{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RATM4PPY5A25ER7KSOOOW6WY2Q","short_pith_number":"pith:RATM4PPY","canonical_record":{"source":{"id":"2605.13018","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T05:17:51Z","cross_cats_sorted":[],"title_canon_sha256":"68ee27e06f17cfd3757253330c561e3288ed8d91c55bef3d151b1f40f4e82243","abstract_canon_sha256":"fbc3a18548d4e4fa4199a3ef4078067be1635d9227eb0db676e7e33d1ee6e5ee"},"schema_version":"1.0"},"canonical_sha256":"8826ce3df8e835d247ea939ceb7ad8d407a4973b35e6ef28580ed71b594b5eba","source":{"kind":"arxiv","id":"2605.13018","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13018","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13018v1","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13018","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"pith_short_12","alias_value":"RATM4PPY5A25","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"RATM4PPY5A25ER7K","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"RATM4PPY","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RATM4PPY5A25ER7KSOOOW6WY2Q","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13018","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T05:17:51Z","cross_cats_sorted":[],"title_canon_sha256":"68ee27e06f17cfd3757253330c561e3288ed8d91c55bef3d151b1f40f4e82243","abstract_canon_sha256":"fbc3a18548d4e4fa4199a3ef4078067be1635d9227eb0db676e7e33d1ee6e5ee"},"schema_version":"1.0"},"canonical_sha256":"8826ce3df8e835d247ea939ceb7ad8d407a4973b35e6ef28580ed71b594b5eba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:00.097114Z","signature_b64":"8DRMozRDbY0K1L2Xq6/webHvBevakhOT+8NSqg7FqtxPKmAbi/9YIBN740mg5pLanWyCZ1Y31lobiiJU/ZWnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8826ce3df8e835d247ea939ceb7ad8d407a4973b35e6ef28580ed71b594b5eba","last_reissued_at":"2026-05-18T03:09:00.096596Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:00.096596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13018","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y0JD59FdnIpD82WkGYC5uSkOMfEg8onDf1b+ixisl2eyEDGgiHPHgFwEfAn6GINI6ueg4dATIQcA233H3vHZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:05:38.677702Z"},"content_sha256":"5043bd0a0ff1608ce7ca037f89b9db1bbe6e59c534a238c45301830de524241b","schema_version":"1.0","event_id":"sha256:5043bd0a0ff1608ce7ca037f89b9db1bbe6e59c534a238c45301830de524241b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RATM4PPY5A25ER7KSOOOW6WY2Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OCH3R: Object-Centric Holistic 3D Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"OCH3R reconstructs every object in a scene with its 6D pose and detailed 3D shape from a single RGB image in one forward pass.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Leonidas Guibas, Xiang Wan, Yang You, Yi Du","submitted_at":"2026-05-13T05:17:51Z","abstract_excerpt":"Object-centric scene understanding is a fundamental challenge in computer vision. Existing approaches often rely on multi-stage pipelines that first apply pre-trained segmentors to extract individual objects, followed by per-object 3D reconstruction. Such methods are computationally expensive, fragile to segmentation errors, and scale poorly with scene complexity. We introduce OCH3R, a unified framework for Object-Centric Holistic 3D Reconstruction from a single RGB image. OCH3R performs one forward pass to simultaneously predict all object instances with their 6D poses and detailed 3D reconst"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"OCH3R performs one forward pass to simultaneously predict all object instances with their 6D poses and detailed 3D reconstructions, achieving state-of-the-art performance across monocular depth estimation, open-vocabulary semantic segmentation, and RGB-only category-level 6D pose estimation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That predicted 6D poses are sufficiently accurate to transform Gaussians into canonical space for reliable supervision, and that a fixed number of Gaussians per object can represent detailed shapes without per-image label generation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A transformer predicts per-pixel CLIP embeddings, metric depth, NOCS coordinates, and fixed 3D Gaussians per object, supervised by canonical-space alignment after pose prediction, achieving SOTA on depth, segmentation, and category-level pose tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"OCH3R reconstructs every object in a scene with its 6D pose and detailed 3D shape from a single RGB image in one forward pass.