{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:D27I63ZS3EXLMVMNJIVVCSV4HB","short_pith_number":"pith:D27I63ZS","schema_version":"1.0","canonical_sha256":"1ebe8f6f32d92eb6558d4a2b514abc3852e67fb0269f0ea744a6b4a3793f9e05","source":{"kind":"arxiv","id":"2008.08535","version":1},"attestation_state":"computed","paper":{"title":"STAR: Sparse Trained Articulated Human Body Regressor","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmed A. A. Osman, Michael J. Black, Timo Bolkart","submitted_at":"2020-08-19T16:27:55Z","abstract_excerpt":"The SMPL body model is widely used for the estimation, synthesis, and analysis of 3D human pose and shape. While popular, we show that SMPL has several limitations and introduce STAR, which is quantitatively and qualitatively superior to SMPL. First, SMPL has a huge number of parameters resulting from its use of global blend shapes. These dense pose-corrective offsets relate every vertex on the mesh to all the joints in the kinematic tree, capturing spurious long-range correlations. To address this, we define per-joint pose correctives and learn the subset of mesh vertices that are influenced "},"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":"2008.08535","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-19T16:27:55Z","cross_cats_sorted":[],"title_canon_sha256":"26837f6a722b865784aa992d22b908c9ac896d79c4c20393d218fc30545f8c06","abstract_canon_sha256":"b046852030423055a41ee37184751badae3675864bd6bef946a8c1ab8f19b2bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:28:26.701274Z","signature_b64":"Kw96Cc3BBg34Q55qTmBf7Fo7z5SWL0Tq5lJ6x/nxWeN1zKu5aoQwKUxxoBhGQFenYaj9eVKKmWunl4k9U7Y1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ebe8f6f32d92eb6558d4a2b514abc3852e67fb0269f0ea744a6b4a3793f9e05","last_reissued_at":"2026-07-05T01:28:26.700874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:28:26.700874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STAR: Sparse Trained Articulated Human Body Regressor","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmed A. A. Osman, Michael J. Black, Timo Bolkart","submitted_at":"2020-08-19T16:27:55Z","abstract_excerpt":"The SMPL body model is widely used for the estimation, synthesis, and analysis of 3D human pose and shape. While popular, we show that SMPL has several limitations and introduce STAR, which is quantitatively and qualitatively superior to SMPL. First, SMPL has a huge number of parameters resulting from its use of global blend shapes. These dense pose-corrective offsets relate every vertex on the mesh to all the joints in the kinematic tree, capturing spurious long-range correlations. To address this, we define per-joint pose correctives and learn the subset of mesh vertices that are influenced "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.08535","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/2008.08535/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":"2008.08535","created_at":"2026-07-05T01:28:26.700929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.08535v1","created_at":"2026-07-05T01:28:26.700929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.08535","created_at":"2026-07-05T01:28:26.700929+00:00"},{"alias_kind":"pith_short_12","alias_value":"D27I63ZS3EXL","created_at":"2026-07-05T01:28:26.700929+00:00"},{"alias_kind":"pith_short_16","alias_value":"D27I63ZS3EXLMVMN","created_at":"2026-07-05T01:28:26.700929+00:00"},{"alias_kind":"pith_short_8","alias_value":"D27I63ZS","created_at":"2026-07-05T01:28:26.700929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03191","citing_title":"Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forward","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D27I63ZS3EXLMVMNJIVVCSV4HB","json":"https://pith.science/pith/D27I63ZS3EXLMVMNJIVVCSV4HB.json","graph_json":"https://pith.science/api/pith-number/D27I63ZS3EXLMVMNJIVVCSV4HB/graph.json","events_json":"https://pith.science/api/pith-number/D27I63ZS3EXLMVMNJIVVCSV4HB/events.json","paper":"https://pith.science/paper/D27I63ZS"},"agent_actions":{"view_html":"https://pith.science/pith/D27I63ZS3EXLMVMNJIVVCSV4HB","download_json":"https://pith.science/pith/D27I63ZS3EXLMVMNJIVVCSV4HB.json","view_paper":"https://pith.science/paper/D27I63ZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.08535&json=true","fetch_graph":"https://pith.science/api/pith-number/D27I63ZS3EXLMVMNJIVVCSV4HB/graph.json","fetch_events":"https://pith.science/api/pith-number/D27I63ZS3EXLMVMNJIVVCSV4HB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D27I63ZS3EXLMVMNJIVVCSV4HB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D27I63ZS3EXLMVMNJIVVCSV4HB/action/storage_attestation","attest_author":"https://pith.science/pith/D27I63ZS3EXLMVMNJIVVCSV4HB/action/author_attestation","sign_citation":"https://pith.science/pith/D27I63ZS3EXLMVMNJIVVCSV4HB/action/citation_signature","submit_replication":"https://pith.science/pith/D27I63ZS3EXLMVMNJIVVCSV4HB/action/replication_record"}},"created_at":"2026-07-05T01:28:26.700929+00:00","updated_at":"2026-07-05T01:28:26.700929+00:00"}