{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WVF5TQEPK6O54OW2FPAZJS3YR6","short_pith_number":"pith:WVF5TQEP","schema_version":"1.0","canonical_sha256":"b54bd9c08f579dde3ada2bc194cb788fbfeca30eead93c4dc456c0d4a777900e","source":{"kind":"arxiv","id":"2108.12617","version":2},"attestation_state":"computed","paper":{"title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Hang Yu, Jing Zhang, Wei Zhao, Yufei Xu, Ziyu Guan","submitted_at":"2021-08-28T10:23:34Z","abstract_excerpt":"Accurate animal pose estimation is an essential step towards understanding animal behavior, and can potentially benefit many downstream applications, such as wildlife conservation. Previous works only focus on specific animals while ignoring the diversity of animal species, limiting the generalization ability. In this paper, we propose AP-10K, the first large-scale benchmark for mammal animal pose estimation, to facilitate the research in animal pose estimation. AP-10K consists of 10,015 images collected and filtered from 23 animal families and 54 species following the taxonomic rank and high-"},"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":"2108.12617","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-28T10:23:34Z","cross_cats_sorted":[],"title_canon_sha256":"fb20c2bcbe356d39029e9e47541880edf9502fc45abfa15423f3787ac48d78eb","abstract_canon_sha256":"8a46ddb4ab0ae79480e874b70e4b072d272136369b23f07f32593b0e948b8695"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:35.292403Z","signature_b64":"46uYpRJetQwlLee2e4quSiQ2w8Bsm+qRtsUGyZm0YlBTHI9GxnysfHMIAzf4b2EuLOWmmklvx16mtK47m8AYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b54bd9c08f579dde3ada2bc194cb788fbfeca30eead93c4dc456c0d4a777900e","last_reissued_at":"2026-07-05T03:27:35.291926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:35.291926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Hang Yu, Jing Zhang, Wei Zhao, Yufei Xu, Ziyu Guan","submitted_at":"2021-08-28T10:23:34Z","abstract_excerpt":"Accurate animal pose estimation is an essential step towards understanding animal behavior, and can potentially benefit many downstream applications, such as wildlife conservation. Previous works only focus on specific animals while ignoring the diversity of animal species, limiting the generalization ability. In this paper, we propose AP-10K, the first large-scale benchmark for mammal animal pose estimation, to facilitate the research in animal pose estimation. AP-10K consists of 10,015 images collected and filtered from 23 animal families and 54 species following the taxonomic rank and high-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.12617","kind":"arxiv","version":2},"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/2108.12617/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":"2108.12617","created_at":"2026-07-05T03:27:35.291986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.12617v2","created_at":"2026-07-05T03:27:35.291986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.12617","created_at":"2026-07-05T03:27:35.291986+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVF5TQEPK6O5","created_at":"2026-07-05T03:27:35.291986+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVF5TQEPK6O54OW2","created_at":"2026-07-05T03:27:35.291986+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVF5TQEP","created_at":"2026-07-05T03:27:35.291986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10967","citing_title":"Quo Vadis, Visual In-Context Learning? A Unified Benchmark Across Domains and Tasks","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31597","citing_title":"SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00752","citing_title":"GKDT: General Keypoint Detection Transformer","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31597","citing_title":"SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28237","citing_title":"Unleashing Infinite Motion: Scaling Expressive Quadrupedal Motion via Generative Video Priors","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15497","citing_title":"AnyAct: Towards Human Reenactment of Character Motion From Video","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15497","citing_title":"AnyAct: Towards Human Reenactment of Character Motion From Video","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WVF5TQEPK6O54OW2FPAZJS3YR6","json":"https://pith.science/pith/WVF5TQEPK6O54OW2FPAZJS3YR6.json","graph_json":"https://pith.science/api/pith-number/WVF5TQEPK6O54OW2FPAZJS3YR6/graph.json","events_json":"https://pith.science/api/pith-number/WVF5TQEPK6O54OW2FPAZJS3YR6/events.json","paper":"https://pith.science/paper/WVF5TQEP"},"agent_actions":{"view_html":"https://pith.science/pith/WVF5TQEPK6O54OW2FPAZJS3YR6","download_json":"https://pith.science/pith/WVF5TQEPK6O54OW2FPAZJS3YR6.json","view_paper":"https://pith.science/paper/WVF5TQEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.12617&json=true","fetch_graph":"https://pith.science/api/pith-number/WVF5TQEPK6O54OW2FPAZJS3YR6/graph.json","fetch_events":"https://pith.science/api/pith-number/WVF5TQEPK6O54OW2FPAZJS3YR6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVF5TQEPK6O54OW2FPAZJS3YR6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVF5TQEPK6O54OW2FPAZJS3YR6/action/storage_attestation","attest_author":"https://pith.science/pith/WVF5TQEPK6O54OW2FPAZJS3YR6/action/author_attestation","sign_citation":"https://pith.science/pith/WVF5TQEPK6O54OW2FPAZJS3YR6/action/citation_signature","submit_replication":"https://pith.science/pith/WVF5TQEPK6O54OW2FPAZJS3YR6/action/replication_record"}},"created_at":"2026-07-05T03:27:35.291986+00:00","updated_at":"2026-07-05T03:27:35.291986+00:00"}