{"as_of":"2026-08-21T13:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:df1d16e4c1bc8d43c2ea49e54f2c18725ef3923db96585cf567c89e49c6008e8","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T04:49:16.542411Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T21:17:45.605359Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2205.15400","last_updated":"2022-05-30T19:48:52Z","snapshot_observed_at":"2026-08-20T08:34:22.127282Z","submitted_at":"2022-05-30T19:48:52Z","title":"Designing Rewards for Fast Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.15400","snapshot_observed_at":"2026-08-11T23:41:05.150853Z","title":"Designing rewards for fast learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.02316","last_updated":"2024-12-03T09:32:02Z","snapshot_observed_at":"2026-08-19T18:19:25.072232Z","submitted_at":"2024-12-03T09:32:02Z","title":"Optimizing Plastic Waste Collection in Water Bodies Using Heterogeneous Autonomous Surface Vehicles with Deep Reinforcement Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T23:41:05.150853Z"},"links":{"cited_paper":"/paper/2205.15400","citing_paper":"/paper/2412.02316"},"observation_digest":"sha256:7f1675a66c197e2404ceeb7a8acfc1b051bf02530ddda91da4c6b89d4251003e","observation_id":"acdb7612-10c1-4f0b-b002-a87c6acd77e5","resolution":{"observed_at":"2026-08-11T23:41:05.150853Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.15400","last_updated":"2022-05-30T19:48:52Z","snapshot_observed_at":"2026-08-20T08:34:22.127282Z","submitted_at":"2022-05-30T19:48:52Z","title":"Designing Rewards for Fast Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.15400","snapshot_observed_at":"2026-08-16T04:49:16.542411Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07832","last_updated":"2025-05-01T11:02:55Z","snapshot_observed_at":"2026-08-16T10:28:58.340005Z","submitted_at":"2025-05-01T11:02:55Z","title":"A General Approach of Automated Environment Design for Learning the Optimal Power Flow","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T04:49:16.542411Z"},"links":{"cited_paper":"/paper/2205.15400","citing_paper":"/paper/2505.07832"},"observation_digest":"sha256:db192cc8e242eb5def0e9053541002b07303ebf1c451c54db173e4a446ff4e10","observation_id":"4eadafe7-d748-4008-a0d6-8318cd56f562","resolution":{"observed_at":"2026-08-16T04:49:16.542411Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.15400","last_updated":"2022-05-30T19:48:52Z","snapshot_observed_at":"2026-08-20T08:34:22.127282Z","submitted_at":"2022-05-30T19:48:52Z","title":"Designing Rewards for Fast Learning","version":1},"cited_work":{"arxiv_id":"2205.15400","doi":null,"metadata_source":"pith","pith_arxiv_id":"2205.15400","snapshot_observed_at":"2026-08-06T21:17:45.605359Z","title":"Designing Rewards for Fast Learning","venue":"cs.LG","work_id":"4e5fa6b2-7232-43c8-af1a-c28ba39cdccc","year":2022},"citing_paper":{"arxiv_id":"2507.00611","last_updated":"2025-07-01T09:43:57Z","snapshot_observed_at":"2026-08-16T08:07:01.402551Z","submitted_at":"2025-07-01T09:43:57Z","title":"Residual Reward Models for Preference-based Reinforcement Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T21:17:35.266098Z"},"links":{"cited_paper":"/paper/2205.15400","citing_paper":"/paper/2507.00611"},"observation_digest":"sha256:932292a6f76e5129d2aeb20ce4b436e513567f16afb6c9c843f2c232920f991c","observation_id":"f88d3ae8-ed99-4203-8d96-2eefa5134337","resolution":{"observed_at":"2026-08-06T21:17:45.664056Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2205.15400/citation-record","integrity":"/paper/2205.15400/integrity","json":"/paper/2205.15400/citation-record.json","paper":"/paper/2205.15400"},"outbound":[],"paper":{"arxiv_id":"2205.15400","last_updated":"2022-05-30T19:48:52Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-20T08:34:22.127282Z","submitted_at":"2022-05-30T19:48:52Z","title":"Designing Rewards for Fast Learning"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2205.15400."}