{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LWRUAFIHSWLMQXZQ54VSPNJ5XZ","short_pith_number":"pith:LWRUAFIH","schema_version":"1.0","canonical_sha256":"5da34015079596c85f30ef2b27b53dbe7717861cc6fc5df0023c3881bd83af25","source":{"kind":"arxiv","id":"2501.18668","version":1},"attestation_state":"computed","paper":{"title":"Simulation Streams: A Programming Paradigm for Controlling Large Language Models and Building Complex Systems with Generative AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Joel Z. Leibo, Peter Sunehag","submitted_at":"2025-01-30T16:38:03Z","abstract_excerpt":"We introduce Simulation Streams, a programming paradigm designed to efficiently control and leverage Large Language Models (LLMs) for complex, dynamic simulations and agentic workflows. Our primary goal is to create a minimally interfering framework that harnesses the agentic abilities of LLMs while addressing their limitations in maintaining consistency, selectively ignoring/including information, and enforcing strict world rules. Simulation Streams achieves this through a state-based approach where variables are modified in sequential steps by \"operators,\" producing output on a recurring for"},"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":"2501.18668","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-30T16:38:03Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"43ae3197e1db1c1f63e183a7cf94d63a37daabc1d3fb408edeaf7cae9c193e4c","abstract_canon_sha256":"fae8d3863573c51bc85b855fcd178d66c4614e2169bf6b0ff9d8b18fa79f9c69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:49.911588Z","signature_b64":"sALscD5WjCoV8Le+ea6HH8ACI+IfLhhj44g8tjEbkQ+7b3Cq8YWN4MVUquRcjFAOOSSQJVo9wMwKfTzQ4tmNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5da34015079596c85f30ef2b27b53dbe7717861cc6fc5df0023c3881bd83af25","last_reissued_at":"2026-07-05T10:07:49.911133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:49.911133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simulation Streams: A Programming Paradigm for Controlling Large Language Models and Building Complex Systems with Generative AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Joel Z. Leibo, Peter Sunehag","submitted_at":"2025-01-30T16:38:03Z","abstract_excerpt":"We introduce Simulation Streams, a programming paradigm designed to efficiently control and leverage Large Language Models (LLMs) for complex, dynamic simulations and agentic workflows. Our primary goal is to create a minimally interfering framework that harnesses the agentic abilities of LLMs while addressing their limitations in maintaining consistency, selectively ignoring/including information, and enforcing strict world rules. Simulation Streams achieves this through a state-based approach where variables are modified in sequential steps by \"operators,\" producing output on a recurring for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18668","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/2501.18668/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":"2501.18668","created_at":"2026-07-05T10:07:49.911191+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18668v1","created_at":"2026-07-05T10:07:49.911191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18668","created_at":"2026-07-05T10:07:49.911191+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWRUAFIHSWLM","created_at":"2026-07-05T10:07:49.911191+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWRUAFIHSWLMQXZQ","created_at":"2026-07-05T10:07:49.911191+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWRUAFIH","created_at":"2026-07-05T10:07:49.911191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08892","citing_title":"Multi-Actor Generative Artificial Intelligence as a Game Engine","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWRUAFIHSWLMQXZQ54VSPNJ5XZ","json":"https://pith.science/pith/LWRUAFIHSWLMQXZQ54VSPNJ5XZ.json","graph_json":"https://pith.science/api/pith-number/LWRUAFIHSWLMQXZQ54VSPNJ5XZ/graph.json","events_json":"https://pith.science/api/pith-number/LWRUAFIHSWLMQXZQ54VSPNJ5XZ/events.json","paper":"https://pith.science/paper/LWRUAFIH"},"agent_actions":{"view_html":"https://pith.science/pith/LWRUAFIHSWLMQXZQ54VSPNJ5XZ","download_json":"https://pith.science/pith/LWRUAFIHSWLMQXZQ54VSPNJ5XZ.json","view_paper":"https://pith.science/paper/LWRUAFIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18668&json=true","fetch_graph":"https://pith.science/api/pith-number/LWRUAFIHSWLMQXZQ54VSPNJ5XZ/graph.json","fetch_events":"https://pith.science/api/pith-number/LWRUAFIHSWLMQXZQ54VSPNJ5XZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWRUAFIHSWLMQXZQ54VSPNJ5XZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWRUAFIHSWLMQXZQ54VSPNJ5XZ/action/storage_attestation","attest_author":"https://pith.science/pith/LWRUAFIHSWLMQXZQ54VSPNJ5XZ/action/author_attestation","sign_citation":"https://pith.science/pith/LWRUAFIHSWLMQXZQ54VSPNJ5XZ/action/citation_signature","submit_replication":"https://pith.science/pith/LWRUAFIHSWLMQXZQ54VSPNJ5XZ/action/replication_record"}},"created_at":"2026-07-05T10:07:49.911191+00:00","updated_at":"2026-07-05T10:07:49.911191+00:00"}