{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QZ6MK2FLWOJZZDDVWU52RWVW3Q","short_pith_number":"pith:QZ6MK2FL","canonical_record":{"source":{"id":"2310.06114","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-09T19:42:22Z","cross_cats_sorted":[],"title_canon_sha256":"789e3b72ad104bc24deb582c2640adef7278f1fe06a1f80a6ea817872909cb55","abstract_canon_sha256":"f5fbf1bc995ed3144ec40405870c5e7ba524f6226e1c14e7b7ade4432c605e07"},"schema_version":"1.0"},"canonical_sha256":"867cc568abb3939c8c75b53ba8dab6dc2e0f3c5e9e3d70c0de45f256515bbca0","source":{"kind":"arxiv","id":"2310.06114","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06114","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06114v3","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06114","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"pith_short_12","alias_value":"QZ6MK2FLWOJZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QZ6MK2FLWOJZZDDV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QZ6MK2FL","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QZ6MK2FLWOJZZDDVWU52RWVW3Q","target":"record","payload":{"canonical_record":{"source":{"id":"2310.06114","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-09T19:42:22Z","cross_cats_sorted":[],"title_canon_sha256":"789e3b72ad104bc24deb582c2640adef7278f1fe06a1f80a6ea817872909cb55","abstract_canon_sha256":"f5fbf1bc995ed3144ec40405870c5e7ba524f6226e1c14e7b7ade4432c605e07"},"schema_version":"1.0"},"canonical_sha256":"867cc568abb3939c8c75b53ba8dab6dc2e0f3c5e9e3d70c0de45f256515bbca0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:49.416692Z","signature_b64":"17byKW6sLLw1Do6qB0CRX4ReEsSgj3JDjx9fHoi8flbKG49TcYzqAJg7+wasUoxYPmOLE7d+ltNaRcltMFr+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"867cc568abb3939c8c75b53ba8dab6dc2e0f3c5e9e3d70c0de45f256515bbca0","last_reissued_at":"2026-05-17T23:38:49.416157Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:49.416157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.06114","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uLSG5LyYAsWQ3WNNtUyZDodQ4388GhmOUJ7VmS6H1r6GeJbj4zPr4/7y5tL/KbjmhCUELDKKYfVJSCYNUZcwAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T04:08:55.922630Z"},"content_sha256":"b3ea847426ab10ed3dd883eca921e4c6312fe517041b18c9dc498a111434c7bc","schema_version":"1.0","event_id":"sha256:b3ea847426ab10ed3dd883eca921e4c6312fe517041b18c9dc498a111434c7bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QZ6MK2FLWOJZZDDVWU52RWVW3Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Interactive Real-World Simulators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A generative model simulates real-world interactions from static image, robotics and navigation datasets to enable zero-shot policy transfer.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dale Schuurmans, Jonathan Tompson, Kamyar Ghasemipour, Leslie Kaelbling, Pieter Abbeel, Sherry Yang, Yilun Du","submitted_at":"2023-10-09T19:42:22Z","abstract_excerpt":"Generative models trained on internet data have revolutionized how text, image, and video content can be created. Perhaps the next milestone for generative models is to simulate realistic experience in response to actions taken by humans, robots, and other interactive agents. Applications of a real-world simulator range from controllable content creation in games and movies, to training embodied agents purely in simulation that can be directly deployed in the real world. We explore the possibility of learning a universal simulator (UniSim) of real-world interaction through generative modeling."},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We use the simulator to train both high-level vision-language policies and low-level reinforcement learning policies, each of which can be deployed in the real world in zero shot after training purely in simulation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That careful orchestration of existing static image, robotics, and navigation datasets is sufficient to capture the full interactive dynamics needed for zero-shot real-world transfer.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A generative model simulates real-world interactions from static image, robotics and navigation datasets to enable zero-shot policy transfer.