{"as_of":"2026-08-10T17:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:be763f0a76699dc47b1361121d7d459770cf3018ce0fb64431bedaefc3e528c5","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T23:26:00.426163Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2607.15459/citation-record","integrity":"/paper/2607.15459/integrity","json":"/paper/2607.15459/citation-record.json","paper":"/paper/2607.15459"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:54.982174Z","title":"Courville, and Marc G","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:54.982174Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:ad52c3d0f40a6221330e0a9860561fb4a7cd952b1a24ae76f97441330b7239f1","observation_id":"673cee85-80f7-4a88-b352-6c1e9bfedeed","resolution":{"observed_at":"2026-08-01T23:25:54.982174Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:55.106059Z","title":"Verifiable reinforcement learning via policy extraction","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:55.106059Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:ea8ce77c052f30f3e88c1526671b41fff4958b8eb47b5b026858152fa2209519","observation_id":"a7b05676-bcbe-4c98-9bb5-6dbb77e7cf37","resolution":{"observed_at":"2026-08-01T23:25:55.106059Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:55.245270Z","title":null,"venue":null,"work_id":null,"year":1984},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:55.245270Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:96f22d29bba84942cd70eab3c44d915c146fa01ed69b15b433d8da3389fcd543","observation_id":"2707512f-c7ef-46b5-8dfc-9e406906bf92","resolution":{"observed_at":"2026-08-01T23:25:55.245270Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:55.353921Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:55.353921Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:46dfd959264c76f7e246b89798a431df76cd424156eb171ca14192e8a82443b6","observation_id":"765d49d4-965f-4599-bb91-ea207323c05f","resolution":{"observed_at":"2026-08-01T23:25:55.353921Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.06009","last_updated":"2021-06-10T19:06:28Z","snapshot_observed_at":"2026-07-06T11:18:09.557612Z","submitted_at":"2021-06-10T19:06:28Z","title":"Synthesising Reinforcement Learning Policies through Set-Valued Inductive Rule Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.06009","snapshot_observed_at":"2026-08-01T23:25:55.420922Z","title":"Jonker, and Ann Nowé","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:55.420922Z"},"links":{"cited_paper":"/paper/2106.06009","citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:ecd543bba03425842375aa8e8ee7666e921a01a9c33a38d2d9cf807476de9fdf","observation_id":"b47f40c2-c64f-43e2-ba65-233b89229d60","resolution":{"observed_at":"2026-08-01T23:25:55.420922Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:55.528673Z","title":"Interpretable and explainable logical policies via neurally guided symbolic abstraction","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:55.528673Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:e2c8049a57cbc52b8d22dc58c25d5a33dc65f7489b942b65376cf9b9deeb9dda","observation_id":"385b5f86-d786-44f6-9cf6-3e387c0d8fc0","resolution":{"observed_at":"2026-08-01T23:25:55.528673Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:55.614617Z","title":"Interpretable concept bottlenecks to align reinforcement learning agents","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:55.614617Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:72835f49326618b0545326d2a31aa588f592387312e32ab3b655d38a04bbd159","observation_id":"5f7eb31e-747e-46af-ab63-5e6df266063d","resolution":{"observed_at":"2026-08-01T23:25:55.614617Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1702.08608","last_updated":"2017-03-02T19:32:10Z","snapshot_observed_at":"2026-08-07T08:20:39.814613Z","submitted_at":"2017-02-28T02:19:20Z","title":"Towards A Rigorous Science of Interpretable Machine Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1702.08608","snapshot_observed_at":"2026-08-01T23:25:55.700229Z","title":"Towards a rigorous science of interpretable machine learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:55.700229Z"},"links":{"cited_paper":"/paper/1702.08608","citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:41928cbb7fb6430f7c0b720d41dcf7ab7b10d194c49bc702506298d1bc8d80ab","observation_id":"82596e3a-40c9-40d9-bb8a-04ef28024737","resolution":{"observed_at":"2026-08-01T23:25:55.700229Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:55.973042Z","title":"Garrido-Merchán and Cristina