{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RMRJDOKEYVFL6KG2GDWK63KZ3D","short_pith_number":"pith:RMRJDOKE","schema_version":"1.0","canonical_sha256":"8b2291b944c54abf28da30ecaf6d59d8e8fa996cf66da6bfa115ec9176d54eb5","source":{"kind":"arxiv","id":"2309.12276","version":3},"attestation_state":"computed","paper":{"title":"LLMR: Real-time Prompting of Interactive Worlds using Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.ET"],"primary_cat":"cs.HC","authors_text":"Andrzej Banburski-Fahey, Cathy Mengying Fang, Fernanda De La Torre, Han Huang, Jaron Lanier, Judith Amores Fernandez","submitted_at":"2023-09-21T17:37:01Z","abstract_excerpt":"We present Large Language Model for Mixed Reality (LLMR), a framework for the real-time creation and modification of interactive Mixed Reality experiences using LLMs. LLMR leverages novel strategies to tackle difficult cases where ideal training data is scarce, or where the design goal requires the synthesis of internal dynamics, intuitive analysis, or advanced interactivity. Our framework relies on text interaction and the Unity game engine. By incorporating techniques for scene understanding, task planning, self-debugging, and memory management, LLMR outperforms the standard GPT-4 by 4x in a"},"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":"2309.12276","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2023-09-21T17:37:01Z","cross_cats_sorted":["cs.AI","cs.CL","cs.ET"],"title_canon_sha256":"86b1fe975a31dcf18321e22f57753c6226f681e7f61e6d54d3865d311f5f6c69","abstract_canon_sha256":"aa586e3762fbfb5d828358b556573c08e56684ebda7cb5cf735408f59a40308d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:18.036279Z","signature_b64":"NLoQZqax29hZ5WS1yy2AUSQw0bkqkxIm9q18gX6GWGXhd2URYheZrW8bOOBgiRQSruhNiezZUoSTgNpReZ1DAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b2291b944c54abf28da30ecaf6d59d8e8fa996cf66da6bfa115ec9176d54eb5","last_reissued_at":"2026-07-05T07:59:18.035736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:18.035736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMR: Real-time Prompting of Interactive Worlds using Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.ET"],"primary_cat":"cs.HC","authors_text":"Andrzej Banburski-Fahey, Cathy Mengying Fang, Fernanda De La Torre, Han Huang, Jaron Lanier, Judith Amores Fernandez","submitted_at":"2023-09-21T17:37:01Z","abstract_excerpt":"We present Large Language Model for Mixed Reality (LLMR), a framework for the real-time creation and modification of interactive Mixed Reality experiences using LLMs. LLMR leverages novel strategies to tackle difficult cases where ideal training data is scarce, or where the design goal requires the synthesis of internal dynamics, intuitive analysis, or advanced interactivity. Our framework relies on text interaction and the Unity game engine. By incorporating techniques for scene understanding, task planning, self-debugging, and memory management, LLMR outperforms the standard GPT-4 by 4x in a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12276","kind":"arxiv","version":3},"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/2309.12276/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":"2309.12276","created_at":"2026-07-05T07:59:18.035799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.12276v3","created_at":"2026-07-05T07:59:18.035799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12276","created_at":"2026-07-05T07:59:18.035799+00:00"},{"alias_kind":"pith_short_12","alias_value":"RMRJDOKEYVFL","created_at":"2026-07-05T07:59:18.035799+00:00"},{"alias_kind":"pith_short_16","alias_value":"RMRJDOKEYVFL6KG2","created_at":"2026-07-05T07:59:18.035799+00:00"},{"alias_kind":"pith_short_8","alias_value":"RMRJDOKE","created_at":"2026-07-05T07:59:18.035799+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02441","citing_title":"LLMER: Crafting Interactive Extended Reality Worlds with JSON Data Generated by Large Language Models","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RMRJDOKEYVFL6KG2GDWK63KZ3D","json":"https://pith.science/pith/RMRJDOKEYVFL6KG2GDWK63KZ3D.json","graph_json":"https://pith.science/api/pith-number/RMRJDOKEYVFL6KG2GDWK63KZ3D/graph.json","events_json":"https://pith.science/api/pith-number/RMRJDOKEYVFL6KG2GDWK63KZ3D/events.json","paper":"https://pith.science/paper/RMRJDOKE"},"agent_actions":{"view_html":"https://pith.science/pith/RMRJDOKEYVFL6KG2GDWK63KZ3D","download_json":"https://pith.science/pith/RMRJDOKEYVFL6KG2GDWK63KZ3D.json","view_paper":"https://pith.science/paper/RMRJDOKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.12276&json=true","fetch_graph":"https://pith.science/api/pith-number/RMRJDOKEYVFL6KG2GDWK63KZ3D/graph.json","fetch_events":"https://pith.science/api/pith-number/RMRJDOKEYVFL6KG2GDWK63KZ3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RMRJDOKEYVFL6KG2GDWK63KZ3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RMRJDOKEYVFL6KG2GDWK63KZ3D/action/storage_attestation","attest_author":"https://pith.science/pith/RMRJDOKEYVFL6KG2GDWK63KZ3D/action/author_attestation","sign_citation":"https://pith.science/pith/RMRJDOKEYVFL6KG2GDWK63KZ3D/action/citation_signature","submit_replication":"https://pith.science/pith/RMRJDOKEYVFL6KG2GDWK63KZ3D/action/replication_record"}},"created_at":"2026-07-05T07:59:18.035799+00:00","updated_at":"2026-07-05T07:59:18.035799+00:00"}