{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:R7HB7PHXHTQAHHBHA77CRTULZ4","short_pith_number":"pith:R7HB7PHX","schema_version":"1.0","canonical_sha256":"8fce1fbcf73ce0039c2707fe28ce8bcf21c0d8c9aadc3013033d1f70f487d1be","source":{"kind":"arxiv","id":"2510.18135","version":2},"attestation_state":"computed","paper":{"title":"World-in-World: World Models in a Closed-Loop World","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Arda Uzunoglu, Cheng Peng, Daniel Khashabi, Jiahan Zhang, Jiahao Wang, Jieneng Chen, Muqing Jiang, Nanru Dai, Paul Pu Liang, Rama Chellappa, Shunchi Zhang, Taiming Lu, Tianmin Shu, Vishal M. Patel, Yana Wei, Yilun Du","submitted_at":"2025-10-20T22:09:15Z","abstract_excerpt":"Generative world models (WMs) can now simulate worlds with striking visual realism, which naturally raises the question of whether they can endow embodied agents with predictive perception for decision making. Progress on this question has been limited by fragmented evaluation: most existing benchmarks adopt open-loop protocols that emphasize visual quality in isolation, leaving the core issue of embodied utility unresolved, i.e., do WMs actually help agents succeed at embodied tasks? To address this gap, we introduce World-in-World, the first open platform that benchmarks WMs in a closed-loop"},"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":"2510.18135","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-20T22:09:15Z","cross_cats_sorted":[],"title_canon_sha256":"9772727220143825cd67d6e8bf7b50b27b9dc2fb4879a808a49541167ea83aa1","abstract_canon_sha256":"ba54e96cd6966784fe192baf858c994bfd779ce1f9a06ea62232b3985f3cc3e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-18T01:14:05.551615Z","signature_b64":"cVdugOJGyDA2DsqbFVqg7GGx6tqA03X4Oas13FO2Z361rZo/r0eu4X3CX7Yu6LbKqMagjF3DE6F+iJkm5XBoBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fce1fbcf73ce0039c2707fe28ce8bcf21c0d8c9aadc3013033d1f70f487d1be","last_reissued_at":"2026-08-18T01:14:05.549908Z","signature_status":"signed_v1","first_computed_at":"2026-08-18T01:14:05.549908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"World-in-World: World Models in a Closed-Loop World","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Arda Uzunoglu, Cheng Peng, Daniel Khashabi, Jiahan Zhang, Jiahao Wang, Jieneng Chen, Muqing Jiang, Nanru Dai, Paul Pu Liang, Rama Chellappa, Shunchi Zhang, Taiming Lu, Tianmin Shu, Vishal M. Patel, Yana Wei, Yilun Du","submitted_at":"2025-10-20T22:09:15Z","abstract_excerpt":"Generative world models (WMs) can now simulate worlds with striking visual realism, which naturally raises the question of whether they can endow embodied agents with predictive perception for decision making. Progress on this question has been limited by fragmented evaluation: most existing benchmarks adopt open-loop protocols that emphasize visual quality in isolation, leaving the core issue of embodied utility unresolved, i.e., do WMs actually help agents succeed at embodied tasks? To address this gap, we introduce World-in-World, the first open platform that benchmarks WMs in a closed-loop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.18135","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/2510.18135/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":"2510.18135","created_at":"2026-08-18T01:14:05.550491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.18135v2","created_at":"2026-08-18T01:14:05.550491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.18135","created_at":"2026-08-18T01:14:05.550491+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7HB7PHXHTQA","created_at":"2026-08-18T01:14:05.550491+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7HB7PHXHTQAHHBH","created_at":"2026-08-18T01:14:05.550491+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7HB7PHX","created_at":"2026-08-18T01:14:05.550491+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":23,"sample":[{"citing_arxiv_id":"2607.07196","citing_title":"Validate the Dream Before You Trust Its Verdict: Admissibility for World-Model Simulators","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27537","citing_title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","ref_index":77,"is_internal_anchor":true},{"citing_arxiv_id":"2606.10359","citing_title":"ReflectiChain: Epistemic Grounding in LLM-Driven World Models for Supply Chain Resilience","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27537","citing_title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","ref_index":77,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07687","citing_title":"What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02372","citing_title":"COMAP: Co-Evolving World Models and Agent Policies for LLM Agents","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27537","citing_title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","ref_index":77,"is_internal_anchor":true},{"citing_arxiv_id":"2606.31689","citing_title":"ScratchWorld: Evaluating If World Models Compute Executable Consequences","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27537","citing_title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","ref_index":77,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22809","citing_title":"Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2606.29908","citing_title":"Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25874","citing_title":"WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25620","citing_title":"Back to Parsimonious Latents: Learning Task-Centric World Models from Visual Foundations","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00499","citing_title":"OptiWorld: Optimal Control for Video World Generation under Physical Constraints","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22809","citing_title":"Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17912","citing_title":"WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18729","citing_title":"Robo-Cortex: A Self-Evolving Embodied Agent via Dual-Grain Cognitive Memory and Autonomous Knowledge Induction","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2511.17792","citing_title":"Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets?","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10166","citing_title":"Data-Asymmetric Latent Imagination and Reranking for 3D Robotic Imitation Learning","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06388","citing_title":"Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models","ref_index":74,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00080","citing_title":"World Model for Robot Learning: A Comprehensive Survey","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09535","citing_title":"EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08995","citing_title":"Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R7HB7PHXHTQAHHBHA77CRTULZ4","json":"https://pith.science/pith/R7HB7PHXHTQAHHBHA77CRTULZ4.json","graph_json":"https://pith.science/api/pith-number/R7HB7PHXHTQAHHBHA77CRTULZ4/graph.json","events_json":"https://pith.science/api/pith-number/R7HB7PHXHTQAHHBHA77CRTULZ4/events.json","paper":"https://pith.science/paper/R7HB7PHX"},"agent_actions":{"view_html":"https://pith.science/pith/R7HB7PHXHTQAHHBHA77CRTULZ4","download_json":"https://pith.science/pith/R7HB7PHXHTQAHHBHA77CRTULZ4.json","view_paper":"https://pith.science/paper/R7HB7PHX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.18135&json=true","fetch_graph":"https://pith.science/api/pith-number/R7HB7PHXHTQAHHBHA77CRTULZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/R7HB7PHXHTQAHHBHA77CRTULZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7HB7PHXHTQAHHBHA77CRTULZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7HB7PHXHTQAHHBHA77CRTULZ4/action/storage_attestation","attest_author":"https://pith.science/pith/R7HB7PHXHTQAHHBHA77CRTULZ4/action/author_attestation","sign_citation":"https://pith.science/pith/R7HB7PHXHTQAHHBHA77CRTULZ4/action/citation_signature","submit_replication":"https://pith.science/pith/R7HB7PHXHTQAHHBHA77CRTULZ4/action/replication_record"}},"created_at":"2026-08-18T01:14:05.550491+00:00","updated_at":"2026-08-18T01:14:05.550491+00:00"}