Puente","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:55.973042Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:513b7eb50da9616e79dfbbda51558186700a0f28a0d8e7130763a40fd606a253","observation_id":"05a5cfea-37b4-4bb7-bf0f-5928d70af529","resolution":{"observed_at":"2026-08-01T23:25:55.973042Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:56.132507Z","title":"Neural logic reinforcement learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:56.132507Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:c43b8b8ea93000291e8e4ada1c7ba90483ee477c438d678c4818b734c1f8d96f","observation_id":"d232cd2e-986a-4f16-97f0-2587814730b4","resolution":{"observed_at":"2026-08-01T23:25:56.132507Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:56.227910Z","title":"Kakade and John Langford","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:56.227910Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:23eab010284d1af75cfd166ff0695c97d9a92c90b319984cfa9b1adef0323edc","observation_id":"d4072afc-0920-4780-9147-ad9493566de3","resolution":{"observed_at":"2026-08-01T23:25:56.227910Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.14956","last_updated":"2024-05-23T18:07:38Z","snapshot_observed_at":"2026-08-03T20:33:04.114191Z","submitted_at":"2024-05-23T18:07:38Z","title":"Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14956","snapshot_observed_at":"2026-08-01T23:25:56.343456Z","title":"Interpretable and editable programmatic tree policies for reinforcement learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:56.343456Z"},"links":{"cited_paper":"/paper/2405.14956","citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:c304397df1f6d7ed61baf7b5840dbee4be1b38c680b25252b36f10c6b805bcb8","observation_id":"e8e864a3-c648-421f-bc60-c0a6106f6ec5","resolution":{"observed_at":"2026-08-01T23:25:56.343456Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:56.442238Z","title":"Learning finite state representations of recurrent policy networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:56.442238Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:c763eb04fda2d0a89e88bec24a47cedcadc5c7b5d34e6dd837e8b3c502ddc2e5","observation_id":"2c949210-8412-4aa4-8402-e3bd0dabe98a","resolution":{"observed_at":"2026-08-01T23:25:56.442238Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:56.542613Z","title":"Petersen, Sookyung Kim, Cl \\' a udio P","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:56.542613Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:2427a6f2d9c246caae19a59fd49850908323f954ba772283e9004d4487cfca04","observation_id":"4e66db30-8122-4a47-b3c1-7f90ae472ff5","resolution":{"observed_at":"2026-08-01T23:25:56.542613Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:56.679106Z","title":"Toward interpretable deep reinforcement learning with linear model U - T rees","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:56.679106Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:d8bcbe0972cf57fe0fcc934df6817b1bd5c64c39e9805ba9ed49c55844e87783","observation_id":"ad88d6ec-33b0-417c-a8ea-7897a2dc695c","resolution":{"observed_at":"2026-08-01T23:25:56.679106Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:57.076450Z","title":"Gordon, and Drew Bagnell","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:57.076450Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:37a17d7a945a19b5e505310740ecc7ad2ee2c796ef1d69d647ed318441e5f795","observation_id":"49117ef8-d842-49ce-9b88-501c09c8d641","resolution":{"observed_at":"2026-08-01T23:25:57.076450Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-08-01T23:25:57.175985Z","title":"Proximal policy optimization algorithms","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:57.175985Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:efd62e4d4260b5a9b7f840a7296b4e0e9a9a84aaf8749dba972a6f13adb7cb9c","observation_id":"e5fdd9d6-cb2f-4ed7-a79e-0be6c70361e5","resolution":{"observed_at":"2026-08-01T23:25:57.175985Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.06107","last_updated":"2024-06-10T08:46:49Z","snapshot_observed_at":"2026-08-09T23:38:47.719869Z","submitted_at":"2024-06-10T08:46:49Z","title":"EXPIL: Explanatory Predicate Invention for Learning in Games","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.06107","snapshot_observed_at":"2026-08-01T23:25:57.278460Z","title":"EXPIL : Explanatory predicate invention for learning in