{"as_of":"2026-08-08T13:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:76ae7ebe913f7c93ddbb5b3f3895fc27d6bf472266306f8faa81763e73ac3b8f","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":"2026-08-07T05:10:47.735478Z","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":"2026-05-11T12:46:05.148870Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.19409","last_updated":"2024-04-30T09:57:21Z","snapshot_observed_at":"2026-07-06T18:07:34.924208Z","submitted_at":"2024-04-30T09:57:21Z","title":"Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.19409","snapshot_observed_at":"2026-08-07T05:10:47.735478Z","title":"Countering reward over-optimization in llm with demonstration-guided reinforcement learning.arXiv preprint arXiv:2404.19409, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.08643","last_updated":"2025-06-10T09:55:53Z","snapshot_observed_at":"2026-08-07T22:00:08.822941Z","submitted_at":"2025-06-10T09:55:53Z","title":"MEMETRON: Metaheuristic Mechanisms for Test-time Response Optimization of Large Language Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T05:10:47.735478Z"},"links":{"cited_paper":"/paper/2404.19409","citing_paper":"/paper/2506.08643"},"observation_digest":"sha256:8d11efd3c900d9e5294628295217a0d29eb8a16d49fe4ee8aba47f59d73ef475","observation_id":"71434e16-9a23-4888-9167-faa6a70701b9","resolution":{"observed_at":"2026-08-07T05:10:47.735478Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.19409","last_updated":"2024-04-30T09:57:21Z","snapshot_observed_at":"2026-07-06T18:07:34.924208Z","submitted_at":"2024-04-30T09:57:21Z","title":"Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.19409","snapshot_observed_at":"2026-08-04T14:44:14.954740Z","title":"Countering reward over-optimization in llm with demonstration-guided reinforcement learning.arXiv preprint arXiv:2404.19409,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.23730","last_updated":"2026-05-28T14:53:43Z","snapshot_observed_at":"2026-08-08T08:43:28.613998Z","submitted_at":"2025-09-28T08:20:22Z","title":"EAPO: Enhancing Policy Optimization with On-Demand Expert Assistance","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-04T14:44:14.954740Z"},"links":{"cited_paper":"/paper/2404.19409","citing_paper":"/paper/2509.23730"},"observation_digest":"sha256:18a7f72d487a7cdb7f6a8508ef36e352b313b7a275aa0727daaba596996c65eb","observation_id":"b595ddec-1e1b-43db-a522-d74a07f306cf","resolution":{"observed_at":"2026-08-04T14:44:14.954740Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.19409","last_updated":"2024-04-30T09:57:21Z","snapshot_observed_at":"2026-07-06T18:07:34.924208Z","submitted_at":"2024-04-30T09:57:21Z","title":"Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2404.19409","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.19409","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Countering reward over-optimization in llm with demonstration-guided reinforcement learning","venue":null,"work_id":"3dfd4c05-b217-448d-ba08-7326f5283212","year":2024},"citing_paper":{"arxiv_id":"2604.19656","last_updated":"2026-04-21T16:45:29Z","snapshot_observed_at":"2026-07-06T23:06:16.972438Z","submitted_at":"2026-04-21T16:45:29Z","title":"Pause or Fabricate? Training Language Models for Grounded Reasoning","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-05-10T03:01:58.366028Z"},"links":{"cited_paper":"/paper/2404.19409","citing_paper":"/paper/2604.19656"},"observation_digest":"sha256:b7adf3e3444e406a2bb9ec41b1f607fc76ffc9582f757bdd9b5d146c2d77175b","observation_id":"1412861e-0ced-4a33-adbb-e5877f1a6925","resolution":{"observed_at":"2026-05-11T12:46:05.154606Z","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/2404.19409/citation-record","integrity":"/paper/2404.19409/integrity","json":"/paper/2404.19409/citation-record.json","paper":"/paper/2404.19409"},"outbound":[],"paper":{"arxiv_id":"2404.19409","last_updated":"2024-04-30T09:57:21Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T18:07:34.924208Z","submitted_at":"2024-04-30T09:57:21Z","title":"Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement 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":"2026-08-08T06:32:00.761636+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:2404.19409."}