{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QZEFOG4OCAFCF427JQVMZ2HPG3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"37b1f75385ffad5c75a8f588d8df50408ef261e54bb7acef7d83e1672fa7b0ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-22T17:37:27Z","title_canon_sha256":"e97b14f5979abaf31b09ebb7f74fc84244b79d4b3a37198ac77ec611b3db566c"},"schema_version":"1.0","source":{"id":"2408.12569","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12569","created_at":"2026-07-05T08:59:32Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12569v3","created_at":"2026-07-05T08:59:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12569","created_at":"2026-07-05T08:59:32Z"},{"alias_kind":"pith_short_12","alias_value":"QZEFOG4OCAFC","created_at":"2026-07-05T08:59:32Z"},{"alias_kind":"pith_short_16","alias_value":"QZEFOG4OCAFCF427","created_at":"2026-07-05T08:59:32Z"},{"alias_kind":"pith_short_8","alias_value":"QZEFOG4O","created_at":"2026-07-05T08:59:32Z"}],"graph_snapshots":[{"event_id":"sha256:8d82a8d6e95a5655cd652a17b0b22c3a2c2df8a8d43ceeabd05bfb514699aba4","target":"graph","created_at":"2026-07-05T08:59:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.12569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Sapiens, a family of models for four fundamental human-centric vision tasks -- 2D pose estimation, body-part segmentation, depth estimation, and surface normal prediction. Our models natively support 1K high-resolution inference and are extremely easy to adapt for individual tasks by simply fine-tuning models pretrained on over 300 million in-the-wild human images. We observe that, given the same computational budget, self-supervised pretraining on a curated dataset of human images significantly boosts the performance for a diverse set of human-centric tasks. The resulting models ex","authors_text":"Austin James, Julieta Martinez, Peter Selednik, Rawal Khirodkar, Shunsuke Saito, Stuart Anderson, Su Zhaoen, Timur Bagautdinov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-22T17:37:27Z","title":"Sapiens: Foundation for Human Vision Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12569","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:eb0243ea8b8ee3971db8942416e9208b00a85e8024c8c42cf6830213d825cb94","target":"record","created_at":"2026-07-05T08:59:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"37b1f75385ffad5c75a8f588d8df50408ef261e54bb7acef7d83e1672fa7b0ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-22T17:37:27Z","title_canon_sha256":"e97b14f5979abaf31b09ebb7f74fc84244b79d4b3a37198ac77ec611b3db566c"},"schema_version":"1.0","source":{"id":"2408.12569","kind":"arxiv","version":3}},"canonical_sha256":"8648571b8e100a22f35f4c2acce8ef36d4711f8e1e2d09dd08698d3e81b0cb3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8648571b8e100a22f35f4c2acce8ef36d4711f8e1e2d09dd08698d3e81b0cb3c","first_computed_at":"2026-07-05T08:59:32.903734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:59:32.903734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E4S7yQsGMYjSH47eHUE3Il3eKT+baAj0Uu3Vgw1vudJKyKGBNggcLn+z5ffEUkJa2rbyUPKdeTOebVJ5S2a1DA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:59:32.904168Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.12569","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb0243ea8b8ee3971db8942416e9208b00a85e8024c8c42cf6830213d825cb94","sha256:8d82a8d6e95a5655cd652a17b0b22c3a2c2df8a8d43ceeabd05bfb514699aba4"],"state_sha256":"503822f4cee2d2c4c3ffce9eff499b79f67265430178dd57ae729e3472f37051"}