{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5RT7TCY43QL2PVY3MDYAGL55UM","short_pith_number":"pith:5RT7TCY4","schema_version":"1.0","canonical_sha256":"ec67f98b1cdc17a7d71b60f0032fbda31a797c15784d0ec8b09a65e57d1c1ac4","source":{"kind":"arxiv","id":"2608.05948","version":1},"attestation_state":"computed","paper":{"title":"GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.AI","authors_text":"Chaoyang Lyu, Chunhua Shen, Hanqing Wang, Hui Wang, Jiangmiao Pang, Ningyu Yan, Shihan Tian, Shuai Wang, Weinan Zhang, Xing Gao, Xing Shen, Xuekun Jiang, Yang Xiang, Yaxin Feng, Yunsong Zhou","submitted_at":"2026-08-06T12:19:38Z","abstract_excerpt":"Physics engines facilitate large-scale training and evaluation for embodied intelligence, while generative video world models are emerging as implicit simulators of future states and interactions. However, existing evaluations of physical fidelity are often conducted in isolation and rely heavily on perceptual similarity or human judgments, providing limited insight into which physical principles or parameters are violated. We introduce GAUGE, a real-world-grounded diagnostic benchmark for jointly evaluating how numerical simulators and generative video world models reproduce or deviate from r"},"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":"2608.05948","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T12:19:38Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"a990387f1f23856ea35c6df75ad9371338e023f522917911ddb2d9a91d73d869","abstract_canon_sha256":"96afb2c7713703d8d504598e3c89d191eaa49932236c6484dc7c6b072a7adb51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:54:01.261824Z","signature_b64":"BsxTz4EplZS1unahO+6MbPITDMtycjdNM/8Yp3pPxXmg1BYDNL3GTfeRDe78XPxz6L6mhjgz+HF3lJxiBA1WAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec67f98b1cdc17a7d71b60f0032fbda31a797c15784d0ec8b09a65e57d1c1ac4","last_reissued_at":"2026-08-07T00:54:01.260116Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:54:01.260116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.AI","authors_text":"Chaoyang Lyu, Chunhua Shen, Hanqing Wang, Hui Wang, Jiangmiao Pang, Ningyu Yan, Shihan Tian, Shuai Wang, Weinan Zhang, Xing Gao, Xing Shen, Xuekun Jiang, Yang Xiang, Yaxin Feng, Yunsong Zhou","submitted_at":"2026-08-06T12:19:38Z","abstract_excerpt":"Physics engines facilitate large-scale training and evaluation for embodied intelligence, while generative video world models are emerging as implicit simulators of future states and interactions. However, existing evaluations of physical fidelity are often conducted in isolation and rely heavily on perceptual similarity or human judgments, providing limited insight into which physical principles or parameters are violated. We introduce GAUGE, a real-world-grounded diagnostic benchmark for jointly evaluating how numerical simulators and generative video world models reproduce or deviate from r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05948","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/2608.05948/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":"2608.05948","created_at":"2026-08-07T00:54:01.261784+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05948v1","created_at":"2026-08-07T00:54:01.261784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05948","created_at":"2026-08-07T00:54:01.261784+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RT7TCY43QL2","created_at":"2026-08-07T00:54:01.261784+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RT7TCY43QL2PVY3","created_at":"2026-08-07T00:54:01.261784+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RT7TCY4","created_at":"2026-08-07T00:54:01.261784+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/5RT7TCY43QL2PVY3MDYAGL55UM","json":"https://pith.science/pith/5RT7TCY43QL2PVY3MDYAGL55UM.json","graph_json":"https://pith.science/api/pith-number/5RT7TCY43QL2PVY3MDYAGL55UM/graph.json","events_json":"https://pith.science/api/pith-number/5RT7TCY43QL2PVY3MDYAGL55UM/events.json","paper":"https://pith.science/paper/5RT7TCY4"},"agent_actions":{"view_html":"https://pith.science/pith/5RT7TCY43QL2PVY3MDYAGL55UM","download_json":"https://pith.science/pith/5RT7TCY43QL2PVY3MDYAGL55UM.json","view_paper":"https://pith.science/paper/5RT7TCY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05948&json=true","fetch_graph":"https://pith.science/api/pith-number/5RT7TCY43QL2PVY3MDYAGL55UM/graph.json","fetch_events":"https://pith.science/api/pith-number/5RT7TCY43QL2PVY3MDYAGL55UM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RT7TCY43QL2PVY3MDYAGL55UM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RT7TCY43QL2PVY3MDYAGL55UM/action/storage_attestation","attest_author":"https://pith.science/pith/5RT7TCY43QL2PVY3MDYAGL55UM/action/author_attestation","sign_citation":"https://pith.science/pith/5RT7TCY43QL2PVY3MDYAGL55UM/action/citation_signature","submit_replication":"https://pith.science/pith/5RT7TCY43QL2PVY3MDYAGL55UM/action/replication_record"}},"created_at":"2026-08-07T00:54:01.261784+00:00","updated_at":"2026-08-07T00:54:01.261784+00:00"}