{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AORPMTNWFDJGEG3WTNM36CTMNZ","short_pith_number":"pith:AORPMTNW","schema_version":"1.0","canonical_sha256":"03a2f64db628d2621b769b59bf0a6c6e43571e38af607af4c8b39a5069a53099","source":{"kind":"arxiv","id":"2504.06982","version":1},"attestation_state":"computed","paper":{"title":"SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengqi Liu, Junting Dong, Lizhuang Ma, Pingyu Wu, Qin Zhao, Ran Yi, Wei Zhai, Yang Cao, Yixing Lu, Yuhang Yang, Zheng-Jun Zha","submitted_at":"2025-04-09T15:38:18Z","abstract_excerpt":"3D human digitization has long been a highly pursued yet challenging task. Existing methods aim to generate high-quality 3D digital humans from single or multiple views, but remain primarily constrained by current paradigms and the scarcity of 3D human assets. Specifically, recent approaches fall into several paradigms: optimization-based and feed-forward (both single-view regression and multi-view generation with reconstruction). However, they are limited by slow speed, low quality, cascade reasoning, and ambiguity in mapping low-dimensional planes to high-dimensional space due to occlusion a"},"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":"2504.06982","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-09T15:38:18Z","cross_cats_sorted":[],"title_canon_sha256":"ae07b2c418d74acf235f0161ace797bbcdb06c7ff9e4c1472bfca621f2eb2b79","abstract_canon_sha256":"2b2825392ad83346a8944a9d976522777f43d47d267fc978a9fef0da91e23724"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:49.545354Z","signature_b64":"v+4fDJ2zZEgfhY6MJhZ6vdNcQrL7TmIZJd5dL+XgW5wWrbcYr9Z5Dbj6ZRdflxhmXOHl2VkOX16uweU5j7/aAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03a2f64db628d2621b769b59bf0a6c6e43571e38af607af4c8b39a5069a53099","last_reissued_at":"2026-07-05T10:46:49.544848Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:49.544848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengqi Liu, Junting Dong, Lizhuang Ma, Pingyu Wu, Qin Zhao, Ran Yi, Wei Zhai, Yang Cao, Yixing Lu, Yuhang Yang, Zheng-Jun Zha","submitted_at":"2025-04-09T15:38:18Z","abstract_excerpt":"3D human digitization has long been a highly pursued yet challenging task. Existing methods aim to generate high-quality 3D digital humans from single or multiple views, but remain primarily constrained by current paradigms and the scarcity of 3D human assets. Specifically, recent approaches fall into several paradigms: optimization-based and feed-forward (both single-view regression and multi-view generation with reconstruction). However, they are limited by slow speed, low quality, cascade reasoning, and ambiguity in mapping low-dimensional planes to high-dimensional space due to occlusion a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06982","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/2504.06982/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":"2504.06982","created_at":"2026-07-05T10:46:49.544909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.06982v1","created_at":"2026-07-05T10:46:49.544909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06982","created_at":"2026-07-05T10:46:49.544909+00:00"},{"alias_kind":"pith_short_12","alias_value":"AORPMTNWFDJG","created_at":"2026-07-05T10:46:49.544909+00:00"},{"alias_kind":"pith_short_16","alias_value":"AORPMTNWFDJGEG3W","created_at":"2026-07-05T10:46:49.544909+00:00"},{"alias_kind":"pith_short_8","alias_value":"AORPMTNW","created_at":"2026-07-05T10:46:49.544909+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07095","citing_title":"Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data","ref_index":94,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AORPMTNWFDJGEG3WTNM36CTMNZ","json":"https://pith.science/pith/AORPMTNWFDJGEG3WTNM36CTMNZ.json","graph_json":"https://pith.science/api/pith-number/AORPMTNWFDJGEG3WTNM36CTMNZ/graph.json","events_json":"https://pith.science/api/pith-number/AORPMTNWFDJGEG3WTNM36CTMNZ/events.json","paper":"https://pith.science/paper/AORPMTNW"},"agent_actions":{"view_html":"https://pith.science/pith/AORPMTNWFDJGEG3WTNM36CTMNZ","download_json":"https://pith.science/pith/AORPMTNWFDJGEG3WTNM36CTMNZ.json","view_paper":"https://pith.science/paper/AORPMTNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.06982&json=true","fetch_graph":"https://pith.science/api/pith-number/AORPMTNWFDJGEG3WTNM36CTMNZ/graph.json","fetch_events":"https://pith.science/api/pith-number/AORPMTNWFDJGEG3WTNM36CTMNZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AORPMTNWFDJGEG3WTNM36CTMNZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AORPMTNWFDJGEG3WTNM36CTMNZ/action/storage_attestation","attest_author":"https://pith.science/pith/AORPMTNWFDJGEG3WTNM36CTMNZ/action/author_attestation","sign_citation":"https://pith.science/pith/AORPMTNWFDJGEG3WTNM36CTMNZ/action/citation_signature","submit_replication":"https://pith.science/pith/AORPMTNWFDJGEG3WTNM36CTMNZ/action/replication_record"}},"created_at":"2026-07-05T10:46:49.544909+00:00","updated_at":"2026-07-05T10:46:49.544909+00:00"}