{"as_of":"2026-08-09T18:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:aecefa512478977cc8ac3d80e937ab83f52888b3abc19db181bba0ebcec7ce8b","coverage":[{"denominator":45,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":45,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-11T05:41:50.671046Z","state":"measured"},{"denominator":45,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":45,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.05568/citation-record","integrity":"/paper/2607.05568/integrity","json":"/paper/2607.05568/citation-record.json","paper":"/paper/2607.05568"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": GPT-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:19f88b532bc09fb663f4ebe6477907c6dfda7101bcd45844ec3ed7b5f3cfa412","observation_id":"4560de9e-fcb0-40a8-aba9-820921d98e8e","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": Iterative superquadric recomposition of 3D objects","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:2020620dc054d728e5d1e5c1c34a503b78c84200696990f4fbd4fd968bfa68ca","observation_id":"41b24766-a9a7-4130-8180-fb06a59e7017","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":"https://artificialanalysis.ai/image/leaderboard/editing, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:e9b810d477641bcf22016af127df4f4ef30c80b1810595b140e1e31c520a7927","observation_id":"56c88fe8-c2ca-416b-b426-894667ea6ea5","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":null,"venue":null,"work_id":null,"year":1981},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:d4fa716ebb0c5990809e60303f16be37c4f1faa2bb6fe264c8148d9215371d8c","observation_id":"31eab53a-d595-46c5-8ef1-0a42e6a196fb","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": Efficiently approximating the minimum-volume bounding box of a point set in three dimensions","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:7be489b8805e0a137a8f8108441297aa659341ef97bbbe7e47553718526e0039","observation_id":"59f50118-2ae3-432b-8a61-0a8d2c0fc52d","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1512.03012","last_updated":"2015-12-09T19:42:48Z","snapshot_observed_at":"2026-08-07T11:28:03.211074Z","submitted_at":"2015-12-09T19:42:48Z","title":"ShapeNet: An Information-Rich 3D Model Repository","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1512.03012","snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":"X., Funkhouser T., Guibas L., Hanrahan P., Huang Q., Li Z., Savarese S., Savva M., Song S., Su H., Xiao J., Yi L., Yu F","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"cited_paper":"/paper/1512.03012","citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:32100b7585c8ff1a78a0c518f6476ae95282a6bf594176aaecff9696d10aee8b","observation_id":"32cf53f2-1161-4606-bd24-6ba142f3d795","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": SuperDec : 3D scene decomposition with superquadric primitives","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:0f3b46b766e286a408999c8473645c7bb2a722af46aaf5641c89cd292b58bd11","observation_id":"811df8a1-9b93-4e4b-a96d-200d6f1f3128","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": Image generators are generalist vision learners","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:fbf7f38b42590bd8c2023fa650019b3d655203c7ff3b91dd6524a41b66153b97","observation_id":"d317a658-8102-4a0e-8237-93a5f0295b1c","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":"M., et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:57187a47681f8dac010b05f1c3f48ba330aa741fc5fdb32896b4872d5cb2380c","observation_id":"60218f13-bc2f-408e-a937-c412973f85f7","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": Residual primitive fitting of 3D shapes with SuperFrusta","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:78ce393f71b25f9a14f857dddaf75fe05e813c8dcb2ba3b442645fe7f5c8a853","observation_id":"8a8d8ba8-e749-4b8f-84d2-def8325fa79e","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":"https://blog.google/innovation-and-ai/technology/ai/nano-banana-2/, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:63f571a4d77ebebaace8fdda87851d93961c4409de23ab36585f70d62288b8a3","observation_id":"0cddc0e4-085e-47d8-825e-db263bc1279d","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": 3D part segmentation via geometric aggregation of 2D visual features","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:0933f2d1f55a2e111ccdefea65da07ef5e228f479a3b882273058e4dd7572bd1","observation_id":"ba07174e-1b3e-4324-84f1-dd32934b95c2","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": Self-supervised learning of hybrid part-aware 3D representations of 2D Gaussians and superquadrics","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:e3ba4d5995afc87dce86dd779a925a4e129941788c440d7bcd4f48ec5ea0bc69","observation_id":"6ea2f135-e994-4c3b-960b-d2f8a4c55d64","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": Segmentation and Recovery of Superquadrics","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:0d43090dbcf1841fe5d84b310b44ecc2cdd54ee2d89d07393b7560c600be9664","observation_id":"4e73b423-367e-4073-921e-c807c0ad2217","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": Learning fine-to-coarse cuboid shape abstraction","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:4325ba75e68cdf4240a426921c7ec06e6faaa3f3274f9515651c49c7a18e5a77","observation_id":"33a5d2f8-0b38-4798-91b8-fb5e87970403","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":"C., Lo W.