{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BQYYD3ALJXX36LGJW66TWMJ67Y","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":"03d0879eec8c56b261be7f43a33fe915c7430afd2c9e98e9165e4626f26dde6c","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:56:22Z","title_canon_sha256":"b6d032c3800b99e3737bfc10db21eab9f4181f45fa4408bb15fd0434762fec40"},"schema_version":"1.0","source":{"id":"2503.10745","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10745","created_at":"2026-07-05T11:18:19Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10745v3","created_at":"2026-07-05T11:18:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10745","created_at":"2026-07-05T11:18:19Z"},{"alias_kind":"pith_short_12","alias_value":"BQYYD3ALJXX3","created_at":"2026-07-05T11:18:19Z"},{"alias_kind":"pith_short_16","alias_value":"BQYYD3ALJXX36LGJ","created_at":"2026-07-05T11:18:19Z"},{"alias_kind":"pith_short_8","alias_value":"BQYYD3AL","created_at":"2026-07-05T11:18:19Z"}],"graph_snapshots":[{"event_id":"sha256:a7daaa9d53f40439af619b4c3b9b3936b44dfbd8667a8fc615dec8fd05543b1f","target":"graph","created_at":"2026-07-05T11:18:19Z","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/2503.10745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Progress in 3D vision-language learning has been hindered by the scarcity of large-scale 3D datasets. We introduce UniVLG, a unified architecture for 2D and 3D vision-language understanding that bridges the gap between existing 2D-centric models and the rich 3D sensory data available in embodied systems. Our approach initializes most model weights from pre-trained 2D models and trains on both 2D and 3D vision-language data. We propose a novel language-conditioned mask decoder shared across 2D and 3D modalities to ground objects effectively in both RGB and RGB-D images, outperforming box-based ","authors_text":"Ada Martin, Alexander Sax, Alexander Swerdlow, Ayush Jain, Franziska Meier, Katerina Fragkiadaki, Sergio Arnaud, Yuzhou Wang","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:56:22Z","title":"Unifying 2D and 3D Vision-Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10745","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":"sha256:9a7a50da0498d7ac26feaf1c11e3329150bf1378c74aed929f425c610230a436","target":"record","created_at":"2026-07-05T11:18:19Z","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":"03d0879eec8c56b261be7f43a33fe915c7430afd2c9e98e9165e4626f26dde6c","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:56:22Z","title_canon_sha256":"b6d032c3800b99e3737bfc10db21eab9f4181f45fa4408bb15fd0434762fec40"},"schema_version":"1.0","source":{"id":"2503.10745","kind":"arxiv","version":3}},"canonical_sha256":"0c3181ec0b4defbf2cc9b7bd3b313efe39d3d1412707a14c2f09e17d218a386d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c3181ec0b4defbf2cc9b7bd3b313efe39d3d1412707a14c2f09e17d218a386d","first_computed_at":"2026-07-05T11:18:19.370472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:19.370472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ntl0ugVAUGGCXImq5K2dcLCGg09aVT4EDkMakYoSP6tADJRYVwXxn/JW75eRa1VmY47CLeAmhfJqHTUPDSULAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:19.370958Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.10745","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a7a50da0498d7ac26feaf1c11e3329150bf1378c74aed929f425c610230a436","sha256:a7daaa9d53f40439af619b4c3b9b3936b44dfbd8667a8fc615dec8fd05543b1f"],"state_sha256":"2f2bc2c08f0a140b8eeb5a9a5a12fff21e66ff31b712e78cfde36dd612ee06e5"}