{"as_of":"2026-08-24T04:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:875e1cb95eba65b170057c82c51c15aa8372b7e129f79d18771dbaf465936a04","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":"2026-08-23T06:30:58.430688+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":"2026-08-11T22:12:10.594853Z","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":"2026-08-06T16:34:25.815039Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2111.13485","last_updated":"2022-03-17T07:01:28Z","snapshot_observed_at":"2026-08-16T17:39:08.887455Z","submitted_at":"2021-11-26T13:23:36Z","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.13485","snapshot_observed_at":"2026-08-11T22:12:10.594853Z","title":"Learning long- term reward redistribution via randomized return decom- position,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.03800","last_updated":"2024-12-05T01:42:13Z","snapshot_observed_at":"2026-08-15T01:01:26.542685Z","submitted_at":"2024-12-05T01:42:13Z","title":"ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T22:12:10.594853Z"},"links":{"cited_paper":"/paper/2111.13485","citing_paper":"/paper/2412.03800"},"observation_digest":"sha256:4deb39a32b5717137f701cd5ec8934eb3e2c35f517c18991e7e6df5fefb192d4","observation_id":"68be9271-8664-452c-8f4e-0b90f90c6cc5","resolution":{"observed_at":"2026-08-11T22:12:10.594853Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.13485","last_updated":"2022-03-17T07:01:28Z","snapshot_observed_at":"2026-08-16T17:39:08.887455Z","submitted_at":"2021-11-26T13:23:36Z","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.13485","snapshot_observed_at":"2026-08-11T12:00:51.130093Z","title":"Learning long-term reward redistribution via randomized return decomposition","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.14779","last_updated":"2024-12-19T12:05:13Z","snapshot_observed_at":"2026-08-12T16:13:13.246603Z","submitted_at":"2024-12-19T12:05:13Z","title":"Agent-Temporal Credit Assignment for Optimal Policy Preservation in Sparse Multi-Agent Reinforcement Learning","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-11T12:00:51.130093Z"},"links":{"cited_paper":"/paper/2111.13485","citing_paper":"/paper/2412.14779"},"observation_digest":"sha256:e37eff54709e32959bcf7ca1bc51133a121bc6732230bc9a79c8e33b7f13c63d","observation_id":"d2d5f467-4e05-4f11-be85-917b19366878","resolution":{"observed_at":"2026-08-11T12:00:51.130093Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.13485","last_updated":"2022-03-17T07:01:28Z","snapshot_observed_at":"2026-08-16T17:39:08.887455Z","submitted_at":"2021-11-26T13:23:36Z","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition","version":2},"cited_work":{"arxiv_id":"2111.13485","doi":null,"metadata_source":"pith","pith_arxiv_id":"2111.13485","snapshot_observed_at":"2026-08-06T16:34:25.815039Z","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition","venue":"cs.LG","work_id":"00aa9170-bef2-4714-a594-8ff23db955d3","year":2021},"citing_paper":{"arxiv_id":"2507.13158","last_updated":"2025-07-17T14:22:24Z","snapshot_observed_at":"2026-08-15T15:23:09.345799Z","submitted_at":"2025-07-17T14:22:24Z","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T16:34:25.163198Z"},"links":{"cited_paper":"/paper/2111.13485","citing_paper":"/paper/2507.13158"},"observation_digest":"sha256:56eb7ecc94e77cf09a94078ec784732acc62d8d9a836d8543388bb94acce33fa","observation_id":"a2502d7e-e280-42d3-b361-6ba68091870a","resolution":{"observed_at":"2026-08-06T16:34:25.818920Z","resolver_source":"local_arxiv","status":"verified_exact"},"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"}}],"links":{"evidence":"/evidence","html":"/paper/2111.13485/citation-record","integrity":"/paper/2111.13485/integrity","json":"/paper/2111.13485/citation-record.json","paper":"/paper/2111.13485"},"outbound":[],"paper":{"arxiv_id":"2111.13485","last_updated":"2022-03-17T07:01:28Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T17:39:08.887455Z","submitted_at":"2021-11-26T13:23:36Z","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition"},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 24 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2111.13485."}