{"as_of":"2026-08-17T15:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a5eb7fa6b03be62e635c47c1eb72583506cc8a8b78217ae481e5b158779c6bb3","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:21:33.953684Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-18T06:38:36.797784Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2009.14108","last_updated":"2022-06-28T18:39:18Z","snapshot_observed_at":"2026-08-16T18:04:33.227548Z","submitted_at":"2020-09-29T15:48:02Z","title":"Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution","version":2},"cited_work":{"arxiv_id":"2009.14108","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2009.14108","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2009.14108 , year=","venue":null,"work_id":"71a7298d-d88b-43c5-8a66-d174228ee5c7","year":2009},"citing_paper":{"arxiv_id":"2408.00724","last_updated":"2025-03-03T07:53:32Z","snapshot_observed_at":"2026-08-13T03:06:10.986532Z","submitted_at":"2024-08-01T17:16:04Z","title":"Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models","version":3},"reference_index":94,"source":"arxiv_source","source_observed_at":"2026-05-18T06:38:36.517935Z"},"links":{"cited_paper":"/paper/2009.14108","citing_paper":"/paper/2408.00724"},"observation_digest":"sha256:1cbfe341b8f7b5020371e24e2a40df3f66aa3ab151ba66a22adb6a9d716af1ad","observation_id":"b84fefce-b3fa-4fd3-bc26-0cfb6ff99226","resolution":{"observed_at":"2026-05-18T06:38:36.800745Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2009.14108","last_updated":"2022-06-28T18:39:18Z","snapshot_observed_at":"2026-08-16T18:04:33.227548Z","submitted_at":"2020-09-29T15:48:02Z","title":"Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.14108","snapshot_observed_at":"2026-08-11T15:22:54.412698Z","title":"In ICML, 17156–17185","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.11120","last_updated":"2025-01-09T11:39:32Z","snapshot_observed_at":"2026-08-16T18:07:58.075253Z","submitted_at":"2024-12-15T08:51:14Z","title":"Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-11T15:22:54.412698Z"},"links":{"cited_paper":"/paper/2009.14108","citing_paper":"/paper/2412.11120"},"observation_digest":"sha256:9a273e92148784e96b08a1385089fa242a5cefb9ada138bcd13dbb48d6222612","observation_id":"27c941b5-3961-43af-ad2f-d36d6cc64edd","resolution":{"observed_at":"2026-08-11T15:22:54.412698Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.14108","last_updated":"2022-06-28T18:39:18Z","snapshot_observed_at":"2026-08-16T18:04:33.227548Z","submitted_at":"2020-09-29T15:48:02Z","title":"Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.14108","snapshot_observed_at":"2026-08-11T12:00:51.115869Z","title":"Align-rudder: Learning from few demonstrations by reward redistribution","venue":null,"work_id":null,"year":2009},"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":27,"source":"arxiv_source","source_observed_at":"2026-08-11T12:00:51.115869Z"},"links":{"cited_paper":"/paper/2009.14108","citing_paper":"/paper/2412.14779"},"observation_digest":"sha256:a9a6566dcfb330708e75d72790862cc605dca1e0739ecc2774d7839b51981f83","observation_id":"a2e3590e-f44c-4377-8dc7-1f9549d47f3c","resolution":{"observed_at":"2026-08-11T12:00:51.115869Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.14108","last_updated":"2022-06-28T18:39:18Z","snapshot_observed_at":"2026-08-16T18:04:33.227548Z","submitted_at":"2020-09-29T15:48:02Z","title":"Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.14108","snapshot_observed_at":"2026-08-15T18:21:33.953684Z","title":"arXiv preprint arXiv:2009.14108 , year=","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2608.13026","last_updated":"2026-08-13T09:54:14Z","snapshot_observed_at":"2026-08-17T10:59:38.876278Z","submitted_at":"2026-08-13T09:54:14Z","title":"Temporal GRPO: Beyond Trajectory-Level Credit in Vision-Language-Action Reinforcement Learning","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-15T18:21:33.953684Z"},"links":{"cited_paper":"/paper/2009.14108","citing_paper":"/paper/2608.13026"},"observation_digest":"sha256:052a0193288b3c0eafa178e12b21167d62ea845f29b0417ed71e94146af8eb5c","observation_id":"d60282f9-1343-48c8-9ff0-4e97a6bd045a","resolution":{"observed_at":"2026-08-15T18:21:33.953684Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2009.14108/citation-record","integrity":"/paper/2009.14108/integrity","json":"/paper/2009.14108/citation-record.json","paper":"/paper/2009.14108"},"outbound":[],"paper":{"arxiv_id":"2009.14108","last_updated":"2022-06-28T18:39:18Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T18:04:33.227548Z","submitted_at":"2020-09-29T15:48:02Z","title":"Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2009.14108."}