{"as_of":"2026-08-08T11:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4ba29498c928beffcffd31e7fbb722aa521f4b6fe4bc38e52ec8776fff95d6ff","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T14:49:31.040589Z","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":"2026-05-22T21:52:10.203651Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.13410","last_updated":"2024-11-20T15:52:03Z","snapshot_observed_at":"2026-07-06T19:53:12.584883Z","submitted_at":"2024-11-20T15:52:03Z","title":"A Survey On Enhancing Reinforcement Learning in Complex Environments: Insights from Human and LLM Feedback","version":1},"cited_work":{"arxiv_id":"2411.13410","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.13410","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A survey on enhancing reinforcement learning in complex environments: Insights from human and llm feedback","venue":null,"work_id":"69543d3f-313a-48de-a7f3-36676f728ed5","year":2024},"citing_paper":{"arxiv_id":"2503.21460","last_updated":"2025-03-27T12:50:17Z","snapshot_observed_at":"2026-07-06T20:59:35.694800Z","submitted_at":"2025-03-27T12:50:17Z","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","version":1},"reference_index":112,"source":"pdf_text","source_observed_at":"2026-05-22T21:51:34.309870Z"},"links":{"cited_paper":"/paper/2411.13410","citing_paper":"/paper/2503.21460"},"observation_digest":"sha256:c3ee8bec10055e8d0fb23896e6eeadb3271889213f90f08fa89b6be6367814b6","observation_id":"9faa6ac4-da25-47ec-a49f-093ca02ed54f","resolution":{"observed_at":"2026-05-22T21:52:10.206920Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.13410","last_updated":"2024-11-20T15:52:03Z","snapshot_observed_at":"2026-07-06T19:53:12.584883Z","submitted_at":"2024-11-20T15:52:03Z","title":"A Survey On Enhancing Reinforcement Learning in Complex Environments: Insights from Human and LLM Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.13410","snapshot_observed_at":"2026-08-07T14:49:31.040589Z","title":"A survey on enhancing reinforcement learning in complex environments: Insights from human and llm feedback.arXiv preprint arXiv:2411.13410, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.17481","last_updated":"2025-05-23T05:21:11Z","snapshot_observed_at":"2026-08-07T21:56:32.010090Z","submitted_at":"2025-05-23T05:21:11Z","title":"MARCO: Meta-Reflection with Cross-Referencing for Code Reasoning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T14:49:31.040589Z"},"links":{"cited_paper":"/paper/2411.13410","citing_paper":"/paper/2505.17481"},"observation_digest":"sha256:8dffd0222e41f88ab0353e8aa12915142356702da6d3b2d52371a560f3f10f25","observation_id":"8f4ded18-1345-48f0-99d2-3ef83c081391","resolution":{"observed_at":"2026-08-07T14:49:31.040589Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.13410","last_updated":"2024-11-20T15:52:03Z","snapshot_observed_at":"2026-07-06T19:53:12.584883Z","submitted_at":"2024-11-20T15:52:03Z","title":"A Survey On Enhancing Reinforcement Learning in Complex Environments: Insights from Human and LLM Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.13410","snapshot_observed_at":"2026-08-07T13:53:38.995783Z","title":"A survey on enhancing reinforcement learning in complex environments: Insights from human and llm feedback.arXiv preprint arXiv:2411.13410, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20671","last_updated":"2025-05-27T03:40:02Z","snapshot_observed_at":"2026-08-07T14:06:45.729132Z","submitted_at":"2025-05-27T03:40:02Z","title":"LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:38.995783Z"},"links":{"cited_paper":"/paper/2411.13410","citing_paper":"/paper/2505.20671"},"observation_digest":"sha256:2d2cb0d08051064451fb60e1a1cc9c28c15bad5f61bc711b83f65f187b1ca34b","observation_id":"693244ae-1063-432e-a529-52d44d492358","resolution":{"observed_at":"2026-08-07T13:53:38.995783Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.13410","last_updated":"2024-11-20T15:52:03Z","snapshot_observed_at":"2026-07-06T19:53:12.584883Z","submitted_at":"2024-11-20T15:52:03Z","title":"A Survey On Enhancing Reinforcement Learning in Complex Environments: Insights from Human and LLM Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.13410","snapshot_observed_at":"2026-08-07T12:11:03.514978Z","title":"A survey on enhancing reinforce- ment learning in complex environments: Insights from human and llm feedback,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00309","last_updated":"2025-06-28T05:54:45Z","snapshot_observed_at":"2026-08-07T23:21:38.558900Z","submitted_at":"2025-05-30T23:37:37Z","title":"Evaluation of LLMs for mathematical problem solving","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T12:11:03.514978Z"},"links":{"cited_paper":"/paper/2411.13410","citing_paper":"/paper/2506.00309"},"observation_digest":"sha256:27079291fded9e0399e7b2b0bea755d3a6ef97f33d6209fe790e14302dd32991","observation_id":"2af1b1a6-5461-4764-9987-518e640f6b4c","resolution":{"observed_at":"2026-08-07T12:11:03.514978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2411.13410/citation-record","integrity":"/paper/2411.13410/integrity","json":"/paper/2411.13410/citation-record.json","paper":"/paper/2411.13410"},"outbound":[],"paper":{"arxiv_id":"2411.13410","last_updated":"2024-11-20T15:52:03Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T19:53:12.584883Z","submitted_at":"2024-11-20T15:52:03Z","title":"A Survey On Enhancing Reinforcement Learning in Complex Environments: Insights from Human and LLM Feedback"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2411.13410."}