQJGMKOA2ZQUO/action/author_attestation","sign_citation":"https://pith.science/pith/TWWF7BBQXM7R4FQJGMKOA2ZQUO/action/citation_signature","submit_replication":"https://pith.science/pith/TWWF7BBQXM7R4FQJGMKOA2ZQUO/action/replication_record"}},"created_at":"2026-07-05T09:44:37.272882+00:00","updated_at":"2026-07-05T09:44:37.272882+00:00"}