{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VRFWDBJFSROCX5GCJ3ZVSPTDF2","short_pith_number":"pith:VRFWDBJF","schema_version":"1.0","canonical_sha256":"ac4b618525945c2bf4c24ef3593e632e90833f62a7004ad0b85f0203336dd6db","source":{"kind":"arxiv","id":"2107.03438","version":3},"attestation_state":"computed","paper":{"title":"LanguageRefer: Spatial-Language Model for 3D Visual Grounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.RO","authors_text":"Ali Farhadi, Dieter Fox, Junha Roh, Karthik Desingh","submitted_at":"2021-07-07T18:55:03Z","abstract_excerpt":"For robots to understand human instructions and perform meaningful tasks in the near future, it is important to develop learned models that comprehend referential language to identify common objects in real-world 3D scenes. In this paper, we introduce a spatial-language model for a 3D visual grounding problem. Specifically, given a reconstructed 3D scene in the form of point clouds with 3D bounding boxes of potential object candidates, and a language utterance referring to a target object in the scene, our model successfully identifies the target object from a set of potential candidates. Spec"},"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":"2107.03438","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2021-07-07T18:55:03Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"c873b639f7f806d302ef3c293bae592e466963a3ad28dc60fbc44385f99860f9","abstract_canon_sha256":"5f47f72b43afd830350bbcd4fd514d1c81243836e088b7d4ddf7c68d45e20d87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:17.703504Z","signature_b64":"cviJC5stuJ7yRIzs1S94bw8tKNeYp4XIHCMGiWX74c7f0HTzYRn4/I7cyg7ForRwqWEsioBz+yDfaSPJsK2IBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac4b618525945c2bf4c24ef3593e632e90833f62a7004ad0b85f0203336dd6db","last_reissued_at":"2026-07-05T03:29:17.702938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:17.702938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LanguageRefer: Spatial-Language Model for 3D Visual Grounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.RO","authors_text":"Ali Farhadi, Dieter Fox, Junha Roh, Karthik Desingh","submitted_at":"2021-07-07T18:55:03Z","abstract_excerpt":"For robots to understand human instructions and perform meaningful tasks in the near future, it is important to develop learned models that comprehend referential language to identify common objects in real-world 3D scenes. In this paper, we introduce a spatial-language model for a 3D visual grounding problem. Specifically, given a reconstructed 3D scene in the form of point clouds with 3D bounding boxes of potential object candidates, and a language utterance referring to a target object in the scene, our model successfully identifies the target object from a set of potential candidates. Spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.03438","kind":"arxiv","version":3},"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/2107.03438/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":"2107.03438","created_at":"2026-07-05T03:29:17.703053+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.03438v3","created_at":"2026-07-05T03:29:17.703053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.03438","created_at":"2026-07-05T03:29:17.703053+00:00"},{"alias_kind":"pith_short_12","alias_value":"VRFWDBJFSROC","created_at":"2026-07-05T03:29:17.703053+00:00"},{"alias_kind":"pith_short_16","alias_value":"VRFWDBJFSROCX5GC","created_at":"2026-07-05T03:29:17.703053+00:00"},{"alias_kind":"pith_short_8","alias_value":"VRFWDBJF","created_at":"2026-07-05T03:29:17.703053+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28490","citing_title":"SSR3D-LLM: Structured Spatial Reasoning via Latent Steps for Fine-Grained Grounding in Unified 3D-LLMs","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VRFWDBJFSROCX5GCJ3ZVSPTDF2","json":"https://pith.science/pith/VRFWDBJFSROCX5GCJ3ZVSPTDF2.json","graph_json":"https://pith.science/api/pith-number/VRFWDBJFSROCX5GCJ3ZVSPTDF2/graph.json","events_json":"https://pith.science/api/pith-number/VRFWDBJFSROCX5GCJ3ZVSPTDF2/events.json","paper":"https://pith.science/paper/VRFWDBJF"},"agent_actions":{"view_html":"https://pith.science/pith/VRFWDBJFSROCX5GCJ3ZVSPTDF2","download_json":"https://pith.science/pith/VRFWDBJFSROCX5GCJ3ZVSPTDF2.json","view_paper":"https://pith.science/paper/VRFWDBJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.03438&json=true","fetch_graph":"https://pith.science/api/pith-number/VRFWDBJFSROCX5GCJ3ZVSPTDF2/graph.json","fetch_events":"https://pith.science/api/pith-number/VRFWDBJFSROCX5GCJ3ZVSPTDF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VRFWDBJFSROCX5GCJ3ZVSPTDF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VRFWDBJFSROCX5GCJ3ZVSPTDF2/action/storage_attestation","attest_author":"https://pith.science/pith/VRFWDBJFSROCX5GCJ3ZVSPTDF2/action/author_attestation","sign_citation":"https://pith.science/pith/VRFWDBJFSROCX5GCJ3ZVSPTDF2/action/citation_signature","submit_replication":"https://pith.science/pith/VRFWDBJFSROCX5GCJ3ZVSPTDF2/action/replication_record"}},"created_at":"2026-07-05T03:29:17.703053+00:00","updated_at":"2026-07-05T03:29:17.703053+00:00"}