{"as_of":"2026-08-02T23:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:318e28e0008221152c78b6891699decd7f8aa81f660c9ff803bffb3cf6bb9d3a","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":"2026-08-02T06:30:47.504484+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":"2026-05-18T00:02:24.352947Z","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":"2026-05-18T00:02:25.252362Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.07534","last_updated":"2025-08-16T10:01:44Z","snapshot_observed_at":"2026-07-06T22:10:49.664301Z","submitted_at":"2025-08-11T01:26:16Z","title":"From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR","version":2},"cited_work":{"arxiv_id":"2508.07534","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.07534","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"From trial-and-error to improvement: A systematic analysis of llm exploration mechanisms in rlvr","venue":null,"work_id":"ac56228f-c766-462e-8c76-3db7885a98e2","year":2025},"citing_paper":{"arxiv_id":"2509.08827","last_updated":"2025-10-09T17:08:52Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-09-10T17:59:43Z","title":"A Survey of Reinforcement Learning for Large Reasoning Models","version":3},"reference_index":106,"source":"arxiv_source","source_observed_at":"2026-05-18T00:02:24.352947Z"},"links":{"cited_paper":"/paper/2508.07534","citing_paper":"/paper/2509.08827"},"observation_digest":"sha256:570b5e38895d2e49d6820c89be9e143c9f3cccd77b41af33ef6f8c43cb49d167","observation_id":"9a761aa7-9967-4ef2-81d7-1f3f78de71b1","resolution":{"observed_at":"2026-05-18T00:02:25.255020Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.07534","last_updated":"2025-08-16T10:01:44Z","snapshot_observed_at":"2026-07-06T22:10:49.664301Z","submitted_at":"2025-08-11T01:26:16Z","title":"From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR","version":2},"cited_work":{"arxiv_id":"2508.07534","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.07534","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"From trial-and-error to improvement: A systematic analysis of llm exploration mechanisms in rlvr","venue":null,"work_id":"ac56228f-c766-462e-8c76-3db7885a98e2","year":2025},"citing_paper":{"arxiv_id":"2605.00380","last_updated":"2026-05-08T11:24:05Z","snapshot_observed_at":"2026-08-02T19:56:31.797001Z","submitted_at":"2026-05-01T03:57:44Z","title":"ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-05-09T19:26:57.596581Z"},"links":{"cited_paper":"/paper/2508.07534","citing_paper":"/paper/2605.00380"},"observation_digest":"sha256:ec3c847c4c5d91b776a7a4c2dda29c4ce0dd20217f45e8680e43f99ed592ee6e","observation_id":"ffad19ef-e6cf-4214-9ca7-868e40a51bff","resolution":{"observed_at":"2026-05-11T15:41:45.790129Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.07534","last_updated":"2025-08-16T10:01:44Z","snapshot_observed_at":"2026-07-06T22:10:49.664301Z","submitted_at":"2025-08-11T01:26:16Z","title":"From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR","version":2},"cited_work":{"arxiv_id":"2508.07534","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.07534","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"From trial-and-error to improvement: A systematic analysis of llm exploration mechanisms in rlvr","venue":null,"work_id":"ac56228f-c766-462e-8c76-3db7885a98e2","year":2025},"citing_paper":{"arxiv_id":"2605.00380","last_updated":"2026-05-08T11:24:05Z","snapshot_observed_at":"2026-08-02T19:56:31.797001Z","submitted_at":"2026-05-01T03:57:44Z","title":"ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning","version":2},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-05-11T02:07:21.806345Z"},"links":{"cited_paper":"/paper/2508.07534","citing_paper":"/paper/2605.00380"},"observation_digest":"sha256:8a086b27e0193c6a84152089b38b8de8995de7e25a98db7475a561cb765643a5","observation_id":"5c712013-bb5f-41fa-9ad7-1ab6b67256b3","resolution":{"observed_at":"2026-05-11T03:55:56.685011Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2508.07534/citation-record","integrity":"/paper/2508.07534/integrity","json":"/paper/2508.07534/citation-record.json","paper":"/paper/2508.07534"},"outbound":[],"paper":{"arxiv_id":"2508.07534","last_updated":"2025-08-16T10:01:44Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T22:10:49.664301Z","submitted_at":"2025-08-11T01:26:16Z","title":"From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR"},"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":"2026-08-02T06:30:47.504484+00:00","source":"crossref"},{"observed_at":"2026-08-02T06:30:44.765945+00:00","source":"retraction_watch"}],"thesis":"As of 2 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2508.07534."}