{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KZKUEZCIX2LHOY4KFXH35OZC5R","short_pith_number":"pith:KZKUEZCI","schema_version":"1.0","canonical_sha256":"5655426448be9677638a2dcfbebb22ec6e73adbf1616034601ccb7fc98715293","source":{"kind":"arxiv","id":"2503.09617","version":1},"attestation_state":"computed","paper":{"title":"Factorio Learning Environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.MA","authors_text":"Akbir Khan, Jack Hopkins, Mart Bakler","submitted_at":"2025-03-06T20:13:02Z","abstract_excerpt":"Large Language Models (LLMs) are rapidly saturating existing benchmarks, necessitating new open-ended evaluations. We introduce the Factorio Learning Environment (FLE), based on the game of Factorio, that tests agents in long-term planning, program synthesis, and resource optimization. FLE provides exponentially scaling challenges -- from basic automation to complex factories processing millions of resource units per second. We provide two settings: (1) lab-play consisting of eight structured tasks with fixed resources, and (2) open-play with the unbounded task of building the largest factory "},"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":"2503.09617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-03-06T20:13:02Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"542b73cba922e4cfda8070d879a9adffb7dbc9c67cb6cb8646cfdce9074b2993","abstract_canon_sha256":"b09905880ee0621cecf175fefaeec46a3d9679027538ff706ec3121e8af6d094"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:04.820853Z","signature_b64":"zEWHdJgFBux+7tE4GeaMLOww3Pk/sEv29KdjGWd0aO2XBKkmGJ++yJzIZIZVcuuzSzEsb1cgaFpBtXAyNi6rBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5655426448be9677638a2dcfbebb22ec6e73adbf1616034601ccb7fc98715293","last_reissued_at":"2026-07-05T10:30:04.820375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:04.820375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Factorio Learning Environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.MA","authors_text":"Akbir Khan, Jack Hopkins, Mart Bakler","submitted_at":"2025-03-06T20:13:02Z","abstract_excerpt":"Large Language Models (LLMs) are rapidly saturating existing benchmarks, necessitating new open-ended evaluations. We introduce the Factorio Learning Environment (FLE), based on the game of Factorio, that tests agents in long-term planning, program synthesis, and resource optimization. FLE provides exponentially scaling challenges -- from basic automation to complex factories processing millions of resource units per second. We provide two settings: (1) lab-play consisting of eight structured tasks with fixed resources, and (2) open-play with the unbounded task of building the largest factory "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09617","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/2503.09617/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":"2503.09617","created_at":"2026-07-05T10:30:04.820430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.09617v1","created_at":"2026-07-05T10:30:04.820430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09617","created_at":"2026-07-05T10:30:04.820430+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZKUEZCIX2LH","created_at":"2026-07-05T10:30:04.820430+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZKUEZCIX2LHOY4K","created_at":"2026-07-05T10:30:04.820430+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZKUEZCI","created_at":"2026-07-05T10:30:04.820430+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":119,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KZKUEZCIX2LHOY4KFXH35OZC5R","json":"https://pith.science/pith/KZKUEZCIX2LHOY4KFXH35OZC5R.json","graph_json":"https://pith.science/api/pith-number/KZKUEZCIX2LHOY4KFXH35OZC5R/graph.json","events_json":"https://pith.science/api/pith-number/KZKUEZCIX2LHOY4KFXH35OZC5R/events.json","paper":"https://pith.science/paper/KZKUEZCI"},"agent_actions":{"view_html":"https://pith.science/pith/KZKUEZCIX2LHOY4KFXH35OZC5R","download_json":"https://pith.science/pith/KZKUEZCIX2LHOY4KFXH35OZC5R.json","view_paper":"https://pith.science/paper/KZKUEZCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.09617&json=true","fetch_graph":"https://pith.science/api/pith-number/KZKUEZCIX2LHOY4KFXH35OZC5R/graph.json","fetch_events":"https://pith.science/api/pith-number/KZKUEZCIX2LHOY4KFXH35OZC5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZKUEZCIX2LHOY4KFXH35OZC5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZKUEZCIX2LHOY4KFXH35OZC5R/action/storage_attestation","attest_author":"https://pith.science/pith/KZKUEZCIX2LHOY4KFXH35OZC5R/action/author_attestation","sign_citation":"https://pith.science/pith/KZKUEZCIX2LHOY4KFXH35OZC5R/action/citation_signature","submit_replication":"https://pith.science/pith/KZKUEZCIX2LHOY4KFXH35OZC5R/action/replication_record"}},"created_at":"2026-07-05T10:30:04.820430+00:00","updated_at":"2026-07-05T10:30:04.820430+00:00"}