{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PIB6YOB5J5B4CVIBAIKJ2EV2LR","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":"7c5f04f6034551c6f5df8e5dc11307d73a0da77b886ea05887ccbdd75ca70741","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-12-07T18:51:19Z","title_canon_sha256":"29d5956f4088a4f69d01ef4f78ad4aabf7f524e42c04316896490cf687489264"},"schema_version":"1.0","source":{"id":"2312.04533","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.04533","created_at":"2026-07-05T08:49:52Z"},{"alias_kind":"arxiv_version","alias_value":"2312.04533v2","created_at":"2026-07-05T08:49:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04533","created_at":"2026-07-05T08:49:52Z"},{"alias_kind":"pith_short_12","alias_value":"PIB6YOB5J5B4","created_at":"2026-07-05T08:49:52Z"},{"alias_kind":"pith_short_16","alias_value":"PIB6YOB5J5B4CVIB","created_at":"2026-07-05T08:49:52Z"},{"alias_kind":"pith_short_8","alias_value":"PIB6YOB5","created_at":"2026-07-05T08:49:52Z"}],"graph_snapshots":[{"event_id":"sha256:3d5d57eb46aa8c8624a85d6be159f4970ef80515caf8fa34005937bac9cfdfb7","target":"graph","created_at":"2026-07-05T08:49:52Z","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/2312.04533/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Dream2Real, a robotics framework which integrates vision-language models (VLMs) trained on 2D data into a 3D object rearrangement pipeline. This is achieved by the robot autonomously constructing a 3D representation of the scene, where objects can be rearranged virtually and an image of the resulting arrangement rendered. These renders are evaluated by a VLM, so that the arrangement which best satisfies the user instruction is selected and recreated in the real world with pick-and-place. This enables language-conditioned rearrangement to be performed zero-shot, without needing to ","authors_text":"Edward Johns, Ignacio Alzugaray, Ivan Kapelyukh, Yifei Ren","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-12-07T18:51:19Z","title":"Dream2Real: Zero-Shot 3D Object Rearrangement with Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04533","kind":"arxiv","version":2},"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":"sha256:20d8649bf3e9fc78b0f9138af76e59d9608d1f1a878bdd3b55e71af4dde0ee64","target":"record","created_at":"2026-07-05T08:49:52Z","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":"7c5f04f6034551c6f5df8e5dc11307d73a0da77b886ea05887ccbdd75ca70741","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-12-07T18:51:19Z","title_canon_sha256":"29d5956f4088a4f69d01ef4f78ad4aabf7f524e42c04316896490cf687489264"},"schema_version":"1.0","source":{"id":"2312.04533","kind":"arxiv","version":2}},"canonical_sha256":"7a03ec383d4f43c1550102149d12ba5c57fc30d80c7f67a71ed5aa9c207e206c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a03ec383d4f43c1550102149d12ba5c57fc30d80c7f67a71ed5aa9c207e206c","first_computed_at":"2026-07-05T08:49:52.043095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:49:52.043095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dgziKsFKKfte8i9mZiIjDBuz9NKL/wpCTnpaUX2lrTklmzZH5j59q6i00qtPcXKA3O2gAhuraDCWX0oR7x0SDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:49:52.043526Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.04533","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20d8649bf3e9fc78b0f9138af76e59d9608d1f1a878bdd3b55e71af4dde0ee64","sha256:3d5d57eb46aa8c8624a85d6be159f4970ef80515caf8fa34005937bac9cfdfb7"],"state_sha256":"ff09f013d454f397df62c097cbb06c38a6b2d7aecd1219b722e8aa6b731dcf78"}