{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RHLJK3WPJEUG3VF2H3EME7FFB3","short_pith_number":"pith:RHLJK3WP","schema_version":"1.0","canonical_sha256":"89d6956ecf49286dd4ba3ec8c27ca50eed05a3995d15375393c8e13e77c37dab","source":{"kind":"arxiv","id":"2606.28757","version":1},"attestation_state":"computed","paper":{"title":"A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Boris Ivanovic, Junyuan Hong, Lulin Liu, Marco Pavone, Nuo Chen, Wenyan Cong, Yang Zhou, Yan Wang, Yunhao Yang, Zhangyang Wang, Zhengzhong Tu, Zhiwen Fan, Zihao Li, Zihao Zhu, Ziyao Zeng","submitted_at":"2026-06-27T06:13:35Z","abstract_excerpt":"Generative world models hold immense promise as scalable simulators for autonomous systems, particularly for synthesizing rare but safety-critical multi-agent interactions, such as vehicle collisions. However, current evaluation paradigms index heavily on visual fidelity and semantic alignment, leaving a critical blind spot: they cannot reliably quantify whether generated dynamics actually obey the fundamental physical laws required for reliable simulation. Assessing this physical plausibility is inherently difficult due to a lack of physical metrics and the challenge of extracting metric-scal"},"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":"2606.28757","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-27T06:13:35Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"5cb4cbaeac3ac928034e93ae7d1656d1bf6e9493e9b2a5fc526e0106462c0849","abstract_canon_sha256":"11fcdd58af590eae92ad3336b362cc548021cacd7e056c2981b88ec8d93c6dd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:50.652511Z","signature_b64":"w2fcOjpsQjWfj/DXJNllJTluPkXgbSdNiUglgxVgRVPcF3yuhdj4ThHFNqbe06T6fIK93EFYuZnqSPNpSRw2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89d6956ecf49286dd4ba3ec8c27ca50eed05a3995d15375393c8e13e77c37dab","last_reissued_at":"2026-06-30T01:16:50.652058Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:50.652058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Boris Ivanovic, Junyuan Hong, Lulin Liu, Marco Pavone, Nuo Chen, Wenyan Cong, Yang Zhou, Yan Wang, Yunhao Yang, Zhangyang Wang, Zhengzhong Tu, Zhiwen Fan, Zihao Li, Zihao Zhu, Ziyao Zeng","submitted_at":"2026-06-27T06:13:35Z","abstract_excerpt":"Generative world models hold immense promise as scalable simulators for autonomous systems, particularly for synthesizing rare but safety-critical multi-agent interactions, such as vehicle collisions. However, current evaluation paradigms index heavily on visual fidelity and semantic alignment, leaving a critical blind spot: they cannot reliably quantify whether generated dynamics actually obey the fundamental physical laws required for reliable simulation. Assessing this physical plausibility is inherently difficult due to a lack of physical metrics and the challenge of extracting metric-scal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28757","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/2606.28757/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":"2606.28757","created_at":"2026-06-30T01:16:50.652119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28757v1","created_at":"2026-06-30T01:16:50.652119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28757","created_at":"2026-06-30T01:16:50.652119+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHLJK3WPJEUG","created_at":"2026-06-30T01:16:50.652119+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHLJK3WPJEUG3VF2","created_at":"2026-06-30T01:16:50.652119+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHLJK3WP","created_at":"2026-06-30T01:16:50.652119+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/RHLJK3WPJEUG3VF2H3EME7FFB3","json":"https://pith.science/pith/RHLJK3WPJEUG3VF2H3EME7FFB3.json","graph_json":"https://pith.science/api/pith-number/RHLJK3WPJEUG3VF2H3EME7FFB3/graph.json","events_json":"https://pith.science/api/pith-number/RHLJK3WPJEUG3VF2H3EME7FFB3/events.json","paper":"https://pith.science/paper/RHLJK3WP"},"agent_actions":{"view_html":"https://pith.science/pith/RHLJK3WPJEUG3VF2H3EME7FFB3","download_json":"https://pith.science/pith/RHLJK3WPJEUG3VF2H3EME7FFB3.json","view_paper":"https://pith.science/paper/RHLJK3WP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28757&json=true","fetch_graph":"https://pith.science/api/pith-number/RHLJK3WPJEUG3VF2H3EME7FFB3/graph.json","fetch_events":"https://pith.science/api/pith-number/RHLJK3WPJEUG3VF2H3EME7FFB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHLJK3WPJEUG3VF2H3EME7FFB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHLJK3WPJEUG3VF2H3EME7FFB3/action/storage_attestation","attest_author":"https://pith.science/pith/RHLJK3WPJEUG3VF2H3EME7FFB3/action/author_attestation","sign_citation":"https://pith.science/pith/RHLJK3WPJEUG3VF2H3EME7FFB3/action/citation_signature","submit_replication":"https://pith.science/pith/RHLJK3WPJEUG3VF2H3EME7FFB3/action/replication_record"}},"created_at":"2026-06-30T01:16:50.652119+00:00","updated_at":"2026-06-30T01:16:50.652119+00:00"}