{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NYVZZ6EEITI4BOUYMFOV4ZTAKF","short_pith_number":"pith:NYVZZ6EE","schema_version":"1.0","canonical_sha256":"6e2b9cf88444d1c0ba98615d5e6660517f61aa4a04358830d23f32cc55b5578e","source":{"kind":"arxiv","id":"2502.12231","version":2},"attestation_state":"computed","paper":{"title":"PUGS: Zero-shot Physical Understanding with Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Zhao, Jianzhu Ma, Jv Zheng, Meng Yang, Nan Wang, Ran Yu, Wenbo Ding, Xiaowei Song, Yinghao Shuai, Yuantao Chen, Zhicheng Wang, Zijian Jiang","submitted_at":"2025-02-17T18:59:42Z","abstract_excerpt":"Current robotic systems can understand the categories and poses of objects well. But understanding physical properties like mass, friction, and hardness, in the wild, remains challenging. We propose a new method that reconstructs 3D objects using the Gaussian splatting representation and predicts various physical properties in a zero-shot manner. We propose two techniques during the reconstruction phase: a geometry-aware regularization loss function to improve the shape quality and a region-aware feature contrastive loss function to promote region affinity. Two other new techniques are designe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.12231","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-17T18:59:42Z","cross_cats_sorted":[],"title_canon_sha256":"cd3c8e7d26d1a51ae3545827c6a5a15a2f66d11ccf778304718ce888980f0ef0","abstract_canon_sha256":"3d21fdab43ab7ee3be8de4b45d329f93da455447c4797f966157aa745631e88e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:36.306791Z","signature_b64":"91YIYNqQMvBeS/O8KmyUllj/XsCT6PcVPDuY+767O2YIYkWHtgd1e10An/vfxrT8sGSm9O+ShnZlXRik5bXHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e2b9cf88444d1c0ba98615d5e6660517f61aa4a04358830d23f32cc55b5578e","last_reissued_at":"2026-07-05T10:36:36.305779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:36.305779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PUGS: Zero-shot Physical Understanding with Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Zhao, Jianzhu Ma, Jv Zheng, Meng Yang, Nan Wang, Ran Yu, Wenbo Ding, Xiaowei Song, Yinghao Shuai, Yuantao Chen, Zhicheng Wang, Zijian Jiang","submitted_at":"2025-02-17T18:59:42Z","abstract_excerpt":"Current robotic systems can understand the categories and poses of objects well. But understanding physical properties like mass, friction, and hardness, in the wild, remains challenging. We propose a new method that reconstructs 3D objects using the Gaussian splatting representation and predicts various physical properties in a zero-shot manner. We propose two techniques during the reconstruction phase: a geometry-aware regularization loss function to improve the shape quality and a region-aware feature contrastive loss function to promote region affinity. Two other new techniques are designe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12231","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.12231/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.12231","created_at":"2026-07-05T10:36:36.305904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12231v2","created_at":"2026-07-05T10:36:36.305904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12231","created_at":"2026-07-05T10:36:36.305904+00:00"},{"alias_kind":"pith_short_12","alias_value":"NYVZZ6EEITI4","created_at":"2026-07-05T10:36:36.305904+00:00"},{"alias_kind":"pith_short_16","alias_value":"NYVZZ6EEITI4BOUY","created_at":"2026-07-05T10:36:36.305904+00:00"},{"alias_kind":"pith_short_8","alias_value":"NYVZZ6EE","created_at":"2026-07-05T10:36:36.305904+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08655","citing_title":"PhysGraph: A Physics-aware 3D Scene Graph for Perception and Reasoning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20303","citing_title":"Physically Guided Visual Mass Estimation from a Single RGB Image","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00177","citing_title":"FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting","ref_index":130,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NYVZZ6EEITI4BOUYMFOV4ZTAKF","json":"https://pith.science/pith/NYVZZ6EEITI4BOUYMFOV4ZTAKF.json","graph_json":"https://pith.science/api/pith-number/NYVZZ6EEITI4BOUYMFOV4ZTAKF/graph.json","events_json":"https://pith.science/api/pith-number/NYVZZ6EEITI4BOUYMFOV4ZTAKF/events.json","paper":"https://pith.science/paper/NYVZZ6EE"},"agent_actions":{"view_html":"https://pith.science/pith/NYVZZ6EEITI4BOUYMFOV4ZTAKF","download_json":"https://pith.science/pith/NYVZZ6EEITI4BOUYMFOV4ZTAKF.json","view_paper":"https://pith.science/paper/NYVZZ6EE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12231&json=true","fetch_graph":"https://pith.science/api/pith-number/NYVZZ6EEITI4BOUYMFOV4ZTAKF/graph.json","fetch_events":"https://pith.science/api/pith-number/NYVZZ6EEITI4BOUYMFOV4ZTAKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NYVZZ6EEITI4BOUYMFOV4ZTAKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NYVZZ6EEITI4BOUYMFOV4ZTAKF/action/storage_attestation","attest_author":"https://pith.science/pith/NYVZZ6EEITI4BOUYMFOV4ZTAKF/action/author_attestation","sign_citation":"https://pith.science/pith/NYVZZ6EEITI4BOUYMFOV4ZTAKF/action/citation_signature","submit_replication":"https://pith.science/pith/NYVZZ6EEITI4BOUYMFOV4ZTAKF/action/replication_record"}},"created_at":"2026-07-05T10:36:36.305904+00:00","updated_at":"2026-07-05T10:36:36.305904+00:00"}