games","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:57.278460Z"},"links":{"cited_paper":"/paper/2406.06107","citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:b2003c0333e293bb457793af46a6495601b83dd44e4f7f934b6fc92e00634350","observation_id":"073e7dd7-579a-4b48-a778-21fb228342e4","resolution":{"observed_at":"2026-08-01T23:25:57.278460Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:57.346561Z","title":"B lend RL : A framework for merging symbolic and neural policy learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:57.346561Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:9f065636e05c6dbd4077d06b4e036717280481d1db3a20e8ea0bac03668c05f1","observation_id":"1fa479bb-5f13-4de0-86ff-caa12b054a41","resolution":{"observed_at":"2026-08-01T23:25:57.346561Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.17032","last_updated":"2025-11-02T13:42:19Z","snapshot_observed_at":"2026-07-06T18:51:06.750136Z","submitted_at":"2024-07-24T06:35:05Z","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.17032","snapshot_observed_at":"2026-08-01T23:25:57.400121Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:57.400121Z"},"links":{"cited_paper":"/paper/2407.17032","citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:95e7b1b54b62d8a43e8e4191c2570631c896c375d0994d79f3d6167e719d4a5e","observation_id":"b4785357-4054-4f39-b40a-7edf56e9a0a2","resolution":{"observed_at":"2026-08-01T23:25:57.400121Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:57.448602Z","title":"Programmatically interpretable reinforcement learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:57.448602Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:72b23f07317fb8fd85302b3a5bf6d6300faa79f1e75be8495c8ff93728bff8c2","observation_id":"2e62338d-4c5e-4122-b828-dbf9bc99bf19","resolution":{"observed_at":"2026-08-01T23:25:57.448602Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:57.554458Z","title":"Imitation-projected programmatic reinforcement learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:57.554458Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:c0752d2f6275651e968327e98c6ddea372a7ff5a10efc23b9f5cdec5b58aa314","observation_id":"03412034-877d-4252-83bd-e25057355f8c","resolution":{"observed_at":"2026-08-01T23:25:57.554458Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:57.773262Z","title":"Kakade and John Langford , editor =","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:57.773262Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:f3e1935089a0be54d9256a491ae64f62c5fdb742363bd86cb0959156b1a82636","observation_id":"06a8322c-dab3-4e91-a0e3-982ec7f80bd3","resolution":{"observed_at":"2026-08-01T23:25:57.773262Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:57.866516Z","title":"Verifiable Reinforcement Learning via Policy Extraction , booktitle =","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:57.866516Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:7444252852a45406b3cdfd1e8800765d555a1becc15677f7ebb224ecb92b0547","observation_id":"383bf49f-201c-4b57-8057-1dd60b1974b1","resolution":{"observed_at":"2026-08-01T23:25:57.866516Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:57.977354Z","title":"Programmatically Interpretable Reinforcement Learning , booktitle =","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:57.977354Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:a8f1525e3a9300da2f659baf44be6ad2c8bdb7a74af891bacee18cc6a734049f","observation_id":"a396459d-8081-49c3-87f9-956e830ecebb","resolution":{"observed_at":"2026-08-01T23:25:57.977354Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:58.093001Z","title":"Imitation-Projected Programmatic Reinforcement Learning , booktitle =","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:58.093001Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:4731b460f1737b797565598d51431e6f4b651b3e2d347dd2ed95486ddd373966","observation_id":"26049bc2-80cf-4a72-a1a5-863ed9f95268","resolution":{"observed_at":"2026-08-01T23:25:58.093001Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:58.202466Z","title":"Neural Logic Reinforcement Learning , booktitle =","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:58.202466Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:4c355fa7ceda4268b8da232c15bae04edd89c4a3a964fb4da861375d02108d4e","observation_id":"60073971-b706-47eb-ae24-dfaaa1cfce64","resolution":{"observed_at":"2026-08-01T23:25:58.202466Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:58.312244Z","title":"Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction , booktitle =","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:58.312244Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:d44e6807d7a1d61f4c17bbfb80eebbe2fbeeaf459cdf701812b37a093518248b","observation_id":"30b036a1-7b60-41ea-af5a-9cb578e0f3ee","resolution":{"observed_at":"2026-08-01T23:25:58.312244Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:58.466159Z","title":"The Thirteenth International Conference on Learning Representations,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:58.466159Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:6cefe69eb038c396a116bde39b3e3799a69c5ab30e0e9479088c40e74187f855","observation_id":"30263fdd-78a2-4050-806d-7cc19c8be0c8","resolution":{"observed_at":"2026-08-01T23:25:58.466159Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:58.612636Z","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents , booktitle =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:58.612636Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:35cab321c8cf773fc85474d20feab8beb8094d6c7637007c025b0e2b3130f7d0","observation_id":"4e2a84e7-3495-445e-99f2-4ca2ab645dfa","resolution":{"observed_at":"2026-08-01T23:25:58.612636Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:58.736051Z","title":"Petersen and Sookyung Kim and Cl","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:58.736051Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:cde6e51ef560abf00be96975a644cffde0cc5cf36eb00d2933a646608a9319a9","observation_id":"f0a0faef-5e95-4c2a-a53f-73be27f44917","resolution":{"observed_at":"2026-08-01T23:25:58.736051Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:58.871100Z","title":"2024 , url =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:58.871100Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:703d81a1c0440e3fa6e3b30907051e01346e583a59eee776264d25d2dffdc62b","observation_id":"a487b52a-1981-46b8-87fb-c6041d315f29","resolution":{"observed_at":"2026-08-01T23:25:58.871100Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:59.021678Z","title":"Courville and Marc G","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:59.021678Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:b032f7f5c67311e3f9baafa5c0bc0805921e2829cb897c755b690c292285225e","observation_id":"92fa4c3a-5121-48fd-b1c1-150f659a341b","resolution":{"observed_at":"2026-08-01T23:25:59.021678Z","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":"10.1007/bf00117105","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Ross Quinlan , title =","venue":"Machine Learning","work_id":"35c0a928-5335-4acf-bfe8-77d9c639b7d0","year":1990},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:59.146726Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:24e59b399d03a128700dbd027b1e4f5830fa2298aaf54505db4d56e93891db07","observation_id":"10e9eb86-925f-4427-864b-516c423e32c8","resolution":{"observed_at":"2026-08-01T23:28:29.335729Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1023/a:1007694015589","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"Machine Learning","work_id":"ff859c9a-9c83-42c7-a72c-368dde717f7d","year":2001},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:59.242904Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:7b5e4f0f2a23a8bfe80cd1626f2911875cf3a560cb402008977035c861ef2150","observation_id":"e569c93a-c744-4e75-89c1-dcca5f3993bf","resolution":{"observed_at":"2026-08-01T23:28:29.588148Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-01T23:25:59.336648Z","title":"A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning , booktitle =","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:59.336648Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:b6e04ad0686f9b2c5187f5c2037afc8a9feadd0426443b33f01e3bf6047ad3c9","observation_id":"71785031-4105-4c7a-8ccf-4b4982a39658","resolution":{"observed_at":"2026-08-01T23:25:59.336648Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:59.500851Z","title":"7th International Conference on Learning Representations,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:59.500851Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:ba0a562474e145f5f38117da19831f71a6b8469742a50feaff665412951eec3f","observation_id":"a65ce775-2b2f-4f8b-a0cb-a054e0d7cdb6","resolution":{"observed_at":"2026-08-01T23:25:59.500851Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:59.637679Z","title":"Theory Pract","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:59.637679Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:830a2c7904465157a42fcb07abdc1b59e0659f46707be06bdf3e3fd8ed201f1e","observation_id":"7ef71411-43df-436e-a273-8dc8eabdfc9a","resolution":{"observed_at":"2026-08-01T23:25:59.637679Z","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":"10.1007/978-3-030-10928-8","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Toward