{"as_of":"2026-08-09T09:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b39198bbfea4ed24949829e451e47883e0d0285d6c1740c37feacedc6cce82f6","coverage":[{"denominator":26,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":26,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T16:47:25.181509Z","state":"measured"},{"denominator":26,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":26,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.12666/citation-record","integrity":"/paper/2507.12666/integrity","json":"/paper/2507.12666/citation-record.json","paper":"/paper/2507.12666"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:28.510637Z","title":"Deep reinforcement learning at the edge of the statistical precipice","venue":null,"work_id":"ddfbea16-41bd-4e1c-b89f-4ba33cad1731","year":2021},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:22.820069Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:7527a17a2b82dfdf444db64ec7ecaad31d20ac3ce03d6f9f800bda54fab84f62","observation_id":"8be4dd52-b55f-4d19-8b79-a125121762d3","resolution":{"observed_at":"2026-08-06T16:47:28.582241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:28.383644Z","title":"The I nk S plotch E ffect: A case study on ChatGPT as a co-creative game designer","venue":null,"work_id":"875d7005-8949-473b-99e7-2bf0d3ec8eda","year":2024},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:22.909174Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:a2661ae416bb8cc1335db51a0f45847090edf8db73d11f3c27be19b2a7f2beef","observation_id":"cab5262a-dbf4-45ff-bd75-af2aeed211bd","resolution":{"observed_at":"2026-08-06T16:47:28.440178Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.06680","last_updated":"2019-12-13T19:56:40Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2019-12-13T19:56:40Z","title":"Dota 2 with Large Scale Deep Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.06680","snapshot_observed_at":"2026-08-06T16:47:23.007820Z","title":"Dota 2 with large scale deep reinforcement learning","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:23.007820Z"},"links":{"cited_paper":"/paper/1912.06680","citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:b92db745dfb0ceebe083180d844c30e86b22500344f74c171e4d30a68aab31a0","observation_id":"efe3c378-84c2-4596-93b7-8dd60da6e8f3","resolution":{"observed_at":"2026-08-06T16:47:23.007820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.3390/s24061905","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:25.329131Z","title":"Playing F lappy B ird based on motion recognition using a transformer model and LIDAR sensor","venue":null,"work_id":"18d732e6-3fc4-4ddc-bdd8-1ee6126a7649","year":2024},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:23.107024Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:38f14089b516f56272ef69e65e1d00135a45fb1ab6adf47b586240e389800283","observation_id":"b2e3eb37-cd9d-4fe5-9610-328f71a18576","resolution":{"observed_at":"2026-08-06T16:47:25.418686Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:28.255042Z","title":"Adversarial reinforcement learning for procedural content generation","venue":null,"work_id":"4418aad7-d403-4501-81c8-f1214be4c122","year":2021},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:23.240291Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:512f26cb54e9b97a1a59e588d828daa3db95f215c12fc4da4e125abc04755a7f","observation_id":"8e469dfb-37f8-49a1-a6a5-dc0a2be3dae6","resolution":{"observed_at":"2026-08-06T16:47:28.310086Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:23.346837Z","title":"Mastering diverse control tasks through world models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:23.346837Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:b970912842c8d02905c5ca5479cfbbd00e915eb2b0f54aea8355ff6b026d9f83","observation_id":"b1b3a1ad-4929-4d36-a34f-fa75294232ae","resolution":{"observed_at":"2026-08-06T16:47:23.346837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:28.100683Z","title":"Gen2Sim : Scaling up robot learning in simulation with generative models","venue":null,"work_id":"13a1c4b0-0533-4ba9-a471-918d2db939e7","year":2024},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:23.443980Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:f9eeb17160b1fcb34208d590b5611f1403c6bab585f46560ffc68610042ae6df","observation_id":"76761cd2-2112-4b5c-91af-41e6d8f7e70d","resolution":{"observed_at":"2026-08-06T16:47:28.160197Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:27.990278Z","title":"PCGRL : Procedural content generation via reinforcement learning","venue":null,"work_id":"a1a8fc45-a948-435f-9aad-2db895e5cf5f","year":2020},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:23.538564Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:2ec444c5efd5ae42b1b0fac8398b9327267c4e0096d8ede8ca47c3983ea0eee3","observation_id":"0b538b68-29d6-4ed4-9463-73b8149d6791","resolution":{"observed_at":"2026-08-06T16:47:28.041064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:27.816219Z","title":"Reward