{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LJHUW6AYODUNYUY3UBFIV6JLS7","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":"4f47ee0a5b4dedd7b27c6fe1061559319ed77d33695b15255171ac542dd21944","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-18T01:21:38Z","title_canon_sha256":"d3f6a0a01ad1f88f36aa4d2acac57a9346d7c35c4738df676395e28791d80bc8"},"schema_version":"1.0","source":{"id":"2311.12871","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.12871","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2311.12871v3","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12871","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"LJHUW6AYODUN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LJHUW6AYODUNYUY3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LJHUW6AY","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:64cc669d2f807acf7829afb68396fa35998860143b9eae37ac20dba092fd87e8","target":"graph","created_at":"2026-05-17T23:38:13Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Through extensive experiments, we demonstrate LEO's remarkable proficiency across a wide spectrum of tasks, including 3D captioning, question answering, embodied reasoning, navigation and manipulation."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The central claim assumes that the collected large-scale 3D VL and VLA datasets plus the two-stage training procedure are sufficient to produce generalist performance that transfers beyond the specific benchmarks shown."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"LEO is an embodied generalist agent that performs 3D captioning, question answering, reasoning, navigation, and manipulation after 3D vision-language alignment followed by vision-language-action instruction tuning on large-scale object- and scene-level datasets."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"LEO trains as a 3D embodied generalist agent through two-stage alignment on large vision-language and vision-language-action datasets."}],"snapshot_sha256":"1ba28f9ab79b4d87813e61ea5758858db44d6e974a02ee779f4e777be0d75666"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4a0c00bfe591c510c5d6f0e5e9394e6cb682f8a0b168a0fdf54511e583e49651"},"paper":{"abstract_excerpt":"Leveraging massive knowledge from large language models (LLMs), recent machine learning models show notable successes in general-purpose task solving in diverse domains such as computer vision and robotics. However, several significant challenges remain: (i) most of these models rely on 2D images yet exhibit a limited capacity for 3D input; (ii) these models rarely explore the tasks inherently defined in 3D world, e.g., 3D grounding, embodied reasoning and acting. We argue these limitations significantly hinder current models from performing real-world tasks and approaching general intelligenc","authors_text":"Baoxiong Jia, Jiangyong Huang, Puhao Li, Qing Li, Silong Yong, Siyuan Huang, Song-Chun Zhu, Xiaojian Ma, Xiongkun Linghu, Yan Wang","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"LEO trains as a 3D embodied generalist agent through two-stage alignment on large vision-language and vision-language-action datasets.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-18T01:21:38Z","title":"An Embodied Generalist Agent in 3D World"},"references":{"count":27,"internal_anchors":10,"resolved_work":27,"sample":[{"cited_arxiv_id":"2302.04023","doi":"","is_internal_anchor":true,"ref_index":1,"title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","work_id":"41dff74c-00b2-4c77-a674-9f86030c06c8","year":2022},{"cited_arxiv_id":"2212.06817","doi":"","is_internal_anchor":true,"ref_index":2,"title":"RT-1: Robotics Transformer for Real-World Control at Scale","work_id":"e11bda85-8531-46bc-a07f-d0ade3643ab1","year":2022},{"cited_arxiv_id":"2210.11416","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Scaling Instruction-Finetuned Language Models","work_id":"8405abb1-7558-4fdf-af24-f4c52fa77a06","year":2022},{"cited_arxiv_id":"2304.15010","doi":"","is_internal_anchor":true,"ref_index":4,"title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","work_id":"0fe2cfd8-d442-4ceb-b1a9-a465704f39b2","year":2022},{"cited_arxiv_id":"2001.08361","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Scaling Laws for Neural Language Models","work_id":"b7dd8749-9c45-4977-ab9b-64478dce1ae8","year":2001}],"snapshot_sha256":"637ea65950bdb3b83fba8253b8026046cca6267d4912d88a95831e9a9b795c1e"},"source":{"id":"2311.12871","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-17T14:15:53.121198Z","id":"d9ad041c-600a-47ef-85dc-ec0ba0765a0a","model_set":{"reader":"grok-4.3"},"one_line_summary":"LEO is an embodied generalist agent that performs 3D captioning, question answering, reasoning, navigation, and manipulation after 3D vision-language alignment followed by vision-language-action instruction tuning on large-scale object- and scene-level datasets.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"LEO trains as a 3D embodied generalist agent through two-stage alignment on large vision-language and vision-language-action datasets.","strongest_claim":"Through extensive experiments, we demonstrate LEO's remarkable proficiency across a wide spectrum of tasks, including 3D captioning, question answering, embodied reasoning, navigation and manipulation.","weakest_assumption":"The central claim assumes that the collected large-scale 3D VL and VLA datasets plus the two-stage training procedure are sufficient to produce generalist performance that transfers beyond the specific benchmarks shown."}},"verdict_id":"d9ad041c-600a-47ef-85dc-ec0ba0765a0a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ab97f1dc25f78e43405aa56ec5da2a35d79977182fdb75876a0bca5219f1a0de","target":"record","created_at":"2026-05-17T23:38:13Z","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":"4f47ee0a5b4dedd7b27c6fe1061559319ed77d33695b15255171ac542dd21944","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-18T01:21:38Z","title_canon_sha256":"d3f6a0a01ad1f88f36aa4d2acac57a9346d7c35c4738df676395e28791d80bc8"},"schema_version":"1.0","source":{"id":"2311.12871","kind":"arxiv","version":3}},"canonical_sha256":"5a4f4b781870e8dc531ba04a8af92b97ce9163b929a16e03aaf471e3739edb0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a4f4b781870e8dc531ba04a8af92b97ce9163b929a16e03aaf471e3739edb0f","first_computed_at":"2026-05-17T23:38:13.838991Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:13.838991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZpXWOEqX6grMWOJ2l+2qtq7Nb4Ly9BPmSudqWIy0jq61p92OePnffzC+oVNmfoGXZ1Wk6my3sTTs0GtM9TRQCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:13.839721Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.12871","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab97f1dc25f78e43405aa56ec5da2a35d79977182fdb75876a0bca5219f1a0de","sha256:64cc669d2f807acf7829afb68396fa35998860143b9eae37ac20dba092fd87e8"],"state_sha256":"8dacba84fa9ad53e8ca4984bbe834625a4afe5bb6073ce058dadba18fdd35728"}