{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4ETCSH7Y3FDAJZDBNDACBLPZPY","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":"1b324bf22ffdf465ea19ee8bfac1d6f6cb6828a1d5d99b9492b463f8d59a6489","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T18:02:20Z","title_canon_sha256":"4ed0c9a4890141ddf6661d89cce07215e2e305dac5d7872acdc6c15c8d191e29"},"schema_version":"1.0","source":{"id":"2403.14760","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14760","created_at":"2026-07-05T08:39:32Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14760v3","created_at":"2026-07-05T08:39:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14760","created_at":"2026-07-05T08:39:32Z"},{"alias_kind":"pith_short_12","alias_value":"4ETCSH7Y3FDA","created_at":"2026-07-05T08:39:32Z"},{"alias_kind":"pith_short_16","alias_value":"4ETCSH7Y3FDAJZDB","created_at":"2026-07-05T08:39:32Z"},{"alias_kind":"pith_short_8","alias_value":"4ETCSH7Y","created_at":"2026-07-05T08:39:32Z"}],"graph_snapshots":[{"event_id":"sha256:02e7051683c5f355e119dbd325937b96af4d5c817bfe4460766b972e10f1f34d","target":"graph","created_at":"2026-07-05T08:39:32Z","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/2403.14760/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Edith Ngai, Jiahui Liu, Jihan Yang, Runyu Ding, Weipeng Deng, Xiaojuan Qi, Yijiang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T18:02:20Z","title":"Can 3D Vision-Language Models Truly Understand Natural Language?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14760","kind":"arxiv","version":3},"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":"sha256:8c856dbf04d0c572ef39d51f1448096a580fd70042e41d6668525e4c7aaf443f","target":"record","created_at":"2026-07-05T08:39:32Z","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":"1b324bf22ffdf465ea19ee8bfac1d6f6cb6828a1d5d99b9492b463f8d59a6489","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T18:02:20Z","title_canon_sha256":"4ed0c9a4890141ddf6661d89cce07215e2e305dac5d7872acdc6c15c8d191e29"},"schema_version":"1.0","source":{"id":"2403.14760","kind":"arxiv","version":3}},"canonical_sha256":"e126291ff8d94604e46168c020adf97e16ab41bac269b1b3b127c8524d969442","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e126291ff8d94604e46168c020adf97e16ab41bac269b1b3b127c8524d969442","first_computed_at":"2026-07-05T08:39:32.532410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:32.532410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cfeABmx/Na6Y+RKeeWLtHd1xtdGU+jmYCoBXDzKb6/Uwqfh4GzwWNr+3q+n+sLYThr2kCOXJ8prpuO2BnFIwDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:32.532935Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.14760","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c856dbf04d0c572ef39d51f1448096a580fd70042e41d6668525e4c7aaf443f","sha256:02e7051683c5f355e119dbd325937b96af4d5c817bfe4460766b972e10f1f34d"],"state_sha256":"71bcb37064d0a2a54cfd0a57a2f196fc7c8c06a743f34104fae335fbfcc29d82"}