{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UTI32JA7IHOVGRA3HN6PVRUBIE","short_pith_number":"pith:UTI32JA7","schema_version":"1.0","canonical_sha256":"a4d1bd241f41dd53441b3b7cfac681413e4fd6be9174f80a5eb1d82e1056092e","source":{"kind":"arxiv","id":"2605.22359","version":1},"attestation_state":"computed","paper":{"title":"GazePrior: Zero-Shot AR/VR Eye Tracking via Learned 3D Gaze Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Fix, Ali Behrooz, Corentin Dumery, David Colmenares, Jogendra Kundu, Pascal Fua","submitted_at":"2026-05-21T11:54:01Z","abstract_excerpt":"Eye tracking (ET) is a foundational technology for advanced AR/VR applications. However, training ET models for every new ET device is challenging: real data collection is costly and time-consuming, while existing synthetic data generation methods lack realism. To remove the need for additional data collection while maintaining data quality, we introduce a data-driven 3D prior that models the distribution of human eyes across diverse identities, gaze directions, and light settings. This model, which we coin GazePrior, then enables sparse-input 3D reconstruction of annotated data collected with"},"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":"2605.22359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T11:54:01Z","cross_cats_sorted":[],"title_canon_sha256":"e2a8c99cc542d2c60ab6478a5aa9b936d1676ad066ae389f691e7975f0b3e8f1","abstract_canon_sha256":"b756e60dd61ebef5ad54700e5b25c36b3daa5ed7f1893f86afc13ea65334cdc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:39.531974Z","signature_b64":"1r0NitHt2toHtrNAR12TPnbF2FZpdhJUkgikd059wPPt8clbRFs8nwUjoXVYgyMuycecKd6HoITRdP2dsq43Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4d1bd241f41dd53441b3b7cfac681413e4fd6be9174f80a5eb1d82e1056092e","last_reissued_at":"2026-05-22T01:04:39.531216Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:39.531216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GazePrior: Zero-Shot AR/VR Eye Tracking via Learned 3D Gaze Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Fix, Ali Behrooz, Corentin Dumery, David Colmenares, Jogendra Kundu, Pascal Fua","submitted_at":"2026-05-21T11:54:01Z","abstract_excerpt":"Eye tracking (ET) is a foundational technology for advanced AR/VR applications. However, training ET models for every new ET device is challenging: real data collection is costly and time-consuming, while existing synthetic data generation methods lack realism. To remove the need for additional data collection while maintaining data quality, we introduce a data-driven 3D prior that models the distribution of human eyes across diverse identities, gaze directions, and light settings. This model, which we coin GazePrior, then enables sparse-input 3D reconstruction of annotated data collected with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22359","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/2605.22359/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":"2605.22359","created_at":"2026-05-22T01:04:39.531354+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22359v1","created_at":"2026-05-22T01:04:39.531354+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22359","created_at":"2026-05-22T01:04:39.531354+00:00"},{"alias_kind":"pith_short_12","alias_value":"UTI32JA7IHOV","created_at":"2026-05-22T01:04:39.531354+00:00"},{"alias_kind":"pith_short_16","alias_value":"UTI32JA7IHOVGRA3","created_at":"2026-05-22T01:04:39.531354+00:00"},{"alias_kind":"pith_short_8","alias_value":"UTI32JA7","created_at":"2026-05-22T01:04:39.531354+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UTI32JA7IHOVGRA3HN6PVRUBIE","json":"https://pith.science/pith/UTI32JA7IHOVGRA3HN6PVRUBIE.json","graph_json":"https://pith.science/api/pith-number/UTI32JA7IHOVGRA3HN6PVRUBIE/graph.json","events_json":"https://pith.science/api/pith-number/UTI32JA7IHOVGRA3HN6PVRUBIE/events.json","paper":"https://pith.science/paper/UTI32JA7"},"agent_actions":{"view_html":"https://pith.science/pith/UTI32JA7IHOVGRA3HN6PVRUBIE","download_json":"https://pith.science/pith/UTI32JA7IHOVGRA3HN6PVRUBIE.json","view_paper":"https://pith.science/paper/UTI32JA7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22359&json=true","fetch_graph":"https://pith.science/api/pith-number/UTI32JA7IHOVGRA3HN6PVRUBIE/graph.json","fetch_events":"https://pith.science/api/pith-number/UTI32JA7IHOVGRA3HN6PVRUBIE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UTI32JA7IHOVGRA3HN6PVRUBIE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UTI32JA7IHOVGRA3HN6PVRUBIE/action/storage_attestation","attest_author":"https://pith.science/pith/UTI32JA7IHOVGRA3HN6PVRUBIE/action/author_attestation","sign_citation":"https://pith.science/pith/UTI32JA7IHOVGRA3HN6PVRUBIE/action/citation_signature","submit_replication":"https://pith.science/pith/UTI32JA7IHOVGRA3HN6PVRUBIE/action/replication_record"}},"created_at":"2026-05-22T01:04:39.531354+00:00","updated_at":"2026-05-22T01:04:39.531354+00:00"}