{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5BKTZVFUZ62334D5UJQMLAPBEE","short_pith_number":"pith:5BKTZVFU","schema_version":"1.0","canonical_sha256":"e8553cd4b4cfb5bdf07da260c581e12133b423b61dd9eccdd798d30de8bab2ae","source":{"kind":"arxiv","id":"2006.10204","version":1},"attestation_state":"computed","paper":{"title":"BlazePose: On-device Real-time Body Pose tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Zhang, Ivan Grishchenko, Karthik Raveendran, Matthias Grundmann, Tyler Zhu, Valentin Bazarevsky","submitted_at":"2020-06-17T23:52:46Z","abstract_excerpt":"We present BlazePose, a lightweight convolutional neural network architecture for human pose estimation that is tailored for real-time inference on mobile devices. During inference, the network produces 33 body keypoints for a single person and runs at over 30 frames per second on a Pixel 2 phone. This makes it particularly suited to real-time use cases like fitness tracking and sign language recognition. Our main contributions include a novel body pose tracking solution and a lightweight body pose estimation neural network that uses both heatmaps and regression to keypoint coordinates."},"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":"2006.10204","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-17T23:52:46Z","cross_cats_sorted":[],"title_canon_sha256":"dc0e5d420bbc76fbc6bdc3b9c6ed58fe83f77fb8dbc3452b1d95119b2c8f6480","abstract_canon_sha256":"0ef149a604e6f5487b31bbab95f553b8c188fe9183c549e1634381a7cb7ce8cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:15.850915Z","signature_b64":"r3/UTx6nWg2MuV2goaTPLd9ON/kTOKw4rHTUlBRiJK5iTDVFLYwBAHT0m7oA7AtsEtzhYlspSXbj1jsKdE0uCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8553cd4b4cfb5bdf07da260c581e12133b423b61dd9eccdd798d30de8bab2ae","last_reissued_at":"2026-07-05T01:11:15.850438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:15.850438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BlazePose: On-device Real-time Body Pose tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Zhang, Ivan Grishchenko, Karthik Raveendran, Matthias Grundmann, Tyler Zhu, Valentin Bazarevsky","submitted_at":"2020-06-17T23:52:46Z","abstract_excerpt":"We present BlazePose, a lightweight convolutional neural network architecture for human pose estimation that is tailored for real-time inference on mobile devices. During inference, the network produces 33 body keypoints for a single person and runs at over 30 frames per second on a Pixel 2 phone. This makes it particularly suited to real-time use cases like fitness tracking and sign language recognition. Our main contributions include a novel body pose tracking solution and a lightweight body pose estimation neural network that uses both heatmaps and regression to keypoint coordinates."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10204","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/2006.10204/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":"2006.10204","created_at":"2026-07-05T01:11:15.850494+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.10204v1","created_at":"2026-07-05T01:11:15.850494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10204","created_at":"2026-07-05T01:11:15.850494+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BKTZVFUZ623","created_at":"2026-07-05T01:11:15.850494+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BKTZVFUZ62334D5","created_at":"2026-07-05T01:11:15.850494+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BKTZVFU","created_at":"2026-07-05T01:11:15.850494+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05230","citing_title":"Video-based detection of cessation of breathing in pre-term infants using machine learning","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20183","citing_title":"MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21421","citing_title":"AIGaitor: Privacy-preserving and cloud-free motion analysis for everyone, using edge computing","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2502.20209","citing_title":"DIPSER: A Dataset for In-Person Student Engagement Recognition in the Wild","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21421","citing_title":"AIGaitor: Privacy-preserving and cloud-free motion analysis for everyone, using edge computing","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20183","citing_title":"MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11570","citing_title":"From Multimodal Signals to Adaptive XR Experiences for De-escalation Training","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01876","citing_title":"BadmintonGRF: A Multimodal Dataset and Benchmark for Markerless Ground Reaction Force Estimation in Badminton","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23532","citing_title":"Emotion-Conditioned Short-Horizon Human Pose Forecasting with a Lightweight Predictive World Model","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5BKTZVFUZ62334D5UJQMLAPBEE","json":"https://pith.science/pith/5BKTZVFUZ62334D5UJQMLAPBEE.json","graph_json":"https://pith.science/api/pith-number/5BKTZVFUZ62334D5UJQMLAPBEE/graph.json","events_json":"https://pith.science/api/pith-number/5BKTZVFUZ62334D5UJQMLAPBEE/events.json","paper":"https://pith.science/paper/5BKTZVFU"},"agent_actions":{"view_html":"https://pith.science/pith/5BKTZVFUZ62334D5UJQMLAPBEE","download_json":"https://pith.science/pith/5BKTZVFUZ62334D5UJQMLAPBEE.json","view_paper":"https://pith.science/paper/5BKTZVFU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.10204&json=true","fetch_graph":"https://pith.science/api/pith-number/5BKTZVFUZ62334D5UJQMLAPBEE/graph.json","fetch_events":"https://pith.science/api/pith-number/5BKTZVFUZ62334D5UJQMLAPBEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BKTZVFUZ62334D5UJQMLAPBEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BKTZVFUZ62334D5UJQMLAPBEE/action/storage_attestation","attest_author":"https://pith.science/pith/5BKTZVFUZ62334D5UJQMLAPBEE/action/author_attestation","sign_citation":"https://pith.science/pith/5BKTZVFUZ62334D5UJQMLAPBEE/action/citation_signature","submit_replication":"https://pith.science/pith/5BKTZVFUZ62334D5UJQMLAPBEE/action/replication_record"}},"created_at":"2026-07-05T01:11:15.850494+00:00","updated_at":"2026-07-05T01:11:15.850494+00:00"}