{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:342L4ORVWWVNZEBWXM5QVTGKYF","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":"4c44eb9b0533f056d3383aacd0c2652c0c4493324f777f34470675c0a66bcc07","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-18T17:57:05Z","title_canon_sha256":"916f00503c7e4f99b5ead585c56ed128823c4cdb5b6051bd582ae53d6649fbd3"},"schema_version":"1.0","source":{"id":"2310.12147","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12147","created_at":"2026-07-05T07:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12147v1","created_at":"2026-07-05T07:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12147","created_at":"2026-07-05T07:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"342L4ORVWWVN","created_at":"2026-07-05T07:02:23Z"},{"alias_kind":"pith_short_16","alias_value":"342L4ORVWWVNZEBW","created_at":"2026-07-05T07:02:23Z"},{"alias_kind":"pith_short_8","alias_value":"342L4ORV","created_at":"2026-07-05T07:02:23Z"}],"graph_snapshots":[{"event_id":"sha256:704c5e26be85e4b3aae4656184850dfee635887bfec77288b4465d00609c4d70","target":"graph","created_at":"2026-07-05T07:02:23Z","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/2310.12147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ambiguity is ubiquitous in human communication. Previous approaches in Human-Robot Interaction (HRI) have often relied on predefined interaction templates, leading to reduced performance in realistic and open-ended scenarios. To address these issues, we present a large-scale dataset, \\invig, for interactive visual grounding under language ambiguity. Our dataset comprises over 520K images accompanied by open-ended goal-oriented disambiguation dialogues, encompassing millions of object instances and corresponding question-answer pairs. Leveraging the \\invig dataset, we conduct extensive studies ","authors_text":"Hanbo Zhang, Jie Xu, Tao Kong, Yuchen Mo","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-18T17:57:05Z","title":"InViG: Benchmarking Interactive Visual Grounding with 500K Human-Robot Interactions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12147","kind":"arxiv","version":1},"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:f6937eabd6f717e0d3905cce90a3cc5f89950f5fe9a9157f43e4b39544a4131e","target":"record","created_at":"2026-07-05T07:02:23Z","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":"4c44eb9b0533f056d3383aacd0c2652c0c4493324f777f34470675c0a66bcc07","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-18T17:57:05Z","title_canon_sha256":"916f00503c7e4f99b5ead585c56ed128823c4cdb5b6051bd582ae53d6649fbd3"},"schema_version":"1.0","source":{"id":"2310.12147","kind":"arxiv","version":1}},"canonical_sha256":"df34be3a35b5aadc9036bb3b0acccac15cdfeda8aa031b644946b0ec5ce9584a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df34be3a35b5aadc9036bb3b0acccac15cdfeda8aa031b644946b0ec5ce9584a","first_computed_at":"2026-07-05T07:02:23.183944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:23.183944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gqZNfjsKlEMNCgrh5ayrndPQdOU/kN7n1tfHwwX84wFHAn23Ym4V8J4JNkkwxq86Q+/1yNTxUIUMjCRmn9dUCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:23.184406Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.12147","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6937eabd6f717e0d3905cce90a3cc5f89950f5fe9a9157f43e4b39544a4131e","sha256:704c5e26be85e4b3aae4656184850dfee635887bfec77288b4465d00609c4d70"],"state_sha256":"e7e94c49951dfba8cf3a67941fe3d6db91e656b5807e14c48d0d6787bdc915eb"}