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c200a8a768416045a77769b1c4525ebf605c6e1e73a556e0dc22dbda870a8343"},"source":{"id":"2605.13018","kind":"arxiv","version":1},"verdict":{"id":"ed2f513b-75dd-40ca-8dc0-9976629e9c13","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:25:01.995579Z","strongest_claim":"OCH3R performs one forward pass to simultaneously predict all object instances with their 6D poses and detailed 3D reconstructions, achieving state-of-the-art performance across monocular depth estimation, open-vocabulary semantic segmentation, and RGB-only category-level 6D pose estimation.","one_line_summary":"A transformer predicts per-pixel CLIP embeddings, metric depth, NOCS coordinates, and fixed 3D Gaussians per object, supervised by canonical-space alignment after pose prediction, achieving SOTA on depth, segmentation, and category-level pose tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That predicted 6D poses are sufficiently accurate to transform Gaussians into canonical space for reliable supervision, and that a fixed number of Gaussians per object can represent detailed shapes without per-image label generation.","pith_extraction_headline":"OCH3R reconstructs every object in a scene with its 6D pose and detailed 3D shape from a single RGB image in one forward pass."},"references":{"count":22,"sample":[{"doi":"","year":2023,"title":"Zoedepth: Zero-shot transfer by com- bining relative and metric depth, 2023","work_id":"e637db31-222e-4a05-9b3f-4d2a53040230","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Richter, and Vladlen Koltun","work_id":"a5d2be1b-6a48-4538-9711-d8e88ca12ed7","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Secondpose: Se(3)- consistent dual-stream feature fusion for category-level pose estimation","work_id":"e24a2795-7d82-4c48-a7bf-4c42dcca51b3","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Garmentnets: Category-level pose estimation for garments via canonical space shape com- pletion, 2021","work_id":"3d8a37ca-45b4-4936-b133-135ef37d60b6","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"McHugh, and Vincent Vanhoucke","work_id":"eb77246e-9045-4ebf-99ec-c015fb0f8443","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":22,"snapshot_sha256":"7d8d9aa9c25df1afe8f62a05c6efcb00ed87bdbd4c5e4cbef3e8c41ab82290ba","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"ed2f513b-75dd-40ca-8dc0-9976629e9c13"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wVk8wRak6e69IXe8jQ2B1Z0DghX6llcl+afdbtO7AjqQHl+adaXK9eChzNlIutwUDd1MYax2Fxj2wryV4KfVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:05:38.678426Z"},"content_sha256":"6c58cc938ee89fa22e80081de548597114183543f562985cba9c76d94a78e683","schema_version":"1.0","event_id":"sha256:6c58cc938ee89fa22e80081de548597114183543f562985cba9c76d94a78e683"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RATM4PPY5A25ER7KSOOOW6WY2Q/bundle.json","state_url":"https://pith.science/pith/RATM4PPY5A25ER7KSOOOW6WY2Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RATM4PPY5A25ER7KSOOOW6WY2Q/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T12:05:38Z","links":{"resolver":"https://pith.science/pith/RATM4PPY5A25ER7KSOOOW6WY2Q","bundle":"https://pith.science/pith/RATM4PPY5A25ER7KSOOOW6WY2Q/bundle.json","state":"https://pith.science/pith/RATM4PPY5A25ER7KSOOOW6WY2Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RATM4PPY5A25ER7KSOOOW6WY2Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RATM4PPY5A25ER7KSOOOW6WY2Q","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":"fbc3a18548d4e4fa4199a3ef4078067be1635d9227eb0db676e7e33d1ee6e5ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T05:17:51Z","title_canon_sha256":"68ee27e06f17cfd3757253330c561e3288ed8d91c55bef3d151b1f40f4e82243"},"schema_version":"1.0","source":{"id":"2605.13018","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13018","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13018v1","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13018","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"pith_short_12","alias_value":"RATM4PPY5A25","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"RATM4PPY5A25ER7K","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"RATM4PPY","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:6c58cc938ee89fa22e80081de548597114183543f562985cba9c76d94a78e683","target":"graph","created_at":"2026-05-18T03:09:00Z","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":"OCH3R performs one forward pass to simultaneously predict all object instances with their 6D poses and detailed 3D reconstructions, achieving state-of-the-art performance across monocular depth estimation, open-vocabulary semantic segmentation, and RGB-only category-level 6D pose estimation."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That predicted 6D poses are sufficiently accurate to transform Gaussians into canonical space for reliable supervision, and that a fixed number of Gaussians per object can represent detailed shapes without per-image label generation."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A transformer predicts per-pixel CLIP embeddings, metric depth, NOCS coordinates, and fixed 3D Gaussians per object, supervised by canonical-space alignment after pose prediction, achieving SOTA on depth, segmentation, and category-level pose tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"OCH3R reconstructs every object in a scene with its 6D pose and detailed 3D shape from a single RGB image in one forward pass."