{"as_of":"2026-08-08T12:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c353dd13f66bbd46024801e3225fc5fd02e25688e8438b835a8742e3190c2b17","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T15:24:59.961027Z","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":"2026-05-11T16:56:07.747463Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.06687","last_updated":"2023-10-02T17:20:21Z","snapshot_observed_at":"2026-08-03T23:49:55.520138Z","submitted_at":"2023-09-13T02:56:56Z","title":"Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Robotics","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.06687","snapshot_observed_at":"2026-08-07T15:24:59.961027Z","title":"Self-refined large language model as automated reward function designer for deep reinforcement learning in robotics.arXiv preprint arXiv:2309.06687, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.15306","last_updated":"2025-05-21T09:35:43Z","snapshot_observed_at":"2026-08-07T15:18:11.639286Z","submitted_at":"2025-05-21T09:35:43Z","title":"Multiple Weaks Win Single Strong: Large Language Models Ensemble Weak Reinforcement Learning Agents into a Supreme One","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T15:24:59.961027Z"},"links":{"cited_paper":"/paper/2309.06687","citing_paper":"/paper/2505.15306"},"observation_digest":"sha256:f8a589e0895f5fd55b3c7e528d7bbfc0c4133623a7b138fe52a0bfee08ec7354","observation_id":"1bfd96f7-721e-46bc-821e-f6528fd842e8","resolution":{"observed_at":"2026-08-07T15:24:59.961027Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.06687","last_updated":"2023-10-02T17:20:21Z","snapshot_observed_at":"2026-08-03T23:49:55.520138Z","submitted_at":"2023-09-13T02:56:56Z","title":"Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Robotics","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.06687","snapshot_observed_at":"2026-08-06T20:39:14.628984Z","title":"Self-refined large language model as automated reward function designer for deep reinforcement learning in robotics.arXiv preprint arXiv:2309.06687,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.02256","last_updated":"2025-07-03T03:09:17Z","snapshot_observed_at":"2026-08-06T20:31:32.680778Z","submitted_at":"2025-07-03T03:09:17Z","title":"Uncertainty-aware Reward Design Process","version":1},"reference_index":2012,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:14.628984Z"},"links":{"cited_paper":"/paper/2309.06687","citing_paper":"/paper/2507.02256"},"observation_digest":"sha256:7418b96ff2e36148631305b69b0869af02a5dbf8e44a1dd19d91e472b2bafd69","observation_id":"85bba71d-bfa2-4543-b947-d32463ec5e82","resolution":{"observed_at":"2026-08-06T20:39:14.628984Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.06687","last_updated":"2023-10-02T17:20:21Z","snapshot_observed_at":"2026-08-03T23:49:55.520138Z","submitted_at":"2023-09-13T02:56:56Z","title":"Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Robotics","version":2},"cited_work":{"arxiv_id":"2309.06687","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.06687","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Self-refined large language model as automated reward function designer for deep reinforcement learning in robotics","venue":null,"work_id":"e92275b1-ebc8-45b4-b407-eccbcfa900d3","year":2023},"citing_paper":{"arxiv_id":"2605.01356","last_updated":"2026-05-02T09:59:24Z","snapshot_observed_at":"2026-07-06T23:14:38.379875Z","submitted_at":"2026-05-02T09:59:24Z","title":"Model-Based Proactive Cost Generation for Learning Safe Policies Offline with Limited Violation Data","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-09T14:24:58.919333Z"},"links":{"cited_paper":"/paper/2309.06687","citing_paper":"/paper/2605.01356"},"observation_digest":"sha256:ced1a72609e30e7501129d175b3cf015958a3cf3cfe51ec84586a500d6a10653","observation_id":"9ed27b09-9f3c-49ab-9504-2c39f3a129f0","resolution":{"observed_at":"2026-05-11T16:56:07.753921Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2309.06687/citation-record","integrity":"/paper/2309.06687/integrity","json":"/paper/2309.06687/citation-record.json","paper":"/paper/2309.06687"},"outbound":[],"paper":{"arxiv_id":"2309.06687","last_updated":"2023-10-02T17:20:21Z","latest_version":2,"primary_category":"cs.RO","snapshot_observed_at":"2026-08-03T23:49:55.520138Z","submitted_at":"2023-09-13T02:56:56Z","title":"Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Robotics"},"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 3 inbound Pith citation observations for arXiv:2309.06687."}