{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6LTA5Y3KJLZDEITUX452G7VJHU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5a0f83caffd24d063eaae901bbfecd3a09706340ec7e95973a120c22a55b1e9e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-08T03:27:32Z","title_canon_sha256":"e8132e1496e12650fc8b6020344df47856e30c031c06c58c7c79bda6595fd629"},"schema_version":"1.0","source":{"id":"2109.03413","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.03413","created_at":"2026-07-05T03:14:36Z"},{"alias_kind":"arxiv_version","alias_value":"2109.03413v2","created_at":"2026-07-05T03:14:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.03413","created_at":"2026-07-05T03:14:36Z"},{"alias_kind":"pith_short_12","alias_value":"6LTA5Y3KJLZD","created_at":"2026-07-05T03:14:36Z"},{"alias_kind":"pith_short_16","alias_value":"6LTA5Y3KJLZDEITU","created_at":"2026-07-05T03:14:36Z"},{"alias_kind":"pith_short_8","alias_value":"6LTA5Y3K","created_at":"2026-07-05T03:14:36Z"}],"graph_snapshots":[{"event_id":"sha256:077faad2d96ebc3ba10ee56d26e9d161446c6ee041bd6fe840cd955bb66a8a61","target":"graph","created_at":"2026-07-05T03:14:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2109.03413/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Deqian Kong, Qing Li, Siyuan Huang, Song-Chun Zhu, Tao Gao, Yik Lun Kei, Yixin Chen, Yixin Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-08T03:27:32Z","title":"YouRefIt: Embodied Reference Understanding with Language and Gesture"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.03413","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4b046fc5f306ee1d7f56b3d00c7020fc2c602c969075301cfcf17c9cc8c72e40","target":"record","created_at":"2026-07-05T03:14:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5a0f83caffd24d063eaae901bbfecd3a09706340ec7e95973a120c22a55b1e9e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-08T03:27:32Z","title_canon_sha256":"e8132e1496e12650fc8b6020344df47856e30c031c06c58c7c79bda6595fd629"},"schema_version":"1.0","source":{"id":"2109.03413","kind":"arxiv","version":2}},"canonical_sha256":"f2e60ee36a4af2322274bf3ba37ea93d28b7718383534ad2f3e054177cd34a7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2e60ee36a4af2322274bf3ba37ea93d28b7718383534ad2f3e054177cd34a7a","first_computed_at":"2026-07-05T03:14:36.428879Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:14:36.428879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TWSScvVqAWc1wEX8GSZOwiRXPmSyyNBLV2bbnCtOWxwQgUzPKcjeCeRJ4cmAS0wS1yFUAMzMZvSXsNCGZ6V2Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:14:36.429328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.03413","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b046fc5f306ee1d7f56b3d00c7020fc2c602c969075301cfcf17c9cc8c72e40","sha256:077faad2d96ebc3ba10ee56d26e9d161446c6ee041bd6fe840cd955bb66a8a61"],"state_sha256":"8c3387845218d969a41ae816bfae327edbb8fc4e98c8dd7776f8aea5eac72e34"}