{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VZORDB756ZNSGWYUWIF6ODE4T7","short_pith_number":"pith:VZORDB75","schema_version":"1.0","canonical_sha256":"ae5d1187fdf65b235b14b20be70c9c9ffe13613036520c7e4796452c73184253","source":{"kind":"arxiv","id":"2503.08133","version":1},"attestation_state":"computed","paper":{"title":"MGHanD: Multi-modal Guidance for authentic Hand Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jieun Choi, Taehyeon Eum, Tae-Kyun Kim","submitted_at":"2025-03-11T07:51:47Z","abstract_excerpt":"Diffusion-based methods have achieved significant successes in T2I generation, providing realistic images from text prompts. Despite their capabilities, these models face persistent challenges in generating realistic human hands, often producing images with incorrect finger counts and structurally deformed hands. MGHanD addresses this challenge by applying multi-modal guidance during the inference process. For visual guidance, we employ a discriminator trained on a dataset comprising paired real and generated images with captions, derived from various hand-in-the-wild datasets. We also employ "},"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":"2503.08133","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T07:51:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"badcb46c622d43a321891337b7afcad9cc171607aee14d54a2d660ba42d5bfed","abstract_canon_sha256":"522748c2027296b6189a2fecdd2d0ed6b668d886cc3f668af354c87867f51f3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:51.847448Z","signature_b64":"o9QQNVGUIEqmR+IidMkMfaa5WILLPgtBqnJpRFuNCYSXrezua9RRf5OXd9/d2Tt8SvV56KaSh40HIHoNRDQ8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae5d1187fdf65b235b14b20be70c9c9ffe13613036520c7e4796452c73184253","last_reissued_at":"2026-07-05T10:28:51.846838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:51.846838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MGHanD: Multi-modal Guidance for authentic Hand Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jieun Choi, Taehyeon Eum, Tae-Kyun Kim","submitted_at":"2025-03-11T07:51:47Z","abstract_excerpt":"Diffusion-based methods have achieved significant successes in T2I generation, providing realistic images from text prompts. Despite their capabilities, these models face persistent challenges in generating realistic human hands, often producing images with incorrect finger counts and structurally deformed hands. MGHanD addresses this challenge by applying multi-modal guidance during the inference process. For visual guidance, we employ a discriminator trained on a dataset comprising paired real and generated images with captions, derived from various hand-in-the-wild datasets. We also employ "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08133","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/2503.08133/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":"2503.08133","created_at":"2026-07-05T10:28:51.846906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.08133v1","created_at":"2026-07-05T10:28:51.846906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08133","created_at":"2026-07-05T10:28:51.846906+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZORDB756ZNS","created_at":"2026-07-05T10:28:51.846906+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZORDB756ZNSGWYU","created_at":"2026-07-05T10:28:51.846906+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZORDB75","created_at":"2026-07-05T10:28:51.846906+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12680","citing_title":"3D Hand Mesh-Guided AI-Generated Malformed Hand Refinement with Hand Pose Transformation via Diffusion Model","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZORDB756ZNSGWYUWIF6ODE4T7","json":"https://pith.science/pith/VZORDB756ZNSGWYUWIF6ODE4T7.json","graph_json":"https://pith.science/api/pith-number/VZORDB756ZNSGWYUWIF6ODE4T7/graph.json","events_json":"https://pith.science/api/pith-number/VZORDB756ZNSGWYUWIF6ODE4T7/events.json","paper":"https://pith.science/paper/VZORDB75"},"agent_actions":{"view_html":"https://pith.science/pith/VZORDB756ZNSGWYUWIF6ODE4T7","download_json":"https://pith.science/pith/VZORDB756ZNSGWYUWIF6ODE4T7.json","view_paper":"https://pith.science/paper/VZORDB75","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.08133&json=true","fetch_graph":"https://pith.science/api/pith-number/VZORDB756ZNSGWYUWIF6ODE4T7/graph.json","fetch_events":"https://pith.science/api/pith-number/VZORDB756ZNSGWYUWIF6ODE4T7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZORDB756ZNSGWYUWIF6ODE4T7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZORDB756ZNSGWYUWIF6ODE4T7/action/storage_attestation","attest_author":"https://pith.science/pith/VZORDB756ZNSGWYUWIF6ODE4T7/action/author_attestation","sign_citation":"https://pith.science/pith/VZORDB756ZNSGWYUWIF6ODE4T7/action/citation_signature","submit_replication":"https://pith.science/pith/VZORDB756ZNSGWYUWIF6ODE4T7/action/replication_record"}},"created_at":"2026-07-05T10:28:51.846906+00:00","updated_at":"2026-07-05T10:28:51.846906+00:00"}