{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:342L4ORVWWVNZEBWXM5QVTGKYF","short_pith_number":"pith:342L4ORV","schema_version":"1.0","canonical_sha256":"df34be3a35b5aadc9036bb3b0acccac15cdfeda8aa031b644946b0ec5ce9584a","source":{"kind":"arxiv","id":"2310.12147","version":1},"attestation_state":"computed","paper":{"title":"InViG: Benchmarking Interactive Visual Grounding with 500K Human-Robot Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Hanbo Zhang, Jie Xu, Tao Kong, Yuchen Mo","submitted_at":"2023-10-18T17:57:05Z","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 "},"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":"2310.12147","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-18T17:57:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"916f00503c7e4f99b5ead585c56ed128823c4cdb5b6051bd582ae53d6649fbd3","abstract_canon_sha256":"4c44eb9b0533f056d3383aacd0c2652c0c4493324f777f34470675c0a66bcc07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:23.184406Z","signature_b64":"gqZNfjsKlEMNCgrh5ayrndPQdOU/kN7n1tfHwwX84wFHAn23Ym4V8J4JNkkwxq86Q+/1yNTxUIUMjCRmn9dUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df34be3a35b5aadc9036bb3b0acccac15cdfeda8aa031b644946b0ec5ce9584a","last_reissued_at":"2026-07-05T07:02:23.183944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:23.183944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InViG: Benchmarking Interactive Visual Grounding with 500K Human-Robot Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Hanbo Zhang, Jie Xu, Tao Kong, Yuchen Mo","submitted_at":"2023-10-18T17:57:05Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12147","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/2310.12147/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":"2310.12147","created_at":"2026-07-05T07:02:23.183999+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.12147v1","created_at":"2026-07-05T07:02:23.183999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12147","created_at":"2026-07-05T07:02:23.183999+00:00"},{"alias_kind":"pith_short_12","alias_value":"342L4ORVWWVN","created_at":"2026-07-05T07:02:23.183999+00:00"},{"alias_kind":"pith_short_16","alias_value":"342L4ORVWWVNZEBW","created_at":"2026-07-05T07:02:23.183999+00:00"},{"alias_kind":"pith_short_8","alias_value":"342L4ORV","created_at":"2026-07-05T07:02:23.183999+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/342L4ORVWWVNZEBWXM5QVTGKYF","json":"https://pith.science/pith/342L4ORVWWVNZEBWXM5QVTGKYF.json","graph_json":"https://pith.science/api/pith-number/342L4ORVWWVNZEBWXM5QVTGKYF/graph.json","events_json":"https://pith.science/api/pith-number/342L4ORVWWVNZEBWXM5QVTGKYF/events.json","paper":"https://pith.science/paper/342L4ORV"},"agent_actions":{"view_html":"https://pith.science/pith/342L4ORVWWVNZEBWXM5QVTGKYF","download_json":"https://pith.science/pith/342L4ORVWWVNZEBWXM5QVTGKYF.json","view_paper":"https://pith.science/paper/342L4ORV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.12147&json=true","fetch_graph":"https://pith.science/api/pith-number/342L4ORVWWVNZEBWXM5QVTGKYF/graph.json","fetch_events":"https://pith.science/api/pith-number/342L4ORVWWVNZEBWXM5QVTGKYF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/342L4ORVWWVNZEBWXM5QVTGKYF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/342L4ORVWWVNZEBWXM5QVTGKYF/action/storage_attestation","attest_author":"https://pith.science/pith/342L4ORVWWVNZEBWXM5QVTGKYF/action/author_attestation","sign_citation":"https://pith.science/pith/342L4ORVWWVNZEBWXM5QVTGKYF/action/citation_signature","submit_replication":"https://pith.science/pith/342L4ORVWWVNZEBWXM5QVTGKYF/action/replication_record"}},"created_at":"2026-07-05T07:02:23.183999+00:00","updated_at":"2026-07-05T07:02:23.183999+00:00"}