-Y., Doll \\'a r P., Girshick R","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:af19e3fcf4cd8cd5e2691771f9def3168110295c86c2ddae0523db8e733a5749","observation_id":"308d835d-b352-473e-9b5e-ed8e2112cd7b","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.13677","last_updated":"2024-07-18T16:52:45Z","snapshot_observed_at":"2026-07-06T18:48:37.723242Z","submitted_at":"2024-07-18T16:52:45Z","title":"PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.13677","snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": PASTA : Controllable part-aware shape generation with autoregressive transformers","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"cited_paper":"/paper/2407.13677","citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:a9dc43131d676644faa0463dc5b757881c6431cfd811f515751d38bcd86dd058","observation_id":"1f8466ae-b234-4755-ac72-8e170f1643eb","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": P3-SAM : Native 3D part segmentation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:832e0b2030f1abf0ead6ef136c9a550b647d1bad60e9651a515ae623bf487bb9","observation_id":"8cc779cf-c667-44c8-a4da-f1215a375035","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": PartField : Learning part field representations for generalizable 3D part segmentation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:64ce78716789c35b12876737ebfb2c1e1179214e5999449d8fa3ce0ec3054890","observation_id":"936d3cb9-030b-45bf-8cec-0ef2ebec473c","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2603.16869","last_updated":"2026-05-10T17:28:14Z","snapshot_observed_at":"2026-07-06T22:49:28.866886Z","submitted_at":"2026-03-17T17:59:51Z","title":"SegviGen: Repurposing 3D Generative Model for Part Segmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2603.16869","snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": SegviGen : Repurposing 3D generative model for part segmentation","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"cited_paper":"/paper/2603.16869","citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:4c5e0379633ddefc71c30576d5661a1657bc9973dc4ad6ee278865f9a397b87a","observation_id":"eca2cd31-a196-4aea-bf3c-26460e610deb","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": Superquadrics for segmenting and modeling range data","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:589223cc06e245a1169bbcff852980e57016a3fd4c35de0aa5734cd044b1f4f1","observation_id":"734be800-e045-4219-a6c9-2b9f15e797b9","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":"C., Nocedal J","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:1db7628e59b36b6df44f17d5eeb235112b0bfa0c1f285b57ccfb7cc5d1f27942","observation_id":"5baadd93-9a46-46b3-b272-ca433b4794c3","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:c059cb1d21aeec8e6954dbbb0e638ab60bd38b06615745dc23b44100ad60f12f","observation_id":"a5460f7e-697f-4212-beea-61934a225f2d","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:cc90bd48bce44c270629e6e5cd485cb1856421c7c80996879e844a6164ca4922","observation_id":"f2ec2d59-bd0c-438a-ab3f-f055a17dc05e","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": PartSLIP : Low-shot part segmentation for 3D point clouds via pretrained image-language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:1a181c831cd87b64c747efd2e93a93cdedc43feb0a5ee07edcf52524a1f7176a","observation_id":"471a3d0a-8146-4978-9663-c4cee723d56b","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":"A., Aubry M","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:3a20a732e6ee9a0fb35d9de049a89a8fcfdbd22fe4b85a7676d4816323fdfdf9","observation_id":"a06fae78-2a19-418c-9d19-5de24695c56e","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":"X., Yi L., Tripathi S., Guibas L","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:30b99c07a916e45530447330f7cd18289ebfa64447659eafc1c89e968141db91","observation_id":"81988054-8080-4fbb-8648-50534929ca74","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":null,"venue":null,"work_id":null,"year":1986},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:c7953fbec13842793072ad961b3d90782cf98627a9759e77001f0d238b19bd09","observation_id":"6181f85a-e0be-44cf-8f29-59c7b784e79e","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":"O., Geiger A","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:4857e070c20398862b49a3242c49db5a9f4468057a559af3cd868bbfce6ab05b","observation_id":"657dfb5c-e4d7-42e3-8339-186254b31c26","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": Neural parts: Learning expressive deformable geometry with invertible neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:5490d3993601fe06ea647ff265999d6d6c1a89b4c6901057193cd43c857f78bf","observation_id":"5f916d91-02c5-41b0-9c9d-d3727ba9d558","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.07572","last_updated":"2024-01-15T10:16:44Z","snapshot_observed_at":"2026-08-02T13:51:50.241477Z","submitted_at":"2024-01-15T10:16:44Z","title":"Exploiting GPT-4 Vision for Zero-shot Point Cloud Understanding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.07572","snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": Exploiting the potential of GPT-4V for zero-shot 3D point cloud understanding","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"cited_paper":"/paper/2401.07572","citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:a93b91ea9235a72745a449acf759ee7353eddbe7e254daab4ee077c771fdccec","observation_id":"bb6ea5cd-ab8a-41ea-a691-59a47c9f9d10","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": Recovery of parametric models from range images: The case for superquadrics with global