{"as_of":"2026-08-23T06:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9e619e8c705eaa7f4e51f347c91997e87fe483be8c0c7271fca6951af0700426","coverage":[{"denominator":29,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":29,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:08:43.060904Z","state":"measured"},{"denominator":29,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":29,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+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/2505.08073/citation-record","integrity":"/paper/2505.08073/integrity","json":"/paper/2505.08073/citation-record.json","paper":"/paper/2505.08073"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:08:45.216988Z","title":"Experiential explanations for reinforce- ment learning","venue":null,"work_id":"fb59be73-018d-4ccd-9090-f856c51f1e61","year":2025},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.108667Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:52dc3c77cb25499c84b5c08d3c2b1cb0b3f371d8b8d783437cf4ae8a278970a7","observation_id":"c634ca70-d014-411f-a831-e0c4d0d92586","resolution":{"observed_at":"2026-08-15T22:08:45.222063Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:44.775162Z","title":"Traditional and raw task load index (tlx) correlations: Are paired comparisons necessary","venue":null,"work_id":"fbd566af-eee2-474e-8a5b-c2f0dee7142b","year":1989},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.424020Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:b0337d0b1570dc18731c853985904542a52ad66a8418c776fb7c8664f5d14e1a","observation_id":"09b97db1-4270-4e63-beea-4cada6455eb7","resolution":{"observed_at":"2026-08-15T22:08:44.780073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:44.387772Z","title":"World models","venue":null,"work_id":"44b626de-e0d7-4cbe-9d51-bc65ae1c5489","year":2018},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.654584Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:0b143fd2a76be8f4d836cffe35a66625ecf553bec52c5c7850481868e760a123","observation_id":"c84ca078-c149-4b9d-b336-0087680c39fb","resolution":{"observed_at":"2026-08-15T22:08:44.392105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:44.326337Z","title":"Learning latent dynamics for planning from pixels,","venue":null,"work_id":"c133a2ad-b7df-4108-b5ac-d1a336ff182a","year":2019},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.659949Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:7b85437fcfea1e448ce86754aa16431b5376aa780d73f91eb8da74f3f571726a","observation_id":"d6da496a-9be0-4a32-910d-c31f99c81769","resolution":{"observed_at":"2026-08-15T22:08:44.378077Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:44.229523Z","title":"Mastering diverse control tasks through world models","venue":null,"work_id":"4d418cab-db26-447a-8cc6-f92860415179","year":2025},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.665606Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:320bc21f76f0cc9709410568ad9878783ae00264ff8b986a8143879026c59b0e","observation_id":"c13b1c27-e517-4dae-ac84-586bb75d44ac","resolution":{"observed_at":"2026-08-15T22:08:44.235237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:44.102593Z","title":"Benchmarking the spectrum of agent capabilities,","venue":null,"work_id":"3c842c6a-61ef-4d08-adf3-3c0024d7dbe5","year":2022},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.670478Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:c4c50d5f891429270473d9526b3f2c36ef7e2da63797265d48d31a7c0866528f","observation_id":"ecdb15b2-15e1-4c81-895b-f0d6e53f07eb","resolution":{"observed_at":"2026-08-15T22:08:44.218815Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:43.990327Z","title":"Olson, and Elisabeth Andr ´e","venue":null,"work_id":"82807f4f-5985-456e-addc-630158ef6107","year":2023},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.840419Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:0707cba63fd79fd9a0cb4e5d78ac4817e6eb3428fd93f29a92882f121c5d3139","observation_id":"138cac29-75a5-48b0-975f-6265ff0ac59a","resolution":{"observed_at":"2026-08-15T22:08:43.995089Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:43.869192Z","title":"[Kaelbling et al., 1996] Leslie Pack Kaelbling, Michael L Littman, and Andrew W Moore","venue":null,"work_id":"45cae27d-1a93-4b04-9285-b55162c53f22","year":1996},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.845916Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:75dc321dc1a7d062f4bcd96b62f293f26bde84fba5e109c8bdea6e6a3ed10ad5","observation_id":"4953046d-cc8d-48ec-ae44-9e1321ed5155","resolution":{"observed_at":"2026-08-15T22:08:43.874056Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:43.775898Z","title":"Why don’t you do something about it? outlining connec- tions between ai explanations and user actions,","venue":null,"work_id":"7099e386-1943-4bfa-b2b9-b4a4cb9d1848","year":2023},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.856212Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:f5bda7ddfa7cf23d6ef97cb2561b3fd22f90ffa20b5e80203a60f27e5eada2ca","observation_id":"2a97cd61-aa9b-4090-a823-f36449c80426","resolution":{"observed_at":"2026-08-15T22:08:43.780647Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:43.699028Z","title":"Explainable reinforcement learning: A survey and comparative