{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MIM4SCMIB4GHCKIPGYVSTZQUOY","short_pith_number":"pith:MIM4SCMI","schema_version":"1.0","canonical_sha256":"6219c909880f0c71290f362b29e6147634ab9e2f297d4b6b5d1ec503184b01d1","source":{"kind":"arxiv","id":"2212.08641","version":1},"attestation_state":"computed","paper":{"title":"GFPose: Learning 3D Human Pose Prior with Gradient Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangwei Zhong, Hai Ci, Hao Dong, Mingdong Wu, Wentao Zhu, Xiaoxuan Ma, Yizhou Wang","submitted_at":"2022-12-16T18:31:48Z","abstract_excerpt":"Learning 3D human pose prior is essential to human-centered AI. Here, we present GFPose, a versatile framework to model plausible 3D human poses for various applications. At the core of GFPose is a time-dependent score network, which estimates the gradient on each body joint and progressively denoises the perturbed 3D human pose to match a given task specification. During the denoising process, GFPose implicitly incorporates pose priors in gradients and unifies various discriminative and generative tasks in an elegant framework. Despite the simplicity, GFPose demonstrates great potential in se"},"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":"2212.08641","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-16T18:31:48Z","cross_cats_sorted":[],"title_canon_sha256":"ba10405feaecfcdaa784ddc6d5988a755b17e9aebf0edceb4cfd871854f1d181","abstract_canon_sha256":"983036557cf93738694285a98e5f9a785574290e25a4bb89f350ffecb222c519"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:59.723870Z","signature_b64":"8qkl9WQiUSjWdW2GsFxjYOCtFOaL7cECuC5HOaGkP81A3u1Tbf/InCHGQttcLuhFL0E270AQeGCudWyWwc+XAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6219c909880f0c71290f362b29e6147634ab9e2f297d4b6b5d1ec503184b01d1","last_reissued_at":"2026-07-05T05:25:59.723405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:59.723405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GFPose: Learning 3D Human Pose Prior with Gradient Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangwei Zhong, Hai Ci, Hao Dong, Mingdong Wu, Wentao Zhu, Xiaoxuan Ma, Yizhou Wang","submitted_at":"2022-12-16T18:31:48Z","abstract_excerpt":"Learning 3D human pose prior is essential to human-centered AI. Here, we present GFPose, a versatile framework to model plausible 3D human poses for various applications. At the core of GFPose is a time-dependent score network, which estimates the gradient on each body joint and progressively denoises the perturbed 3D human pose to match a given task specification. During the denoising process, GFPose implicitly incorporates pose priors in gradients and unifies various discriminative and generative tasks in an elegant framework. Despite the simplicity, GFPose demonstrates great potential in se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08641","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/2212.08641/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":"2212.08641","created_at":"2026-07-05T05:25:59.723463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.08641v1","created_at":"2026-07-05T05:25:59.723463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08641","created_at":"2026-07-05T05:25:59.723463+00:00"},{"alias_kind":"pith_short_12","alias_value":"MIM4SCMIB4GH","created_at":"2026-07-05T05:25:59.723463+00:00"},{"alias_kind":"pith_short_16","alias_value":"MIM4SCMIB4GHCKIP","created_at":"2026-07-05T05:25:59.723463+00:00"},{"alias_kind":"pith_short_8","alias_value":"MIM4SCMI","created_at":"2026-07-05T05:25:59.723463+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MIM4SCMIB4GHCKIPGYVSTZQUOY","json":"https://pith.science/pith/MIM4SCMIB4GHCKIPGYVSTZQUOY.json","graph_json":"https://pith.science/api/pith-number/MIM4SCMIB4GHCKIPGYVSTZQUOY/graph.json","events_json":"https://pith.science/api/pith-number/MIM4SCMIB4GHCKIPGYVSTZQUOY/events.json","paper":"https://pith.science/paper/MIM4SCMI"},"agent_actions":{"view_html":"https://pith.science/pith/MIM4SCMIB4GHCKIPGYVSTZQUOY","download_json":"https://pith.science/pith/MIM4SCMIB4GHCKIPGYVSTZQUOY.json","view_paper":"https://pith.science/paper/MIM4SCMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.08641&json=true","fetch_graph":"https://pith.science/api/pith-number/MIM4SCMIB4GHCKIPGYVSTZQUOY/graph.json","fetch_events":"https://pith.science/api/pith-number/MIM4SCMIB4GHCKIPGYVSTZQUOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MIM4SCMIB4GHCKIPGYVSTZQUOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MIM4SCMIB4GHCKIPGYVSTZQUOY/action/storage_attestation","attest_author":"https://pith.science/pith/MIM4SCMIB4GHCKIPGYVSTZQUOY/action/author_attestation","sign_citation":"https://pith.science/pith/MIM4SCMIB4GHCKIPGYVSTZQUOY/action/citation_signature","submit_replication":"https://pith.science/pith/MIM4SCMIB4GHCKIPGYVSTZQUOY/action/replication_record"}},"created_at":"2026-07-05T05:25:59.723463+00:00","updated_at":"2026-07-05T05:25:59.723463+00:00"}