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"bf491117557ffca811908ae2b804f42959bfc9734799b40a4f6ac5d821d0ec49"},"source":{"id":"2310.06114","kind":"arxiv","version":3},"verdict":{"id":"a252a617-539b-4faa-a6e6-0e1e684f9043","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T02:03:50.905362Z","strongest_claim":"We use the simulator to train both high-level vision-language policies and low-level reinforcement learning policies, each of which can be deployed in the real world in zero shot after training purely in simulation.","one_line_summary":"UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That careful orchestration of existing static image, robotics, and navigation datasets is sufficient to capture the full interactive dynamics needed for zero-shot real-world transfer.","pith_extraction_headline":"A generative model simulates real-world interactions from static image, robotics and navigation datasets to enable zero-shot policy transfer."},"references":{"count":276,"sample":[{"doi":"","year":2018,"title":"A separation principle for control in the age of deep learning","work_id":"3c05974f-3487-4e63-8ea0-d9387f0729e2","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Vision-and-language navigation: Interpreting visually-grounded navigation instructions in real environments","work_id":"78b6696c-9c19-4daa-9316-4c58cde88a1a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Hindsight experience replay","work_id":"1c0c6eeb-5585-47a7-a35f-a23cd37cb214","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"PaLM 2 Technical Report","work_id":"905ee9a7-ea61-4a94-bd62-2600cbe3e315","ref_index":4,"cited_arxiv_id":"2305.10403","is_internal_anchor":true},{"doi":"","year":1995,"title":"Dimitri P. Bertsekas. Dynamic Programming and Optimal Control. Athena Scientific, 1995","work_id":"6d2d0066-454a-43ba-92f5-e8932c3357b9","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":276,"snapshot_sha256":"7624ddbf2708c592972f92b101290308a95b53d427166262953167e45bb0d8ec","internal_anchors":50},"formal_canon":{"evidence_count":2,"snapshot_sha256":"88b9d63a88e3555d09b46e603ebea2bb3de73e81a200d61f02a55696540e761b"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"a252a617-539b-4faa-a6e6-0e1e684f9043"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IjlUH09gsO4D4t5uqWOSaqc4xNzSA2NhIoNA7gW9tXVM/sSpj28OHqxXg9/t7jNk81GL2ovxV7WbeakP8uwSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T04:08:55.923151Z"},"content_sha256":"2efdc8488e0b22750d2211d9ff4f508daefade3c844c7e0edbc738feca7a9fca","schema_version":"1.0","event_id":"sha256:2efdc8488e0b22750d2211d9ff4f508daefade3c844c7e0edbc738feca7a9fca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QZ6MK2FLWOJZZDDVWU52RWVW3Q/bundle.json","state_url":"https://pith.science/pith/QZ6MK2FLWOJZZDDVWU52RWVW3Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QZ6MK2FLWOJZZDDVWU52RWVW3Q/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-02T04:08:55Z","links":{"resolver":"https://pith.science/pith/QZ6MK2FLWOJZZDDVWU52RWVW3Q","bundle":"https://pith.science/pith/QZ6MK2FLWOJZZDDVWU52RWVW3Q/bundle.json","state":"https://pith.science/pith/QZ6MK2FLWOJZZDDVWU52RWVW3Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QZ6MK2FLWOJZZDDVWU52RWVW3Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QZ6MK2FLWOJZZDDVWU52RWVW3Q","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f5fbf1bc995ed3144ec40405870c5e7ba524f6226e1c14e7b7ade4432c605e07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-09T19:42:22Z","title_canon_sha256":"789e3b72ad104bc24deb582c2640adef7278f1fe06a1f80a6ea817872909cb55"},"schema_version":"1.0","source":{"id":"2310.06114","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06114","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06114v3","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06114","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"pith_short_12","alias_value":"QZ6MK2FLWOJZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QZ6MK2FLWOJZZDDV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QZ6MK2FL","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:2efdc8488e0b22750d2211d9ff4f508daefade3c844c7e0edbc738feca7a9fca","target":"graph","created_at":"2026-05-17T23:38:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We use the simulator to train both high-level vision-language policies and low-level reinforcement learning policies, each of which can be deployed in the real world in zero shot after training purely in simulation."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That careful orchestration of existing static image, robotics, and navigation datasets is sufficient to capture the full interactive dynamics needed for zero-shot real-world transfer."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A generative model simulates real-world interactions from static image, robotics and navigation datasets to enable zero-shot policy transfer."