{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NZCP65J7PE3TWYR74UL6G6LE6Y","short_pith_number":"pith:NZCP65J7","schema_version":"1.0","canonical_sha256":"6e44ff753f79373b623fe517e37964f62431da940a4b4aed27fda5bd1dc08859","source":{"kind":"arxiv","id":"2403.10367","version":2},"attestation_state":"computed","paper":{"title":"Testing MediaPipe Holistic for Linguistic Analysis of Nonmanual Markers in Sign Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anna Kuznetsova, Vadim Kimmelman","submitted_at":"2024-03-15T14:59:21Z","abstract_excerpt":"Advances in Deep Learning have made possible reliable landmark tracking of human bodies and faces that can be used for a variety of tasks. We test a recent Computer Vision solution, MediaPipe Holistic (MPH), to find out if its tracking of the facial features is reliable enough for a linguistic analysis of data from sign languages, and compare it to an older solution (OpenFace, OF). We use an existing data set of sentences in Kazakh-Russian Sign Language and a newly created small data set of videos with head tilts and eyebrow movements. We find that MPH does not perform well enough for linguist"},"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":"2403.10367","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-15T14:59:21Z","cross_cats_sorted":[],"title_canon_sha256":"ad2d7b68c9c04f4a4c6783cabb2e04b08390e8576e5a9bc988927611d202cf25","abstract_canon_sha256":"c7fea50d90b36387512ebf614f3902a8a8797a35cc488cff4672a054212636da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:42.366976Z","signature_b64":"Q/Vur2WV1DvIlptn6jlkZMpL7009MG9cSl+tZG1E4jbykbjnlT2PZGDWKsC9NUxY3N0b64mZgjCUx/BLaJvyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e44ff753f79373b623fe517e37964f62431da940a4b4aed27fda5bd1dc08859","last_reissued_at":"2026-07-05T08:00:42.366508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:42.366508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Testing MediaPipe Holistic for Linguistic Analysis of Nonmanual Markers in Sign Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anna Kuznetsova, Vadim Kimmelman","submitted_at":"2024-03-15T14:59:21Z","abstract_excerpt":"Advances in Deep Learning have made possible reliable landmark tracking of human bodies and faces that can be used for a variety of tasks. We test a recent Computer Vision solution, MediaPipe Holistic (MPH), to find out if its tracking of the facial features is reliable enough for a linguistic analysis of data from sign languages, and compare it to an older solution (OpenFace, OF). We use an existing data set of sentences in Kazakh-Russian Sign Language and a newly created small data set of videos with head tilts and eyebrow movements. We find that MPH does not perform well enough for linguist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10367","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/2403.10367/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":"2403.10367","created_at":"2026-07-05T08:00:42.366564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10367v2","created_at":"2026-07-05T08:00:42.366564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10367","created_at":"2026-07-05T08:00:42.366564+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZCP65J7PE3T","created_at":"2026-07-05T08:00:42.366564+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZCP65J7PE3TWYR7","created_at":"2026-07-05T08:00:42.366564+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZCP65J7","created_at":"2026-07-05T08:00:42.366564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.16765","citing_title":"SHuBERT: Self-Supervised Sign Language Representation Learning via Multi-Stream Cluster Prediction","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NZCP65J7PE3TWYR74UL6G6LE6Y","json":"https://pith.science/pith/NZCP65J7PE3TWYR74UL6G6LE6Y.json","graph_json":"https://pith.science/api/pith-number/NZCP65J7PE3TWYR74UL6G6LE6Y/graph.json","events_json":"https://pith.science/api/pith-number/NZCP65J7PE3TWYR74UL6G6LE6Y/events.json","paper":"https://pith.science/paper/NZCP65J7"},"agent_actions":{"view_html":"https://pith.science/pith/NZCP65J7PE3TWYR74UL6G6LE6Y","download_json":"https://pith.science/pith/NZCP65J7PE3TWYR74UL6G6LE6Y.json","view_paper":"https://pith.science/paper/NZCP65J7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10367&json=true","fetch_graph":"https://pith.science/api/pith-number/NZCP65J7PE3TWYR74UL6G6LE6Y/graph.json","fetch_events":"https://pith.science/api/pith-number/NZCP65J7PE3TWYR74UL6G6LE6Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZCP65J7PE3TWYR74UL6G6LE6Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZCP65J7PE3TWYR74UL6G6LE6Y/action/storage_attestation","attest_author":"https://pith.science/pith/NZCP65J7PE3TWYR74UL6G6LE6Y/action/author_attestation","sign_citation":"https://pith.science/pith/NZCP65J7PE3TWYR74UL6G6LE6Y/action/citation_signature","submit_replication":"https://pith.science/pith/NZCP65J7PE3TWYR74UL6G6LE6Y/action/replication_record"}},"created_at":"2026-07-05T08:00:42.366564+00:00","updated_at":"2026-07-05T08:00:42.366564+00:00"}