{"as_of":"2026-08-20T00:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6ef14f7c084c9b183452cd5e02b1d867898e744af34c69a824c4a2dea9b91a5a","coverage":[{"denominator":9,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":9,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T23:46:50.244281Z","state":"measured"},{"denominator":9,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":9,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+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/2505.03947/citation-record","integrity":"/paper/2505.03947/integrity","json":"/paper/2505.03947/citation-record.json","paper":"/paper/2505.03947"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:46:50.201092Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.03947","last_updated":"2025-05-06T19:51:41Z","snapshot_observed_at":"2026-08-18T04:56:10.474163Z","submitted_at":"2025-05-06T19:51:41Z","title":"Frog Soup: Zero-Shot, In-Context, and Sample-Efficient Frogger Agents","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-15T23:46:50.201092Z"},"links":{"citing_paper":"/paper/2505.03947"},"observation_digest":"sha256:bb592403bd46a6e94e133ea19b2010ac668e88f6375c60859c5657a387fd4d6b","observation_id":"265152b9-2b55-40b2-bc81-06dd70d36774","resolution":{"observed_at":"2026-08-15T23:46:50.201092Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.08649","last_updated":"2024-02-27T17:34:43Z","snapshot_observed_at":"2026-08-18T04:56:45.117062Z","submitted_at":"2023-06-14T17:28:46Z","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.08649","snapshot_observed_at":"2026-08-15T23:46:50.207958Z","title":"Ocatari: Object-centric atari 2600 reinforcement learning environments, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.03947","last_updated":"2025-05-06T19:51:41Z","snapshot_observed_at":"2026-08-18T04:56:10.474163Z","submitted_at":"2025-05-06T19:51:41Z","title":"Frog Soup: Zero-Shot, In-Context, and Sample-Efficient Frogger Agents","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-15T23:46:50.207958Z"},"links":{"cited_paper":"/paper/2306.08649","citing_paper":"/paper/2505.03947"},"observation_digest":"sha256:ab09aaca4a509623cc9c6a676c5d447b1095b10ed5236290f3ef2f3be92e414c","observation_id":"98389204-7f83-475b-a274-5b58d17cf2e7","resolution":{"observed_at":"2026-08-15T23:46:50.207958Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1704.03732","last_updated":"2017-11-22T21:18:31Z","snapshot_observed_at":"2026-08-14T22:29:17.225176Z","submitted_at":"2017-04-12T12:44:37Z","title":"Deep Q-learning from Demonstrations","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.03732","snapshot_observed_at":"2026-08-15T23:46:50.213634Z","title":"Z., and Gruslys, A","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.03947","last_updated":"2025-05-06T19:51:41Z","snapshot_observed_at":"2026-08-18T04:56:10.474163Z","submitted_at":"2025-05-06T19:51:41Z","title":"Frog Soup: Zero-Shot, In-Context, and Sample-Efficient Frogger Agents","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-15T23:46:50.213634Z"},"links":{"cited_paper":"/paper/1704.03732","citing_paper":"/paper/2505.03947"},"observation_digest":"sha256:317271d89ca1f1d8dffe73bd5f1dcc42fce95c2c5f69bb307de8f9a15e89ba8e","observation_id":"e73bcb39-850c-4999-84cb-964b3b7d320b","resolution":{"observed_at":"2026-08-15T23:46:50.213634Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1709.06009","last_updated":"2017-12-01T03:18:14Z","snapshot_observed_at":"2026-08-14T20:32:08.654033Z","submitted_at":"2017-09-18T15:32:57Z","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1709.06009","snapshot_observed_at":"2026-08-15T23:46:50.218821Z","title":"C., Bellemare, M","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.03947","last_updated":"2025-05-06T19:51:41Z","snapshot_observed_at":"2026-08-18T04:56:10.474163Z","submitted_at":"2025-05-06T19:51:41Z","title":"Frog Soup: Zero-Shot, In-Context, and Sample-Efficient Frogger Agents","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-15T23:46:50.218821Z"},"links":{"cited_paper":"/paper/1709.06009","citing_paper":"/paper/2505.03947"},"observation_digest":"sha256:4baae0568b8e39dc7a46c301227f9f418802436ca01d805a467143cdcbc9a474","observation_id":"57aa62d2-2535-4d4d-9e73-1a89890a2108","resolution":{"observed_at":"2026-08-15T23:46:50.218821Z","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":"2026-08-15T23:46:50.224295Z","title":"Playing atari with deep reinforcement learning, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.03947","last_updated":"2025-05-06T19:51:41Z","snapshot_observed_at":"2026-08-18T04:56:10.474163Z","submitted_at":"2025-05-06T19:51:41Z","title":"Frog Soup: Zero-Shot, In-Context, and Sample-Efficient