{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OYH2SK6P2H5XLFLNSWVFT6L6IB","short_pith_number":"pith:OYH2SK6P","schema_version":"1.0","canonical_sha256":"760fa92bcfd1fb75956d95aa59f97e4076959b944de836b4ad529be6c31fb8d5","source":{"kind":"arxiv","id":"2608.08053","version":1},"attestation_state":"computed","paper":{"title":"PhysX-CoT: Structured Physical Reasoning from a Single Image to Simulation-Ready 3D Assets","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chen Qian, Fangli Mou, Jiahao Li, Jie Huang, Junhao Fan, Kaixin Zhang, Xiaohe Li, Yuqiang Fang, Zide Fan","submitted_at":"2026-08-08T10:39:09Z","abstract_excerpt":"Simulation-ready 3D assets are central to robotics and embodied AI. Generating them from a single image is usually framed as a vision-language model that emits a serialized asset for a decoder to turn into geometry and physical fields, leaving the image-to-3D reasoning implicit. We argue the limiting factor is this output-centric view: part placement and local shape are entangled in one global-coordinate token stream, and the intermediate physical states are never exposed for supervision, conditioning, or verification. PhysX-CoT instead casts single-image asset generation as an explicit struct"},"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":"2608.08053","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-08T10:39:09Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b5229b5ee8263024e17104f8aed4ae07a08b72e4403d28824b0c34d4d687fc5a","abstract_canon_sha256":"038adef90749b0d93421e3ac778aebabbcdf3d5d69d94930ea20d961c3c4a631"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:21:33.426775Z","signature_b64":"xESJ1hZix0jJcu4RJmpNRD+YAhzOuhB/x/NYLi/MkqaRV1Gd4XoOTtd50XOtYLeezWg24pyVH1+bU9jTO4xKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"760fa92bcfd1fb75956d95aa59f97e4076959b944de836b4ad529be6c31fb8d5","last_reissued_at":"2026-08-11T01:21:33.424383Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:21:33.424383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PhysX-CoT: Structured Physical Reasoning from a Single Image to Simulation-Ready 3D Assets","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chen Qian, Fangli Mou, Jiahao Li, Jie Huang, Junhao Fan, Kaixin Zhang, Xiaohe Li, Yuqiang Fang, Zide Fan","submitted_at":"2026-08-08T10:39:09Z","abstract_excerpt":"Simulation-ready 3D assets are central to robotics and embodied AI. Generating them from a single image is usually framed as a vision-language model that emits a serialized asset for a decoder to turn into geometry and physical fields, leaving the image-to-3D reasoning implicit. We argue the limiting factor is this output-centric view: part placement and local shape are entangled in one global-coordinate token stream, and the intermediate physical states are never exposed for supervision, conditioning, or verification. PhysX-CoT instead casts single-image asset generation as an explicit struct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08053","kind":"arxiv","version":1},"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/2608.08053/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":"2608.08053","created_at":"2026-08-11T01:21:33.425170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08053v1","created_at":"2026-08-11T01:21:33.425170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08053","created_at":"2026-08-11T01:21:33.425170+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYH2SK6P2H5X","created_at":"2026-08-11T01:21:33.425170+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYH2SK6P2H5XLFLN","created_at":"2026-08-11T01:21:33.425170+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYH2SK6P","created_at":"2026-08-11T01:21:33.425170+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYH2SK6P2H5XLFLNSWVFT6L6IB","json":"https://pith.science/pith/OYH2SK6P2H5XLFLNSWVFT6L6IB.json","graph_json":"https://pith.science/api/pith-number/OYH2SK6P2H5XLFLNSWVFT6L6IB/graph.json","events_json":"https://pith.science/api/pith-number/OYH2SK6P2H5XLFLNSWVFT6L6IB/events.json","paper":"https://pith.science/paper/OYH2SK6P"},"agent_actions":{"view_html":"https://pith.science/pith/OYH2SK6P2H5XLFLNSWVFT6L6IB","download_json":"https://pith.science/pith/OYH2SK6P2H5XLFLNSWVFT6L6IB.json","view_paper":"https://pith.science/paper/OYH2SK6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08053&json=true","fetch_graph":"https://pith.science/api/pith-number/OYH2SK6P2H5XLFLNSWVFT6L6IB/graph.json","fetch_events":"https://pith.science/api/pith-number/OYH2SK6P2H5XLFLNSWVFT6L6IB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYH2SK6P2H5XLFLNSWVFT6L6IB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYH2SK6P2H5XLFLNSWVFT6L6IB/action/storage_attestation","attest_author":"https://pith.science/pith/OYH2SK6P2H5XLFLNSWVFT6L6IB/action/author_attestation","sign_citation":"https://pith.science/pith/OYH2SK6P2H5XLFLNSWVFT6L6IB/action/citation_signature","submit_replication":"https://pith.science/pith/OYH2SK6P2H5XLFLNSWVFT6L6IB/action/replication_record"}},"created_at":"2026-08-11T01:21:33.425170+00:00","updated_at":"2026-08-11T01:21:33.425170+00:00"}