{"as_of":"2026-08-13T10:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:db2a19b3ea8111823185a71309c2049166a377bedd0dc1ba83f1568aebc29cac","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":"2026-08-13T06:32:02.005865+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":"2026-07-14T07:36:47.336670Z","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":"2026-07-02T07:56:47.268139Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2509.21882","last_updated":"2026-05-25T20:11:55Z","snapshot_observed_at":"2026-08-11T14:37:27.408618Z","submitted_at":"2025-09-26T05:06:25Z","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","version":3},"cited_work":{"arxiv_id":"2509.21882","doi":null,"metadata_source":"pith","pith_arxiv_id":"2509.21882","snapshot_observed_at":"2026-07-02T07:56:47.268139Z","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","venue":"cs.LG","work_id":"1cb1e1d7-d83e-4791-8d91-eed2ec291aad","year":2025},"citing_paper":{"arxiv_id":"2605.02913","last_updated":"2026-04-08T00:53:29Z","snapshot_observed_at":"2026-08-11T14:34:10.687717Z","submitted_at":"2026-04-08T00:53:29Z","title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","version":1},"reference_index":113,"source":"arxiv_source","source_observed_at":"2026-05-10T19:15:27.406778Z"},"links":{"cited_paper":"/paper/2509.21882","citing_paper":"/paper/2605.02913"},"observation_digest":"sha256:3e5e3774680c377f9575ef9e3b873b6aff27cd9299a2050cc63a4dae2ac426af","observation_id":"c1232b4a-3bca-47d9-b192-b8836dfe601b","resolution":{"observed_at":"2026-05-10T23:15:49.073894Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.21882","last_updated":"2026-05-25T20:11:55Z","snapshot_observed_at":"2026-08-11T14:37:27.408618Z","submitted_at":"2025-09-26T05:06:25Z","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","version":3},"cited_work":{"arxiv_id":"2509.21882","doi":null,"metadata_source":"pith","pith_arxiv_id":"2509.21882","snapshot_observed_at":"2026-07-02T07:56:47.268139Z","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","venue":"cs.LG","work_id":"1cb1e1d7-d83e-4791-8d91-eed2ec291aad","year":2025},"citing_paper":{"arxiv_id":"2606.05104","last_updated":"2026-06-04T05:37:51Z","snapshot_observed_at":"2026-07-06T23:45:06.925235Z","submitted_at":"2026-06-03T17:06:49Z","title":"Knowledge Index of Noah's Ark","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:33.539031Z"},"links":{"cited_paper":"/paper/2509.21882","citing_paper":"/paper/2606.05104"},"observation_digest":"sha256:5557732ac9313febd811091a7b33e1d246ff28e199dd4e3f22e943cf6fbe631b","observation_id":"0b425e98-70da-458c-8c1b-938bd3918292","resolution":{"observed_at":"2026-07-02T07:56:47.269411Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.21882","last_updated":"2026-05-25T20:11:55Z","snapshot_observed_at":"2026-08-11T14:37:27.408618Z","submitted_at":"2025-09-26T05:06:25Z","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.21882","snapshot_observed_at":"2026-07-14T07:36:47.336670Z","title":"Position: The hidden costs and measurement gaps of reinforcement learning with verifiable rewards.arXiv preprint arXiv:2509.21882,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.11022","last_updated":"2026-07-13T02:41:16Z","snapshot_observed_at":"2026-08-10T16:35:21.863640Z","submitted_at":"2026-07-13T02:41:16Z","title":"When the Reward Suite Is Leaky: A Preregistered Causal Contrast of Natural Verifier False Positives in RLVR","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-14T07:36:47.336670Z"},"links":{"cited_paper":"/paper/2509.21882","citing_paper":"/paper/2607.11022"},"observation_digest":"sha256:924053424b71c0ded9c8b5bbfc97bddccb02e18c908831c59d8ac02cecd58fbb","observation_id":"d56ebb19-d727-45c7-b664-0063e6bb2ccd","resolution":{"observed_at":"2026-07-14T07:36:47.336670Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2509.21882/citation-record","integrity":"/paper/2509.21882/integrity","json":"/paper/2509.21882/citation-record.json","paper":"/paper/2509.21882"},"outbound":[],"paper":{"arxiv_id":"2509.21882","last_updated":"2026-05-25T20:11:55Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T14:37:27.408618Z","submitted_at":"2025-09-26T05:06:25Z","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2509.21882."}