}],"snapshot_sha256":"c200a8a768416045a77769b1c4525ebf605c6e1e73a556e0dc22dbda870a8343"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Object-centric scene understanding is a fundamental challenge in computer vision. Existing approaches often rely on multi-stage pipelines that first apply pre-trained segmentors to extract individual objects, followed by per-object 3D reconstruction. Such methods are computationally expensive, fragile to segmentation errors, and scale poorly with scene complexity. We introduce OCH3R, a unified framework for Object-Centric Holistic 3D Reconstruction from a single RGB image. OCH3R performs one forward pass to simultaneously predict all object instances with their 6D poses and detailed 3D reconst","authors_text":"Leonidas Guibas, Xiang Wan, Yang You, Yi Du","cross_cats":[],"headline":"OCH3R reconstructs every object in a scene with its 6D pose and detailed 3D shape from a single RGB image in one forward pass.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T05:17:51Z","title":"OCH3R: Object-Centric Holistic 3D Reconstruction"},"references":{"count":22,"internal_anchors":0,"resolved_work":22,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Zoedepth: Zero-shot transfer by com- bining relative and metric depth, 2023","work_id":"e637db31-222e-4a05-9b3f-4d2a53040230","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Richter, and Vladlen Koltun","work_id":"a5d2be1b-6a48-4538-9711-d8e88ca12ed7","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Secondpose: Se(3)- consistent dual-stream feature fusion for category-level pose estimation","work_id":"e24a2795-7d82-4c48-a7bf-4c42dcca51b3","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Garmentnets: Category-level pose estimation for garments via canonical space shape com- pletion, 2021","work_id":"3d8a37ca-45b4-4936-b133-135ef37d60b6","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"McHugh, and Vincent Vanhoucke","work_id":"eb77246e-9045-4ebf-99ec-c015fb0f8443","year":2022}],"snapshot_sha256":"7d8d9aa9c25df1afe8f62a05c6efcb00ed87bdbd4c5e4cbef3e8c41ab82290ba"},"source":{"id":"2605.13018","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:25:01.995579Z","id":"ed2f513b-75dd-40ca-8dc0-9976629e9c13","model_set":{"reader":"grok-4.3"},"one_line_summary":"A transformer predicts per-pixel CLIP embeddings, metric depth, NOCS coordinates, and fixed 3D Gaussians per object, supervised by canonical-space alignment after pose prediction, achieving SOTA on depth, segmentation, and category-level pose tasks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"OCH3R reconstructs every object in a scene with its 6D pose and detailed 3D shape from a single RGB image in one forward pass.","strongest_claim":"OCH3R performs one forward pass to simultaneously predict all object instances with their 6D poses and detailed 3D reconstructions, achieving state-of-the-art performance across monocular depth estimation, open-vocabulary semantic segmentation, and RGB-only category-level 6D pose estimation.","weakest_assumption":"That predicted 6D poses are sufficiently accurate to transform Gaussians into canonical space for reliable supervision, and that a fixed number of Gaussians per object can represent detailed shapes without per-image label generation."}},"verdict_id":"ed2f513b-75dd-40ca-8dc0-9976629e9c13"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5043bd0a0ff1608ce7ca037f89b9db1bbe6e59c534a238c45301830de524241b","target":"record","created_at":"2026-05-18T03:09:00Z","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":"fbc3a18548d4e4fa4199a3ef4078067be1635d9227eb0db676e7e33d1ee6e5ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T05:17:51Z","title_canon_sha256":"68ee27e06f17cfd3757253330c561e3288ed8d91c55bef3d151b1f40f4e82243"},"schema_version":"1.0","source":{"id":"2605.13018","kind":"arxiv","version":1}},"canonical_sha256":"8826ce3df8e835d247ea939ceb7ad8d407a4973b35e6ef28580ed71b594b5eba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8826ce3df8e835d247ea939ceb7ad8d407a4973b35e6ef28580ed71b594b5eba","first_computed_at":"2026-05-18T03:09:00.096596Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:00.096596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8DRMozRDbY0K1L2Xq6/webHvBevakhOT+8NSqg7FqtxPKmAbi/9YIBN740mg5pLanWyCZ1Y31lobiiJU/ZWnAw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:00.097114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13018","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5043bd0a0ff1608ce7ca037f89b9db1bbe6e59c534a238c45301830de524241b","sha256:6c58cc938ee89fa22e80081de548597114183543f562985cba9c76d94a78e683"],"state_sha256":"23986cf6873effed2d795db3f5eb489217befb612cace7c446e91ec94143359a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PiEIiUeGnP/zQMNPP9wd1/ItIxV84KIYT05v55X4FE/JUnAZ4nJoAgewRehnQmwykh8iUdfr+o5zc0hLO+gcAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T12:05:38.681245Z","bundle_sha256":"bc1d8c0d3945083278b6a2d848f0bfb227f251b2ce9935f51c697c1178e2fa99"}}