{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6LTA5Y3KJLZDEITUX452G7VJHU","short_pith_number":"pith:6LTA5Y3K","schema_version":"1.0","canonical_sha256":"f2e60ee36a4af2322274bf3ba37ea93d28b7718383534ad2f3e054177cd34a7a","source":{"kind":"arxiv","id":"2109.03413","version":2},"attestation_state":"computed","paper":{"title":"YouRefIt: Embodied Reference Understanding with Language and Gesture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deqian Kong, Qing Li, Siyuan Huang, Song-Chun Zhu, Tao Gao, Yik Lun Kei, Yixin Chen, Yixin Zhu","submitted_at":"2021-09-08T03:27:32Z","abstract_excerpt":"We study the understanding of embodied reference: One agent uses both language and gesture to refer to an object to another agent in a shared physical environment. Of note, this new visual task requires understanding multimodal cues with perspective-taking to identify which object is being referred to. To tackle this problem, we introduce YouRefIt, a new crowd-sourced dataset of embodied reference collected in various physical scenes; the dataset contains 4,195 unique reference clips in 432 indoor scenes. To the best of our knowledge, this is the first embodied reference dataset that allows us"},"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":"2109.03413","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-08T03:27:32Z","cross_cats_sorted":[],"title_canon_sha256":"e8132e1496e12650fc8b6020344df47856e30c031c06c58c7c79bda6595fd629","abstract_canon_sha256":"5a0f83caffd24d063eaae901bbfecd3a09706340ec7e95973a120c22a55b1e9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:14:36.429328Z","signature_b64":"TWSScvVqAWc1wEX8GSZOwiRXPmSyyNBLV2bbnCtOWxwQgUzPKcjeCeRJ4cmAS0wS1yFUAMzMZvSXsNCGZ6V2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2e60ee36a4af2322274bf3ba37ea93d28b7718383534ad2f3e054177cd34a7a","last_reissued_at":"2026-07-05T03:14:36.428879Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:14:36.428879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"YouRefIt: Embodied Reference Understanding with Language and Gesture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deqian Kong, Qing Li, Siyuan Huang, Song-Chun Zhu, Tao Gao, Yik Lun Kei, Yixin Chen, Yixin Zhu","submitted_at":"2021-09-08T03:27:32Z","abstract_excerpt":"We study the understanding of embodied reference: One agent uses both language and gesture to refer to an object to another agent in a shared physical environment. Of note, this new visual task requires understanding multimodal cues with perspective-taking to identify which object is being referred to. To tackle this problem, we introduce YouRefIt, a new crowd-sourced dataset of embodied reference collected in various physical scenes; the dataset contains 4,195 unique reference clips in 432 indoor scenes. To the best of our knowledge, this is the first embodied reference dataset that allows us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.03413","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/2109.03413/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":"2109.03413","created_at":"2026-07-05T03:14:36.428933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.03413v2","created_at":"2026-07-05T03:14:36.428933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.03413","created_at":"2026-07-05T03:14:36.428933+00:00"},{"alias_kind":"pith_short_12","alias_value":"6LTA5Y3KJLZD","created_at":"2026-07-05T03:14:36.428933+00:00"},{"alias_kind":"pith_short_16","alias_value":"6LTA5Y3KJLZDEITU","created_at":"2026-07-05T03:14:36.428933+00:00"},{"alias_kind":"pith_short_8","alias_value":"6LTA5Y3K","created_at":"2026-07-05T03:14:36.428933+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24498","citing_title":"VistaRef: Boosting Visual Spatial Orientation Awareness for Pointing-to-Object Detection","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6LTA5Y3KJLZDEITUX452G7VJHU","json":"https://pith.science/pith/6LTA5Y3KJLZDEITUX452G7VJHU.json","graph_json":"https://pith.science/api/pith-number/6LTA5Y3KJLZDEITUX452G7VJHU/graph.json","events_json":"https://pith.science/api/pith-number/6LTA5Y3KJLZDEITUX452G7VJHU/events.json","paper":"https://pith.science/paper/6LTA5Y3K"},"agent_actions":{"view_html":"https://pith.science/pith/6LTA5Y3KJLZDEITUX452G7VJHU","download_json":"https://pith.science/pith/6LTA5Y3KJLZDEITUX452G7VJHU.json","view_paper":"https://pith.science/paper/6LTA5Y3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.03413&json=true","fetch_graph":"https://pith.science/api/pith-number/6LTA5Y3KJLZDEITUX452G7VJHU/graph.json","fetch_events":"https://pith.science/api/pith-number/6LTA5Y3KJLZDEITUX452G7VJHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6LTA5Y3KJLZDEITUX452G7VJHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6LTA5Y3KJLZDEITUX452G7VJHU/action/storage_attestation","attest_author":"https://pith.science/pith/6LTA5Y3KJLZDEITUX452G7VJHU/action/author_attestation","sign_citation":"https://pith.science/pith/6LTA5Y3KJLZDEITUX452G7VJHU/action/citation_signature","submit_replication":"https://pith.science/pith/6LTA5Y3KJLZDEITUX452G7VJHU/action/replication_record"}},"created_at":"2026-07-05T03:14:36.428933+00:00","updated_at":"2026-07-05T03:14:36.428933+00:00"}