review","venue":null,"work_id":"79572365-cf66-43cb-a3c9-e518243395a5","year":2024},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.935701Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:1de11c49692c0d35776970ab5516f1d60d483d35f3531a8cbbf01548db2ea8ba","observation_id":"6141cb9a-4465-4216-9a36-96d830e3260f","resolution":{"observed_at":"2026-08-15T22:08:43.764909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:43.684425Z","title":"Explanation in artificial intelli- gence: Insights from the social sciences","venue":null,"work_id":"907a2c51-8c61-4437-9f5e-1d77d279c76e","year":2019},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.941107Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:24ecac7b1692f39aa07380e730d95f0b398dbeaaf70c4f63337ebbfc4b93fdbe","observation_id":"68b69e45-a37e-4349-806f-a0f982118327","resolution":{"observed_at":"2026-08-15T22:08:43.689442Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:43.515064Z","title":"Olson, Roli Khanna, Lawrence Neal, Fuxin Li, and Weng-Keen Wong","venue":null,"work_id":"5e0ef30c-ab08-4f20-ba81-dc8b871290a7","year":2021},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.945863Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:49178b44b8b20b90d1816c7365cf9b6a78aa79ca8befd8aefa53a5b934eeac12","observation_id":"b398b613-5ee3-4f0b-ab7d-132af08d4ea7","resolution":{"observed_at":"2026-08-15T22:08:43.587478Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:43.498768Z","title":"Inherently explainable reinforcement learning in natural language","venue":null,"work_id":"3b1f688d-75bd-4a1d-9ae1-1ba7bb1abade","year":2022},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.951335Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:eedaa0c91323f65aed5ee18958dbb7d3a9efd5d6410b6d2cd8c7afe481f02fb9","observation_id":"40710ab0-4933-4e05-b106-2edbeef82f63","resolution":{"observed_at":"2026-08-15T22:08:43.504443Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:43.376980Z","title":"Counterfactual ex- plainer for deep reinforcement learning models using pol- icy distillation","venue":null,"work_id":"b2df3a6d-630d-4732-9b7c-d66b11cebd4a","year":2025},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:43.014137Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:34173b9e21316432cc991970f92c16d891618fa695a707af411a7cdb7ca8b92d","observation_id":"c5efbf91-ad15-44c3-a55b-34f822687d8c","resolution":{"observed_at":"2026-08-15T22:08:43.424716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:43.360563Z","title":"Integrating policy summaries with reward decomposition for explaining reinforcement learn- ing agents","venue":null,"work_id":"fdc0bcf6-2d5f-4f32-aa87-06609e0ad4f2","year":2023},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:43.044946Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:7f36da7e2743307612a7f5e956238d94dedcae3753375d5e05af33aa3e12b669","observation_id":"a54340c7-63c7-4c4d-89c6-c2dc7c05570a","resolution":{"observed_at":"2026-08-15T22:08:43.365998Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:43.217162Z","title":"Bridging the gap: Providing post-hoc sym- bolic explanations for sequential decision-making prob- lems with inscrutable representations","venue":null,"work_id":"58fcfca7-3b31-4412-a2d2-5a2275c0c81a","year":2022},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:43.050780Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:9b476e92ea6e8e6c6622dbcee0d6264f91b9f18f92f5fb538c3171cf7e50f09d","observation_id":"841f3181-13c5-4515-8b51-0ddf8d1d9931","resolution":{"observed_at":"2026-08-15T22:08:43.282012Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:43.201015Z","title":"Contrastive explana- tions for reinforcement learning in terms of expected con- sequences","venue":null,"work_id":"8562fd50-a39d-4f63-95bd-4a2d059de735","year":2018},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:43.055405Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:61820730f39b1746a681faf0f2e4330f8c274b033a6a425cc9f55f86485ff8c7","observation_id":"c07f0ad3-1c98-4082-b559-904866319031","resolution":{"observed_at":"2026-08-15T22:08:43.206753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:43.091909Z","title":"Assessing explainability in reinforcement learning","venue":null,"work_id":"f1a08353-fb8c-4b5e-a79f-0440cdf023fe","year":2021},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:43.060904Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:b56a7beaedfc1afe447a021fa8c47281c61894c0ebfe5fa202210cd1494a6456","observation_id":"9ba0c72d-6bb8-4082-8dbf-227614042c79","resolution":{"observed_at":"2026-08-15T22:08:43.189709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:44.005036Z","title":"Hoffman, Shane T","venue":null,"work_id":"310719c2-a6d3-4804-b9c0-17af9b988f53","year":2023},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":1988,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.793711Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:93b4eddfb4d648e664aeed6dff2efe008454bdc113f3e418ef415dff2096aa38","observation_id":"064225cf-735a-467f-97bb-279fd0144754","resolution":{"observed_at":"2026-08-15T22:08:44.068414Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:44.747212Z","title":"The emerging landscape of explainable automated planning & decision making","venue":null,"work_id":"4074e68f-19e7-43e4-94bb-4c807d0a82c5","year":2021},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":1989,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.429763Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:4379f33a8b8f6be9480d3c1ddda9ad58b39079504eb8b5426eea5ed015e93194","observation_id":"2a63aa48-6dcc-4c77-a249-c44c4695f79f","resolution":{"observed_at":"2026-08-15T22:08:44.763930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:43.819185Z","title":"Explainable