{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CF4XOVQRWRYZF4TAAQUDP23UEZ","short_pith_number":"pith:CF4XOVQR","schema_version":"1.0","canonical_sha256":"1179775611b47192f260042837eb742673a030a3c9c561deaca305fa63956677","source":{"kind":"arxiv","id":"2508.17437","version":2},"attestation_state":"computed","paper":{"title":"Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Wang, Chuhao Chen, Dinesh Jayaraman, Eric Eaton, Lingjie Liu, Long Le, Ryan Lucas","submitted_at":"2025-08-20T19:24:04Z","abstract_excerpt":"Inferring the physical properties of 3D scenes from visual information is a critical yet challenging task for creating interactive and realistic virtual worlds. While humans intuitively grasp material characteristics such as elasticity or stiffness, existing methods often rely on slow, per-scene optimization, limiting their generalizability and application. To address this problem, we introduce PIXIE, a novel method that trains a generalizable neural network to predict physical properties across multiple scenes from 3D visual features purely using supervised losses. Once trained, our feed-forw"},"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":"2508.17437","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-20T19:24:04Z","cross_cats_sorted":[],"title_canon_sha256":"a7734b52e7cc650da1fa0dc8bd414e4631fee12ed555c3dd0e660419a6e12376","abstract_canon_sha256":"35a19c1e2716484d6ec0eb0c72e2f50cd5b59a748e2a4d2467cf825cf173b464"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:21.068928Z","signature_b64":"r7b2vVVNuHkmZ1K/PhOFFE78DFv31Yj/DOppdAiy2LLAjD3Ya84M1eYQLRxibq0XbBkIYXVuu6RFYTxExym7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1179775611b47192f260042837eb742673a030a3c9c561deaca305fa63956677","last_reissued_at":"2026-07-05T11:59:21.068466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:21.068466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Wang, Chuhao Chen, Dinesh Jayaraman, Eric Eaton, Lingjie Liu, Long Le, Ryan Lucas","submitted_at":"2025-08-20T19:24:04Z","abstract_excerpt":"Inferring the physical properties of 3D scenes from visual information is a critical yet challenging task for creating interactive and realistic virtual worlds. While humans intuitively grasp material characteristics such as elasticity or stiffness, existing methods often rely on slow, per-scene optimization, limiting their generalizability and application. To address this problem, we introduce PIXIE, a novel method that trains a generalizable neural network to predict physical properties across multiple scenes from 3D visual features purely using supervised losses. Once trained, our feed-forw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17437","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/2508.17437/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":"2508.17437","created_at":"2026-07-05T11:59:21.068524+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.17437v2","created_at":"2026-07-05T11:59:21.068524+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17437","created_at":"2026-07-05T11:59:21.068524+00:00"},{"alias_kind":"pith_short_12","alias_value":"CF4XOVQRWRYZ","created_at":"2026-07-05T11:59:21.068524+00:00"},{"alias_kind":"pith_short_16","alias_value":"CF4XOVQRWRYZF4TA","created_at":"2026-07-05T11:59:21.068524+00:00"},{"alias_kind":"pith_short_8","alias_value":"CF4XOVQR","created_at":"2026-07-05T11:59:21.068524+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05399","citing_title":"UniPixie: Unified and Probabilistic 3D Physics Learning via Flow Matching","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30347","citing_title":"NeuROK: Generative 4D Neural Object Kinematics","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2412.12870","citing_title":"Physically Interpretable World Models via Weakly Supervised Representation Learning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21572","citing_title":"PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04876","citing_title":"PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19136","citing_title":"Automatically Improving Simulation Physics for Articulated Objects","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26509","citing_title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26509","citing_title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09415","citing_title":"PhysInOne: Visual Physics Learning and Reasoning in One Suite","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26509","citing_title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14025","citing_title":"Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective","ref_index":197,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CF4XOVQRWRYZF4TAAQUDP23UEZ","json":"https://pith.science/pith/CF4XOVQRWRYZF4TAAQUDP23UEZ.json","graph_json":"https://pith.science/api/pith-number/CF4XOVQRWRYZF4TAAQUDP23UEZ/graph.json","events_json":"https://pith.science/api/pith-number/CF4XOVQRWRYZF4TAAQUDP23UEZ/events.json","paper":"https://pith.science/paper/CF4XOVQR"},"agent_actions":{"view_html":"https://pith.science/pith/CF4XOVQRWRYZF4TAAQUDP23UEZ","download_json":"https://pith.science/pith/CF4XOVQRWRYZF4TAAQUDP23UEZ.json","view_paper":"https://pith.science/paper/CF4XOVQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.17437&json=true","fetch_graph":"https://pith.science/api/pith-number/CF4XOVQRWRYZF4TAAQUDP23UEZ/graph.json","fetch_events":"https://pith.science/api/pith-number/CF4XOVQRWRYZF4TAAQUDP23UEZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CF4XOVQRWRYZF4TAAQUDP23UEZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CF4XOVQRWRYZF4TAAQUDP23UEZ/action/storage_attestation","attest_author":"https://pith.science/pith/CF4XOVQRWRYZF4TAAQUDP23UEZ/action/author_attestation","sign_citation":"https://pith.science/pith/CF4XOVQRWRYZF4TAAQUDP23UEZ/action/citation_signature","submit_replication":"https://pith.science/pith/CF4XOVQRWRYZF4TAAQUDP23UEZ/action/replication_record"}},"created_at":"2026-07-05T11:59:21.068524+00:00","updated_at":"2026-07-05T11:59:21.068524+00:00"}