Frogger Agents","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-15T23:46:50.224295Z"},"links":{"citing_paper":"/paper/2505.03947"},"observation_digest":"sha256:724e42196079a7816c727c28ac24cade4cbf49af4c3368f1f79c863d27450359","observation_id":"b8feae48-f824-47fb-8470-4738f9d4bf0c","resolution":{"observed_at":"2026-08-15T23:46:50.224295Z","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":"2026-08-15T23:46:50.229215Z","title":"A., Veness, J., Bellemare, M","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.03947","last_updated":"2025-05-06T19:51:41Z","snapshot_observed_at":"2026-08-18T04:56:10.474163Z","submitted_at":"2025-05-06T19:51:41Z","title":"Frog Soup: Zero-Shot, In-Context, and Sample-Efficient Frogger Agents","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-15T23:46:50.229215Z"},"links":{"citing_paper":"/paper/2505.03947"},"observation_digest":"sha256:74f8ff307bc5492c00850b2965b1c92d8dbed2dfe90f47f78a55426e4bd39d7e","observation_id":"d99f0ac2-115e-47d9-b617-63d7fabd1180","resolution":{"observed_at":"2026-08-15T23:46:50.229215Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1511.05952","last_updated":"2016-02-25T17:55:31Z","snapshot_observed_at":"2026-08-15T17:33:32.559096Z","submitted_at":"2015-11-18T20:54:44Z","title":"Prioritized Experience Replay","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.05952","snapshot_observed_at":"2026-08-15T23:46:50.233906Z","title":"Prioritized experience replay, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.03947","last_updated":"2025-05-06T19:51:41Z","snapshot_observed_at":"2026-08-18T04:56:10.474163Z","submitted_at":"2025-05-06T19:51:41Z","title":"Frog Soup: Zero-Shot, In-Context, and Sample-Efficient Frogger Agents","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-15T23:46:50.233906Z"},"links":{"cited_paper":"/paper/1511.05952","citing_paper":"/paper/2505.03947"},"observation_digest":"sha256:7b73ae94a585cd70a3915d3b66c9468a3d05aeb4c1fd92fcd719c7d0ca1ad030","observation_id":"a97a5ffd-180f-4870-8abb-feba799e6db8","resolution":{"observed_at":"2026-08-15T23:46:50.233906Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.11366","last_updated":"2023-10-10T05:21:45Z","snapshot_observed_at":"2026-08-17T19:15:32.679249Z","submitted_at":"2023-03-20T18:08:50Z","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.11366","snapshot_observed_at":"2026-08-15T23:46:50.239455Z","title":"Reflexion: Language agents with verbal reinforcement learning, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.03947","last_updated":"2025-05-06T19:51:41Z","snapshot_observed_at":"2026-08-18T04:56:10.474163Z","submitted_at":"2025-05-06T19:51:41Z","title":"Frog Soup: Zero-Shot, In-Context, and Sample-Efficient Frogger Agents","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-15T23:46:50.239455Z"},"links":{"cited_paper":"/paper/2303.11366","citing_paper":"/paper/2505.03947"},"observation_digest":"sha256:2d61b99ae8480bb861b3c812886cd082165725295e183ecca21add01c751127e","observation_id":"042c2837-21b8-4c07-9522-f58b1af7985e","resolution":{"observed_at":"2026-08-15T23:46:50.239455Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15950","last_updated":"2024-12-02T03:48:43Z","snapshot_observed_at":"2026-08-16T13:23:09.014713Z","submitted_at":"2024-08-28T17:08:56Z","title":"Atari-GPT: Benchmarking Multimodal Large Language Models as Low-Level Policies in Atari Games","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.15950","snapshot_observed_at":"2026-08-15T23:46:50.244281Z","title":"R., White, D., Sunbeam, M., and Goecks, V","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.03947","last_updated":"2025-05-06T19:51:41Z","snapshot_observed_at":"2026-08-18T04:56:10.474163Z","submitted_at":"2025-05-06T19:51:41Z","title":"Frog Soup: Zero-Shot, In-Context, and Sample-Efficient Frogger Agents","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-15T23:46:50.244281Z"},"links":{"cited_paper":"/paper/2408.15950","citing_paper":"/paper/2505.03947"},"observation_digest":"sha256:05ee44f6f768931e536540760c89feb683a55d2127d8c2e4382aac7ea80f467c","observation_id":"204020c0-9bdd-4039-acf8-87e0e137b31c","resolution":{"observed_at":"2026-08-15T23:46:50.244281Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.03947","last_updated":"2025-05-06T19:51:41Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-18T04:56:10.474163Z","submitted_at":"2025-05-06T19:51:41Z","title":"Frog Soup: Zero-Shot, In-Context, and Sample-Efficient Frogger Agents"},"reference_resolution":{"displayed":9,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":9},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 9 of 9 outbound references and 0 inbound Pith citation observations for arXiv:2505.03947."}