design with language models","venue":null,"work_id":"cb34fd4a-cbd9-4ab1-9313-78709b102ad9","year":2023},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:23.637237Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:f8a213e229997e13871835c2351dba1ef0bc9d295b96305b1daa8457fc12e523","observation_id":"ab8eae8f-3740-4a5a-9df8-743371bebefb","resolution":{"observed_at":"2026-08-06T16:47:27.918136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:27.622899Z","title":"Eureka: Human-level reward design via coding large language models","venue":null,"work_id":"e5b94f5e-37f8-4f29-8077-30f37157733c","year":2023},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:23.735178Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:ea00c64eda69f6797b68bb998c2bcf21eafd289b1cd35941bed7a8de9ee64b82","observation_id":"87fc441e-0cfc-4dbe-84b1-1d9eceffec97","resolution":{"observed_at":"2026-08-06T16:47:27.718318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:27.417225Z","title":"DrEureka : Language model guided sim-to-real transfer","venue":null,"work_id":"c1b7c5a4-3ff2-4115-bb5d-ed82b7f151f7","year":2024},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:23.834414Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:c03d46e2d30aa4de328fa1eff337e413c36409a461622d287e711bd718d760dc","observation_id":"e931b437-312a-49a0-9996-6778873a959c","resolution":{"observed_at":"2026-08-06T16:47:27.524926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:23.934263Z","title":"Human-level control through deep reinforcement learning","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:23.934263Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:813b354a27004a7b2c22da13961e97469ffdae66e6c6ecd8c39a47dd3da3733e","observation_id":"f54fb9ee-77ac-4692-afdd-f848d8155407","resolution":{"observed_at":"2026-08-06T16:47:23.934263Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:27.232418Z","title":"MAESTRO : Open-ended environment design for multi-agent reinforcement learning","venue":null,"work_id":"7999572b-2ce4-4e03-b057-9275c7f48d72","year":2023},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:24.032973Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:64e73b99889fe8311a9776a7a450047ead05cdf946931c78e0b63b27f5c014f1","observation_id":"140537b6-f9e5-4b9d-a733-4f35bd750442","resolution":{"observed_at":"2026-08-06T16:47:27.339163Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:24.152678Z","title":"A general reinforcement learning algorithm that masters chess, shogi, and go through self-play","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:24.152678Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:6d007f39a43e540c30c24cb4b45338d16bf4794af90c9a3e4a01a8059ee8c893","observation_id":"4a9086fd-42b0-45d5-8527-60c0e5f65ee6","resolution":{"observed_at":"2026-08-06T16:47:24.152678Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.12808","last_updated":"2021-07-31T16:55:19Z","snapshot_observed_at":"2026-08-07T04:03:03.246090Z","submitted_at":"2021-07-27T13:30:07Z","title":"Open-Ended Learning Leads to Generally Capable Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.12808","snapshot_observed_at":"2026-08-06T16:47:24.273683Z","title":"Open-ended learning leads to generally capable agents","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:24.273683Z"},"links":{"cited_paper":"/paper/2107.12808","citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:721209b5f6e202c2de56df033e283898cb0890da91e32dd987487f7c029f4821","observation_id":"23c62845-b9db-4975-b2ea-c7aabaade011","resolution":{"observed_at":"2026-08-06T16:47:24.273683Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:27.016901Z","title":"MarioGPT : Open-ended text2level generation through large language models","venue":null,"work_id":"7ba2ff24-d8de-41ff-abd4-3a1a73c54abf","year":2023},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:24.367020Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:b7a42f3e4aed2ba823245f50da44e6143e5eaeb5e6b4a8ad1528823c42514074","observation_id":"b5d9b907-689d-444a-bac6-9813077061e7","resolution":{"observed_at":"2026-08-06T16:47:27.109329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:26.896662Z","title":"FactorSim : Generative simulation via factorized representation","venue":null,"work_id":"784085df-d6db-4d10-b8ce-1504fdf2d130","year":2024},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:24.452986Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:75083a78990928ed3244dd2f7bebf125ed7bec53566f9dec16b387c34898e3c5","observation_id":"ce2a29f9-8b65-4488-ba2e-23cfee6802ac","resolution":{"observed_at":"2026-08-06T16:47:26.957193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:26.687956Z","title":"Level generation through large language