}],"snapshot_sha256":"bf491117557ffca811908ae2b804f42959bfc9734799b40a4f6ac5d821d0ec49"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"88b9d63a88e3555d09b46e603ebea2bb3de73e81a200d61f02a55696540e761b"},"paper":{"abstract_excerpt":"Generative models trained on internet data have revolutionized how text, image, and video content can be created. Perhaps the next milestone for generative models is to simulate realistic experience in response to actions taken by humans, robots, and other interactive agents. Applications of a real-world simulator range from controllable content creation in games and movies, to training embodied agents purely in simulation that can be directly deployed in the real world. We explore the possibility of learning a universal simulator (UniSim) of real-world interaction through generative modeling.","authors_text":"Dale Schuurmans, Jonathan Tompson, Kamyar Ghasemipour, Leslie Kaelbling, Pieter Abbeel, Sherry Yang, Yilun Du","cross_cats":[],"headline":"A generative model simulates real-world interactions from static image, robotics and navigation datasets to enable zero-shot policy transfer.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-09T19:42:22Z","title":"Learning Interactive Real-World Simulators"},"references":{"count":276,"internal_anchors":50,"resolved_work":276,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"A separation principle for control in the age of deep learning","work_id":"3c05974f-3487-4e63-8ea0-d9387f0729e2","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Vision-and-language navigation: Interpreting visually-grounded navigation instructions in real environments","work_id":"78b6696c-9c19-4daa-9316-4c58cde88a1a","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Hindsight experience replay","work_id":"1c0c6eeb-5585-47a7-a35f-a23cd37cb214","year":2017},{"cited_arxiv_id":"2305.10403","doi":"","is_internal_anchor":true,"ref_index":4,"title":"PaLM 2 Technical Report","work_id":"905ee9a7-ea61-4a94-bd62-2600cbe3e315","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Dimitri P. Bertsekas. Dynamic Programming and Optimal Control. Athena Scientific, 1995","work_id":"6d2d0066-454a-43ba-92f5-e8932c3357b9","year":1995}],"snapshot_sha256":"7624ddbf2708c592972f92b101290308a95b53d427166262953167e45bb0d8ec"},"source":{"id":"2310.06114","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T02:03:50.905362Z","id":"a252a617-539b-4faa-a6e6-0e1e684f9043","model_set":{"reader":"grok-4.3"},"one_line_summary":"UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A generative model simulates real-world interactions from static image, robotics and navigation datasets to enable zero-shot policy transfer.","strongest_claim":"We use the simulator to train both high-level vision-language policies and low-level reinforcement learning policies, each of which can be deployed in the real world in zero shot after training purely in simulation.","weakest_assumption":"That careful orchestration of existing static image, robotics, and navigation datasets is sufficient to capture the full interactive dynamics needed for zero-shot real-world transfer."}},"verdict_id":"a252a617-539b-4faa-a6e6-0e1e684f9043"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b3ea847426ab10ed3dd883eca921e4c6312fe517041b18c9dc498a111434c7bc","target":"record","created_at":"2026-05-17T23:38:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f5fbf1bc995ed3144ec40405870c5e7ba524f6226e1c14e7b7ade4432c605e07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-09T19:42:22Z","title_canon_sha256":"789e3b72ad104bc24deb582c2640adef7278f1fe06a1f80a6ea817872909cb55"},"schema_version":"1.0","source":{"id":"2310.06114","kind":"arxiv","version":3}},"canonical_sha256":"867cc568abb3939c8c75b53ba8dab6dc2e0f3c5e9e3d70c0de45f256515bbca0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"867cc568abb3939c8c75b53ba8dab6dc2e0f3c5e9e3d70c0de45f256515bbca0","first_computed_at":"2026-05-17T23:38:49.416157Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:49.416157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"17byKW6sLLw1Do6qB0CRX4ReEsSgj3JDjx9fHoi8flbKG49TcYzqAJg7+wasUoxYPmOLE7d+ltNaRcltMFr+Bw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:49.416692Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.06114","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3ea847426ab10ed3dd883eca921e4c6312fe517041b18c9dc498a111434c7bc","sha256:2efdc8488e0b22750d2211d9ff4f508daefade3c844c7e0edbc738feca7a9fca"],"state_sha256":"426f5a93898934e179b7289ff1bc40e383e38b4479bddfad1035a8f256954a07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fz+LBvhxsQEASaaH7mcfVSA8pNWYdPX7QGenzl+NJe4Drym3S4/W61ecarvow9v30+kJ3Le8tLNjgBf4eOU/AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T04:08:55.925607Z","bundle_sha256":"d67b4e6b2d3daa8bd65cca1bc73aef59f0cb26bcc3c0728c6a096af0b3ab5b16"}}