{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4ETCSH7Y3FDAJZDBNDACBLPZPY","short_pith_number":"pith:4ETCSH7Y","schema_version":"1.0","canonical_sha256":"e126291ff8d94604e46168c020adf97e16ab41bac269b1b3b127c8524d969442","source":{"kind":"arxiv","id":"2403.14760","version":3},"attestation_state":"computed","paper":{"title":"Can 3D Vision-Language Models Truly Understand Natural Language?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Edith Ngai, Jiahui Liu, Jihan Yang, Runyu Ding, Weipeng Deng, Xiaojuan Qi, Yijiang Li","submitted_at":"2024-03-21T18:02:20Z","abstract_excerpt":"Rapid advancements in 3D vision-language (3D-VL) tasks have opened up new avenues for human interaction with embodied agents or robots using natural language. Despite this progress, we find a notable limitation: existing 3D-VL models exhibit sensitivity to the styles of language input, struggling to understand sentences with the same semantic meaning but written in different variants. This observation raises a critical question: Can 3D vision-language models truly understand natural language? To test the language understandability of 3D-VL models, we first propose a language robustness task fo"},"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":"2403.14760","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T18:02:20Z","cross_cats_sorted":[],"title_canon_sha256":"4ed0c9a4890141ddf6661d89cce07215e2e305dac5d7872acdc6c15c8d191e29","abstract_canon_sha256":"1b324bf22ffdf465ea19ee8bfac1d6f6cb6828a1d5d99b9492b463f8d59a6489"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:32.532935Z","signature_b64":"cfeABmx/Na6Y+RKeeWLtHd1xtdGU+jmYCoBXDzKb6/Uwqfh4GzwWNr+3q+n+sLYThr2kCOXJ8prpuO2BnFIwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e126291ff8d94604e46168c020adf97e16ab41bac269b1b3b127c8524d969442","last_reissued_at":"2026-07-05T08:39:32.532410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:32.532410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can 3D Vision-Language Models Truly Understand Natural Language?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Edith Ngai, Jiahui Liu, Jihan Yang, Runyu Ding, Weipeng Deng, Xiaojuan Qi, Yijiang Li","submitted_at":"2024-03-21T18:02:20Z","abstract_excerpt":"Rapid advancements in 3D vision-language (3D-VL) tasks have opened up new avenues for human interaction with embodied agents or robots using natural language. Despite this progress, we find a notable limitation: existing 3D-VL models exhibit sensitivity to the styles of language input, struggling to understand sentences with the same semantic meaning but written in different variants. This observation raises a critical question: Can 3D vision-language models truly understand natural language? To test the language understandability of 3D-VL models, we first propose a language robustness task fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14760","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/2403.14760/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":"2403.14760","created_at":"2026-07-05T08:39:32.532471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.14760v3","created_at":"2026-07-05T08:39:32.532471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14760","created_at":"2026-07-05T08:39:32.532471+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ETCSH7Y3FDA","created_at":"2026-07-05T08:39:32.532471+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ETCSH7Y3FDAJZDB","created_at":"2026-07-05T08:39:32.532471+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ETCSH7Y","created_at":"2026-07-05T08:39:32.532471+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.05199","citing_title":"DEGround: An Effective Baseline for Ego-centric 3D Visual Grounding with a Homogeneous Framework","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ETCSH7Y3FDAJZDBNDACBLPZPY","json":"https://pith.science/pith/4ETCSH7Y3FDAJZDBNDACBLPZPY.json","graph_json":"https://pith.science/api/pith-number/4ETCSH7Y3FDAJZDBNDACBLPZPY/graph.json","events_json":"https://pith.science/api/pith-number/4ETCSH7Y3FDAJZDBNDACBLPZPY/events.json","paper":"https://pith.science/paper/4ETCSH7Y"},"agent_actions":{"view_html":"https://pith.science/pith/4ETCSH7Y3FDAJZDBNDACBLPZPY","download_json":"https://pith.science/pith/4ETCSH7Y3FDAJZDBNDACBLPZPY.json","view_paper":"https://pith.science/paper/4ETCSH7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.14760&json=true","fetch_graph":"https://pith.science/api/pith-number/4ETCSH7Y3FDAJZDBNDACBLPZPY/graph.json","fetch_events":"https://pith.science/api/pith-number/4ETCSH7Y3FDAJZDBNDACBLPZPY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ETCSH7Y3FDAJZDBNDACBLPZPY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ETCSH7Y3FDAJZDBNDACBLPZPY/action/storage_attestation","attest_author":"https://pith.science/pith/4ETCSH7Y3FDAJZDBNDACBLPZPY/action/author_attestation","sign_citation":"https://pith.science/pith/4ETCSH7Y3FDAJZDBNDACBLPZPY/action/citation_signature","submit_replication":"https://pith.science/pith/4ETCSH7Y3FDAJZDBNDACBLPZPY/action/replication_record"}},"created_at":"2026-07-05T08:39:32.532471+00:00","updated_at":"2026-07-05T08:39:32.532471+00:00"}