Interpretable Deep Reinforcement Learning with Linear Model","venue":"Lecture notes in computer science","work_id":"141fe012-39cd-49ef-9f9b-c7c17a12164a","year":2018},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:59.717096Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:f22f3dfe27cb093b71cb00473e086d5ae315b4d93fbe1064f4e9c30a5681634c","observation_id":"2c60be33-99dc-4d24-a92d-eb7d38c57c3e","resolution":{"observed_at":"2026-08-01T23:28:28.724163Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-01T23:25:59.796264Z","title":null,"venue":null,"work_id":null,"year":1984},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:59.796264Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:3633aa092aac56f7e2e8ad8fff7f28a22fb833588b213b57f7063fc91e262a65","observation_id":"cb821429-8fb6-40bf-8a13-4724f3304aa3","resolution":{"observed_at":"2026-08-01T23:25:59.796264Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:59.861800Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:59.861800Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:88e683f6e1a5cff4173e518d6476e3c1957c06995e66ae99f413893d8f7972ed","observation_id":"5fe88b83-3c0b-4e53-838f-894facf9ba18","resolution":{"observed_at":"2026-08-01T23:25:59.861800Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:59.922798Z","title":"2017 , eprint =","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:59.922798Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:2d394c5f0b03aa7be8c641adce780212a659428f5c9876f20ae2640061df86d4","observation_id":"a8796f42-b7f1-4b49-a341-97c538fc5af1","resolution":{"observed_at":"2026-08-01T23:25:59.922798Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:25:59.991915Z","title":"Jonker and Ann Nowé , title =","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-01T23:25:59.991915Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:9f23e9259998c1f3d09883f2f4083d5f42987b47b936f40102e8426e4e108138","observation_id":"c66bcd36-7546-44ec-92c3-5a1144398f71","resolution":{"observed_at":"2026-08-01T23:25:59.991915Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:26:00.082561Z","title":"2024 , eprint =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-01T23:26:00.082561Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:9dfe17a5dbade865b2b1694de81371e3561b6f7660ba576125c392beecc5fa5e","observation_id":"8617782b-4dae-44c6-9d5e-c2cfa4bd624c","resolution":{"observed_at":"2026-08-01T23:26:00.082561Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:26:00.174154Z","title":"2024 , eprint =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-01T23:26:00.174154Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:9e973a0a273d14d9bdf371b0f6dc9b656d3b99682ae6e9ffa837c0c85c4bfe5b","observation_id":"5030e046-d50a-4226-b4fd-50afcf72c8b7","resolution":{"observed_at":"2026-08-01T23:26:00.174154Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:26:00.256065Z","title":"Garrido-Merchán and Cristina Puente , title =","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-01T23:26:00.256065Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:f0973f361b115b0a09bae22f2fa61ff00ec9bd4e757f524e9c8954e9d2880d7b","observation_id":"ecd95ef5-6dda-443e-84fb-78b1801785df","resolution":{"observed_at":"2026-08-01T23:26:00.256065Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:26:00.337919Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-01T23:26:00.337919Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:c32cb6853dad47904ab9965931c58f4c2ed147e6511e23a10d1b9c9cd0dfcc2e","observation_id":"e16022cf-4706-497d-bcf3-42dd60b54ffb","resolution":{"observed_at":"2026-08-01T23:26:00.337919Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T23:26:00.426163Z","title":"2017 , eprint =","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-01T23:26:00.426163Z"},"links":{"citing_paper":"/paper/2607.15459"},"observation_digest":"sha256:b2bf4a46113cab719adb7bfeb9d35c4c7f9878e989f1e9d9a7567077b009aed3","observation_id":"6bb04b70-941a-4afc-b0d4-464a09c4174f","resolution":{"observed_at":"2026-08-01T23:26:00.426163Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.15459","last_updated":"2026-07-20T09:36:34Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-01T23:25:52.878240Z","submitted_at":"2026-07-16T21:10:27Z","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":45,"verified_exact":3,"verified_fuzzy":0},"total_outbound_references":48},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2607.15459."}