{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NYD5ZMD3AZB442OWHKOCD5CWQL","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":"095d247b1221f334a15207bf0efa358c7d1296e3321cefedc3b29c935a8c7e77","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T20:48:55Z","title_canon_sha256":"a55a6ebc9027908514e83f2f1041c154626a08f32092dd9dd9169418b9f53689"},"schema_version":"1.0","source":{"id":"2605.30561","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30561","created_at":"2026-06-01T01:03:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30561v1","created_at":"2026-06-01T01:03:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30561","created_at":"2026-06-01T01:03:01Z"},{"alias_kind":"pith_short_12","alias_value":"NYD5ZMD3AZB4","created_at":"2026-06-01T01:03:01Z"},{"alias_kind":"pith_short_16","alias_value":"NYD5ZMD3AZB442OW","created_at":"2026-06-01T01:03:01Z"},{"alias_kind":"pith_short_8","alias_value":"NYD5ZMD3","created_at":"2026-06-01T01:03:01Z"}],"graph_snapshots":[{"event_id":"sha256:c0d31546de6759b19d14157291e258dfdb6448b3816bcab7e69370787ab33662","target":"graph","created_at":"2026-06-01T01:03:01Z","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/2605.30561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models (VLMs) enable a unified model to solve various vision tasks through prompting. They have shown promising performance in semantic understanding. However, 3D understanding still largely relies on expert vision models with complex task-specific designs. The key argument this work wants to make is that VLMs are native 3D learners. Our in-depth large scale study shows that 1) focal length unification, 2) text-based pixel reference and 3) data mixture and scaling, are all you need for effective 3D learning. Model architecture changes, large models, heavy data augmentations, an","authors_text":"Vikas Chandra, Yangyang Shi, Yunyang Xiong, Zechun Liu, Zhipeng Cai, Zhuang Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T20:48:55Z","title":"VLM3: Vision Language Models Are Native 3D Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30561","kind":"arxiv","version":1},"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:bf4582604a60e77383c2c5048913f5afab38535e79e05751f11902e906e53e81","target":"record","created_at":"2026-06-01T01:03:01Z","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":"095d247b1221f334a15207bf0efa358c7d1296e3321cefedc3b29c935a8c7e77","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T20:48:55Z","title_canon_sha256":"a55a6ebc9027908514e83f2f1041c154626a08f32092dd9dd9169418b9f53689"},"schema_version":"1.0","source":{"id":"2605.30561","kind":"arxiv","version":1}},"canonical_sha256":"6e07dcb07b0643ce69d63a9c21f45682d9db91f085c9ebad5f2784d70215bf08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e07dcb07b0643ce69d63a9c21f45682d9db91f085c9ebad5f2784d70215bf08","first_computed_at":"2026-06-01T01:03:01.186935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:01.186935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F2IyP4DGjghRgHkX65fe+TdJMz6GYBZKvVtNicnzqn+Zee6nHaj/i0PuoUDHUileKynzXv6JeCsceVGIdOfCCw==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:01.187915Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30561","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf4582604a60e77383c2c5048913f5afab38535e79e05751f11902e906e53e81","sha256:c0d31546de6759b19d14157291e258dfdb6448b3816bcab7e69370787ab33662"],"state_sha256":"0ddd7c8d5bfe72975bc95595b4d5943d81730038d7cee0aecf2fb7d5b7d31e49"}