{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PWNJNT6FFXOM6YEMU55X4WMMOH","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":"e4f4a7ad21a93e1a57c8a45cc04767b2c114d31b84d1ba346804e6a27cfaacb7","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T08:17:45Z","title_canon_sha256":"a6cdfe85a14cd8dc2533866ec7870bdcf28b75a6368665ccbb928104d497dfed"},"schema_version":"1.0","source":{"id":"2605.13152","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13152","created_at":"2026-05-18T03:08:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13152v1","created_at":"2026-05-18T03:08:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13152","created_at":"2026-05-18T03:08:57Z"},{"alias_kind":"pith_short_12","alias_value":"PWNJNT6FFXOM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"PWNJNT6FFXOM6YEM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"PWNJNT6F","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:266558075149cdf505c0a050719d0957fc2c3c474e555e94be3e1344c2cb022c","target":"graph","created_at":"2026-05-18T03:08:57Z","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":"EvObj integrates two innovative modules: (1) An object discerning module that dynamically refines object candidates, enabling continuous adaptation of object priors to target domains; and (2) An object completion module that reconstructs partial geometries after discovering objects. We conduct extensive experiments on both real-world and synthetic datasets, demonstrating superior 3D object segmentation performance over all baselines while achieving state-of-the-art results."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the proposed object discerning and completion modules can reliably bridge the geometric domain gap between synthetic pretraining data and real-world point clouds (including morphological variations and occlusion artifacts) without any scene supervision or additional real-world labels."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"EvObj learns evolving object-centric representations for unsupervised 3D instance segmentation by dynamically refining object candidates and completing partial geometries to bridge the synthetic-to-real domain gap, outperforming baselines on real and synthetic datasets."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"EvObj adapts synthetic object priors to real 3D point clouds unsupervised by dynamically refining candidates and completing partial geometries."}],"snapshot_sha256":"03983c5f4121b3c911fb81d749a13eb638a48c4a5716a043facd41b505e7254a"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We introduce EvObj for unsupervised 3D instance segmentation that bridges the geometric domain gap between synthetic pretraining data and real-world point clouds. Current methods suffer from structural discrepancies when transferring object priors from synthetic datasets (e.g., ShapeNet) to real scans (e.g., ScanNet), particularly due to morphological variations and occlusion artifacts. To address this, EvObj integrates two innovative modules: (1) An object discerning module that dynamically refines object candidates, enabling continuous adaptation of object priors to target domains; and (2) A","authors_text":"Bo Yang, Jiahao Chen, Jinxi Li, Shenxing Wei, Yafei Yang, Zhixuan Sun, Zihui Zhang","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"EvObj adapts synthetic object priors to real 3D point clouds unsupervised by dynamically refining candidates and completing partial geometries.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T08:17:45Z","title":"EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision"},"references":{"count":66,"internal_anchors":2,"resolved_work":66,"sample":[{"cited_arxiv_id":"1702.01105","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Joint 2d-3d-semantic data for indoor scene understanding","work_id":"cd49417b-13e3-4652-87f2-c992e78d093a","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"SLIM: Self-Supervised LiDAR Scene Flow and Motion Seg- mentation.ICCV, 2021","work_id":"cb11361f-cfc5-41dc-9803-c9870310eeb2","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Open-YOLO 3D: Towards Fast and Accurate Open-V ocabulary 3D Instance Segmentation","work_id":"caabaa27-dadc-45c2-b188-13782dee2a3d","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Emerg- ing Properties in Self-Supervised Vision Transformers","work_id":"85c0bcc8-00a4-4f30-a9bb-5aa5bb0bdbc9","year":2021},{"cited_arxiv_id":"1512.03012","doi":"","is_internal_anchor":true,"ref_index":5,"title":"ShapeNet: An Information-Rich 3D Model Repository","work_id":"b2ac5b60-daa9-435b-9369-12271e126edd","year":2015}],"snapshot_sha256":"6bb371542930a5d6671769a92db542e0e4bd153d822c21da0267e1b9450b1028"},"source":{"id":"2605.13152","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:23:50.737728Z","id":"9821195d-6f3e-47d2-9363-239787739245","model_set":{"reader":"grok-4.3"},"one_line_summary":"EvObj learns evolving object-centric representations for unsupervised 3D instance segmentation by dynamically refining object candidates and completing partial geometries to bridge the synthetic-to-real domain gap, outperforming baselines on real and synthetic datasets.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"EvObj adapts synthetic object priors to real 3D point clouds unsupervised by dynamically refining candidates and completing partial geometries.","strongest_claim":"EvObj integrates two innovative modules: (1) An object discerning module that dynamically refines object candidates, enabling continuous adaptation of object priors to target domains; and (2) An object completion module that reconstructs partial geometries after discovering objects. We conduct extensive experiments on both real-world and synthetic datasets, demonstrating superior 3D object segmentation performance over all baselines while achieving state-of-the-art results.","weakest_assumption":"That the proposed object discerning and completion modules can reliably bridge the geometric domain gap between synthetic pretraining data and real-world point clouds (including morphological variations and occlusion artifacts) without any scene supervision or additional real-world labels."}},"verdict_id":"9821195d-6f3e-47d2-9363-239787739245"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:66d581308b6f5b67fe40d064f15a5f3bc94a8b03cd5e72a1b9080c61d227d12f","target":"record","created_at":"2026-05-18T03:08:57Z","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":"e4f4a7ad21a93e1a57c8a45cc04767b2c114d31b84d1ba346804e6a27cfaacb7","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T08:17:45Z","title_canon_sha256":"a6cdfe85a14cd8dc2533866ec7870bdcf28b75a6368665ccbb928104d497dfed"},"schema_version":"1.0","source":{"id":"2605.13152","kind":"arxiv","version":1}},"canonical_sha256":"7d9a96cfc52ddccf608ca77b7e598c71f99ffde900c03a8ca9e6c212e2970352","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d9a96cfc52ddccf608ca77b7e598c71f99ffde900c03a8ca9e6c212e2970352","first_computed_at":"2026-05-18T03:08:57.100635Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:08:57.100635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vXFfImH3hVlxAcE/WiUKBjcUwl/K7JastNZ3nKmeX8YyABdPRTdm7YjMM/8Bc3ONC3YuRJj1bVXZBIaQkNgxCA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:08:57.101276Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13152","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66d581308b6f5b67fe40d064f15a5f3bc94a8b03cd5e72a1b9080c61d227d12f","sha256:266558075149cdf505c0a050719d0957fc2c3c474e555e94be3e1344c2cb022c"],"state_sha256":"c3dc5c584d1910f813a61ef4faa93cba2cd1fe5d9c598e8fc3941b8cf7ddfcad"}