reinforcement learning through a causal lens","venue":null,"work_id":"d0388054-16b4-437c-894a-fe65b1236f2a","year":2020},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":1996,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.850862Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:75baef89bd284e7fccf7adb3ca281c3c91e8388818b27d23eb41e6c85d83ed33","observation_id":"e40a5ab3-437b-43cb-9792-3e5c464b6e00","resolution":{"observed_at":"2026-08-15T22:08:43.858172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:44.993514Z","title":"Explaining reinforcement learning agents through counterfactual action outcomes","venue":null,"work_id":"7417958c-d06c-4bf1-a794-6414d7f878a9","year":2024},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.271134Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:2a38439a512c8cbfc5b3fb53ad5bcfbfe26b8d3cb71b26a8cd38004ca73168e9","observation_id":"926c3f12-3b05-48d5-92a7-69be3aab3f77","resolution":{"observed_at":"2026-08-15T22:08:44.998630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:44.450173Z","title":"Diversity is all you need: Learning skills without a reward function,","venue":null,"work_id":"1a75c438-006f-4dff-a926-53fe88c950a9","year":2018},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.552256Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:14d5a77f9c6ee0f784fe85201440f29ea1e168bb919f0fb898c6d20ae303218e","observation_id":"0d2a2448-593c-4070-a0ee-4f73d44b145c","resolution":{"observed_at":"2026-08-15T22:08:44.514200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:44.596961Z","title":"State2explanation: Concept-based explanations to benefit agent learning and user understanding.Advances in Neural Information Processing Systems, 36:67156–67182,","venue":null,"work_id":"95c1beb6-5185-49e7-bd09-1eba0203042d","year":2023},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.441000Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:9b27c45ef3f27d4285dc7ea4ec6633715a1181d4ac165a4c68199db8e2acacee","observation_id":"b64c1344-b4a1-484f-a468-9afa71fce6ac","resolution":{"observed_at":"2026-08-15T22:08:44.601728Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:44.611440Z","title":"Leveraging rationales to improve human task per- formance","venue":null,"work_id":"fe7eb73f-1909-4c63-84d5-ee35803ff4f7","year":2020},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.435569Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:3bc58b7d16000bca21f716810bb9919828a4afda05a63c86cf738add4a99f4cc","observation_id":"babc8fc7-8dab-45b9-84b6-fa924764016c","resolution":{"observed_at":"2026-08-15T22:08:44.685176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:44.087431Z","title":"Development of nasa-tlx (task load index): Re- sults of empirical and theoretical research","venue":null,"work_id":"93d788ec-3d61-4060-8df0-c8581d46691d","year":1988},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.703220Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:347a8c1fc86aad16c2fde62b14175f68999726ce9109c6e04456aad5d4f0225a","observation_id":"827bf23b-d9c7-4398-9aff-827cc85839dc","resolution":{"observed_at":"2026-08-15T22:08:44.092568Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:44.582640Z","title":"Auto- mated rationale generation: a technique for explainable ai and its effects on human perceptions","venue":null,"work_id":"7ad69597-f861-4eb1-b919-a742cdc009f3","year":2019},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.445227Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:f74ece413368673f3d04146b66dcc2ffe14ccc3ae140fd9c1f63c64e231c1ff1","observation_id":"a15d1a93-8d50-4c27-8388-a3372b625e4b","resolution":{"observed_at":"2026-08-15T22:08:44.587522Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:44.789719Z","title":"Efficient Adaptation of Reinforcement Learning Agents to Suddent Environmental Change","venue":null,"work_id":"9db7550a-64e0-4623-9dc9-f47489051685","year":2024},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.317238Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:4d152d56572deacb17b556a0bd80662e850251b50c4480b88bed8254a5a8d034","observation_id":"725593ed-5448-4110-8d0a-35d3663ddc6a","resolution":{"observed_at":"2026-08-15T22:08:44.900731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T22:08:45.008214Z","title":"Agent strategy summarization","venue":null,"work_id":"23cd86f5-f4cd-44b9-859e-c7dd47a62301","year":2018},"citing_paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-15T22:08:42.167217Z"},"links":{"citing_paper":"/paper/2505.08073"},"observation_digest":"sha256:5eb6e12d6207d815b5ff71141aacc7dbfedfde8b0673b981d8925fcdb127e4b2","observation_id":"a4e51d79-3b3d-4e10-b22f-f4df66770970","resolution":{"observed_at":"2026-08-15T22:08:45.120924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.08073","last_updated":"2025-08-18T01:05:06Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-15T22:02:01.213636Z","submitted_at":"2025-05-12T21:18:31Z","title":"Explainable Reinforcement Learning Agents Using World Models"},"reference_resolution":{"displayed":29,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":29},"total_outbound_references":29},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2505.08073."}