deformations","venue":null,"work_id":null,"year":1990},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:8b92e056457ad836e6b07ef633c6572c879e06473c3f51ec6a3cf26834484692","observation_id":"7ff52667-f688-4bd4-980a-e9410c92f752","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:bafca8c967d0cded395d4532fff2bc9c9291e33b70b44ada74bd82676e88c86b","observation_id":"d0933075-ee7a-44eb-814f-6b263db7dd20","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": Learning adaptive hierarchical cuboid abstractions of 3D shape collections","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:36400696f4c8a8a05f516780b160ca3ec28ab092e22ce9abb48898eb642ac708","observation_id":"c2252cc7-b5e4-4de6-b1ba-9ed547498040","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": Llm-primitives: Large language model for 3D reconstruction with primitives","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:98a0c9cc2a31b1f465772cf3637215ec48f46ee081f09b9685803d670035b42f","observation_id":"b02894d5-9ad8-4a31-aefa-50250754b5d6","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":"J., Efros A","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:f8c7fa1dc91425b8fb5763a1d6613c6e0a682fa9f6d5e947d2e603d1b3698400","observation_id":"bb9fb91e-eefd-4b42-9e36-1041ee27f6ed","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": Light-SQ : Structure-aware shape abstraction with superquadrics for generated meshes","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:1449af432fef40fbbbb00165fef11cb96bd744bde8530f5bcabc2b3d9c84cb13","observation_id":"59f0edff-77eb-483b-a6e1-53b3d8d1f47c","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.13675","last_updated":"2024-07-25T12:32:21Z","snapshot_observed_at":"2026-08-05T15:37:06.440816Z","submitted_at":"2024-07-18T16:50:59Z","title":"MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis","version":3},"cited_work":{"arxiv_id":"2407.13675","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.13675","snapshot_observed_at":"2026-07-11T05:47:53.485690Z","title":"MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis","venue":"cs.CV","work_id":"3d266f4e-ff2b-4658-ba08-ec50ee5ae1c0","year":2024},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"cited_paper":"/paper/2407.13675","citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:41077378eb662c23f4058dc275ec74b73dec1c44927b4ab94e6677d39316eaad","observation_id":"7b878315-6b61-4328-9134-9d265efb19d4","resolution":{"observed_at":"2026-07-11T05:47:53.489936Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": Unsupervised learning of fine structure generation for 3D point clouds by 2D projection matching","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:9511019eac58d91f532ff95e4e36a0da0e4132dc220964516e0c4c6fc06cbf7a","observation_id":"a6c393c3-ad64-4698-a98f-0b90f4966bdb","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.07184","last_updated":"2024-11-16T07:04:42Z","snapshot_observed_at":"2026-08-08T06:47:38.579688Z","submitted_at":"2024-11-11T17:59:10Z","title":"SAMPart3D: Segment Any Part in 3D Objects","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.07184","snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":"Y., Cao Y.-P., Liu X","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"cited_paper":"/paper/2411.07184","citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:8e2600ebe73813fb204bd69f03c7eb7fb28f77d8ff48c67405e0c262c6687bc0","observation_id":"65a6ed6f-8c0b-4ae1-bf60-699e6034b292","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": PrimitiveAnything : Human-crafted 3D primitive assembly generation with auto-regressive transformer","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:2a646884c5fe7d16878511bb6a43806d32956b7a5696779168a79886204e173f","observation_id":"b882f9e9-12e4-4f25-be2f-5254ba94ea90","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":"A., Han J., Thomas R., Zhang H., Du Y., Chen H., Engelmann F., You S., Guibas L","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:671fef959d0afa79d00f85f9078345087d72794f29ef8b2268ba80037eec63b0","observation_id":"90cc0ec9-c5c4-4346-88ec-a7ae85cc72e0","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": SweepNet : Unsupervised shape abstraction via neural sweeping","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:af85140c5a5386cac183ac7fa95604300fdff8f91ddb12af1e20ae46fa508632","observation_id":"284688fb-f89f-437c-a894-0959710f8603","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": Point- SAM : Promptable 3D segmentation model for point clouds","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:cc4f925b45ed778e758ee318b71341e4f7d83d021cc518b6830c61b98f4158ac","observation_id":"a66cf0a3-b859-41e0-b010-f2d777cd0c22","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T05:41:50.671046Z","title":": 3D-PRNN : Generating shape primitives with recurrent neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-07-11T05:41:50.671046Z"},"links":{"citing_paper":"/paper/2607.05568"},"observation_digest":"sha256:345f2fce3829051f6ad1e697c71dba32f92614433e53c62dcf7dbcda5ee99c17","observation_id":"0639ffaa-ca5d-4a72-a630-27d4940db673","resolution":{"observed_at":"2026-07-11T05:41:50.671046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.05568","last_updated":"2026-07-06T19:10:43Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T06:47:59.048126Z","submitted_at":"2026-07-06T19:10:43Z","title":"Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction"},"reference_resolution":{"displayed":45,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":44,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":45},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2607.05568."}