models","venue":null,"work_id":"7b7204f3-3625-4488-abb6-41352616a813","year":2023},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:24.528637Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:9991cf053c37ad781549547c80d4b54070da2d007a00bedc935a1e11bedb2f67","observation_id":"c958d56f-acf5-4444-bbd0-3fb758fe0300","resolution":{"observed_at":"2026-08-06T16:47:26.784550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:24.609668Z","title":"Czarnecki, Micha \\\"e l Mathieu, Andrew Dudzik, Junyoung Chung, David H","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:24.609668Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:c95f4c4ec39bd52b75ce370e778c0380d11a5f59810c97579baf2014e5cad26c","observation_id":"d45cc9be-b76e-48ae-a8cd-6fe998af2b01","resolution":{"observed_at":"2026-08-06T16:47:24.609668Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:26.502748Z","title":"POET : open-ended coevolution of environments and their optimized solutions","venue":null,"work_id":"d1de926b-4920-4d50-857f-08efa3b6af4a","year":2019},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:24.684186Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:de631abe5f672db73c4a9a8a73176ca3016e96c41bb1be5aab01beb672cc6aa1","observation_id":"8a744cd5-ed2f-4375-bc04-c555881b23cd","resolution":{"observed_at":"2026-08-06T16:47:26.588323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:26.337150Z","title":"Enhanced POET : Open-ended reinforcement learning through unbounded invention of learning challenges and their solutions","venue":null,"work_id":"94c46e41-603e-445e-9e42-5f2ea1f0e0f5","year":2020},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:24.750644Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:b05db168200a74e024a3e4839407d5973d9251fd87b86469a0c7c41a7721d24a","observation_id":"17228f76-73e4-499d-b445-173927c2aa49","resolution":{"observed_at":"2026-08-06T16:47:26.395049Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:26.080483Z","title":"RoboGen : Towards unleashing infinite data for automated robot learning via generative simulation","venue":null,"work_id":"a889a621-5324-418f-8463-e5f382276a15","year":2024},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:24.829471Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:d2e51622b22f7cfaf2ce90461dbf957476a281108f1998529f62985157dfde0d","observation_id":"c70a97ca-4e45-4523-bd9d-2521151e04d3","resolution":{"observed_at":"2026-08-06T16:47:26.218691Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:25.900959Z","title":"Holodeck: Language guided generation of 3d embodied ai environments","venue":null,"work_id":"2f9ef19c-95cb-4d66-b38d-28aed90f996a","year":2024},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:24.906904Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:b447dee1f88b6d828d087db661c3d411946a627e306aff8357b6ed54d1523ce5","observation_id":"86a77f62-0597-488d-a236-d7dec3c40529","resolution":{"observed_at":"2026-08-06T16:47:25.968915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:25.673763Z","title":"Envgen: Generating and adapting environments via LLMs for training embodied agents","venue":null,"work_id":"c1e8f1a7-434d-4f2b-9de1-d5e36a98fbb5","year":2024},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:24.995861Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:c2f8e969c3a576c9665c10682e6462732e3b01a6b2888b8dade709b613d92b35","observation_id":"adb8e1fd-cd7f-4178-8339-b599ca31d48b","resolution":{"observed_at":"2026-08-06T16:47:25.782840Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:25.527976Z","title":"Automatic playtesting for game parameter tuning via active learning","venue":null,"work_id":"2f938b6a-9557-46b1-9eba-89d775878e29","year":2014},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:25.087001Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:5e5cb4ee0a9676593d998858c643658b7f52915c14c8a9e46c20027a7799350e","observation_id":"417a633d-6f68-46da-9c0c-b78168bae041","resolution":{"observed_at":"2026-08-06T16:47:25.604181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:47:25.181509Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-06T16:47:25.181509Z"},"links":{"citing_paper":"/paper/2507.12666"},"observation_digest":"sha256:9995521157eeb0ba7a8482e7cbcf1ba06a70900813bb5b7019bb033b36b6f036","observation_id":"84cbfdcd-6a67-49fe-9e04-1c53f0ef1a97","resolution":{"observed_at":"2026-08-06T16:47:25.181509Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.12666","last_updated":"2025-07-16T22:45:40Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-06T16:39:53.078012Z","submitted_at":"2025-07-16T22:45:40Z","title":"Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models"},"reference_resolution":{"displayed":26,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":1,"verified_fuzzy":18},"total_outbound_references":26},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2507.12666."}