{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OQMKWPIOKYITONMFZWJXDK2DDW","short_pith_number":"pith:OQMKWPIO","schema_version":"1.0","canonical_sha256":"7418ab3d0e5611373585cd9371ab431db9463084b74c98265848c85cd7a056ac","source":{"kind":"arxiv","id":"2210.05359","version":1},"attestation_state":"computed","paper":{"title":"Mind's Eye: Grounded Language Model Reasoning through Simulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrew M. Dai, Claire Cui, Denny Zhou, Jason Wei, Ruibo Liu, Shixiang Shane Gu, Soroush Vosoughi, Te-Yen Wu","submitted_at":"2022-10-11T11:39:23Z","abstract_excerpt":"Successful and effective communication between humans and AI relies on a shared experience of the world. By training solely on written text, current language models (LMs) miss the grounded experience of humans in the real-world -- their failure to relate language to the physical world causes knowledge to be misrepresented and obvious mistakes in their reasoning. We present Mind's Eye, a paradigm to ground language model reasoning in the physical world. Given a physical reasoning question, we use a computational physics engine (DeepMind's MuJoCo) to simulate the possible outcomes, and then use "},"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":"2210.05359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T11:39:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7e8cee69f379bfc0b557c792f4971fd34429bc2a3e90fc0658e1d1eec4097d0c","abstract_canon_sha256":"c2989ac4a2ef94d62401d7738c1b4c95034ad59fd4262b4f065afbe990e80388"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:15.861390Z","signature_b64":"24+fDsW1/J0uhlPPNcQjtnhM9uBcvcbtUWrL/Mqa8xSyWESWv87gZwRz7ZH7R9gZQ4s8pZYaqFz7VTfH04ajCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7418ab3d0e5611373585cd9371ab431db9463084b74c98265848c85cd7a056ac","last_reissued_at":"2026-07-05T05:05:15.860936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:15.860936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mind's Eye: Grounded Language Model Reasoning through Simulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrew M. Dai, Claire Cui, Denny Zhou, Jason Wei, Ruibo Liu, Shixiang Shane Gu, Soroush Vosoughi, Te-Yen Wu","submitted_at":"2022-10-11T11:39:23Z","abstract_excerpt":"Successful and effective communication between humans and AI relies on a shared experience of the world. By training solely on written text, current language models (LMs) miss the grounded experience of humans in the real-world -- their failure to relate language to the physical world causes knowledge to be misrepresented and obvious mistakes in their reasoning. We present Mind's Eye, a paradigm to ground language model reasoning in the physical world. Given a physical reasoning question, we use a computational physics engine (DeepMind's MuJoCo) to simulate the possible outcomes, and then use "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05359","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/2210.05359/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":"2210.05359","created_at":"2026-07-05T05:05:15.860993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05359v1","created_at":"2026-07-05T05:05:15.860993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05359","created_at":"2026-07-05T05:05:15.860993+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQMKWPIOKYIT","created_at":"2026-07-05T05:05:15.860993+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQMKWPIOKYITONMF","created_at":"2026-07-05T05:05:15.860993+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQMKWPIO","created_at":"2026-07-05T05:05:15.860993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":210,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23580","citing_title":"PhysCodeBench: Benchmarking Physics-Aware Symbolic Simulation of 3D Scenes via Self-Corrective Multi-Agent Refinement","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04680","citing_title":"Multi-Level Bidirectional Biomimetic Learning for EEG-Based Visual Decoding","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQMKWPIOKYITONMFZWJXDK2DDW","json":"https://pith.science/pith/OQMKWPIOKYITONMFZWJXDK2DDW.json","graph_json":"https://pith.science/api/pith-number/OQMKWPIOKYITONMFZWJXDK2DDW/graph.json","events_json":"https://pith.science/api/pith-number/OQMKWPIOKYITONMFZWJXDK2DDW/events.json","paper":"https://pith.science/paper/OQMKWPIO"},"agent_actions":{"view_html":"https://pith.science/pith/OQMKWPIOKYITONMFZWJXDK2DDW","download_json":"https://pith.science/pith/OQMKWPIOKYITONMFZWJXDK2DDW.json","view_paper":"https://pith.science/paper/OQMKWPIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05359&json=true","fetch_graph":"https://pith.science/api/pith-number/OQMKWPIOKYITONMFZWJXDK2DDW/graph.json","fetch_events":"https://pith.science/api/pith-number/OQMKWPIOKYITONMFZWJXDK2DDW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQMKWPIOKYITONMFZWJXDK2DDW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQMKWPIOKYITONMFZWJXDK2DDW/action/storage_attestation","attest_author":"https://pith.science/pith/OQMKWPIOKYITONMFZWJXDK2DDW/action/author_attestation","sign_citation":"https://pith.science/pith/OQMKWPIOKYITONMFZWJXDK2DDW/action/citation_signature","submit_replication":"https://pith.science/pith/OQMKWPIOKYITONMFZWJXDK2DDW/action/replication_record"}},"created_at":"2026-07-05T05:05:15.860993+00:00","updated_at":"2026-07-05T05:05:15.860993+00:00"}