{"as_of":"2026-08-02T15:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a8e20bf7c57bcc3a3ebee9adf5670dd2e3c2b373f883b91444870c06fbe1b672","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":"2026-06-28T23:54:32.621093Z","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":"2026-06-29T00:02:49.975961Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.20194","last_updated":"2025-03-26T03:37:52Z","snapshot_observed_at":"2026-07-06T20:58:46.814850Z","submitted_at":"2025-03-26T03:37:52Z","title":"GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization","version":1},"cited_work":{"arxiv_id":"2503.20194","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.20194","snapshot_observed_at":"2026-06-29T00:02:49.975961Z","title":"arXiv preprint arXiv:2503.20194 , year=","venue":null,"work_id":"1ffb39a6-7543-4c31-8d99-5b4f6d535be2","year":2025},"citing_paper":{"arxiv_id":"2604.02988","last_updated":"2026-04-03T11:48:38Z","snapshot_observed_at":"2026-07-06T22:52:15.263364Z","submitted_at":"2026-04-03T11:48:38Z","title":"Self-Optimizing Multi-Agent Systems for Deep Research","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-13T18:13:14.668406Z"},"links":{"cited_paper":"/paper/2503.20194","citing_paper":"/paper/2604.02988"},"observation_digest":"sha256:68f5d38283ff4d36e421ec36ba79e1045fc71641554b29bbd908098cf922acb4","observation_id":"67408328-cee1-451a-9477-0df81bc462b1","resolution":{"observed_at":"2026-05-13T18:18:06.474176Z","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":"2503.20194","last_updated":"2025-03-26T03:37:52Z","snapshot_observed_at":"2026-07-06T20:58:46.814850Z","submitted_at":"2025-03-26T03:37:52Z","title":"GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization","version":1},"cited_work":{"arxiv_id":"2503.20194","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.20194","snapshot_observed_at":"2026-06-29T00:02:49.975961Z","title":"arXiv preprint arXiv:2503.20194 , year=","venue":null,"work_id":"1ffb39a6-7543-4c31-8d99-5b4f6d535be2","year":2025},"citing_paper":{"arxiv_id":"2605.06036","last_updated":"2026-05-07T11:26:04Z","snapshot_observed_at":"2026-07-06T23:18:36.537416Z","submitted_at":"2026-05-07T11:26:04Z","title":"Optimal Transport for LLM Reward Modeling from Noisy Preference","version":1},"reference_index":251,"source":"arxiv_source","source_observed_at":"2026-05-08T14:10:49.634358Z"},"links":{"cited_paper":"/paper/2503.20194","citing_paper":"/paper/2605.06036"},"observation_digest":"sha256:1d9df3278c0d99d1e65ed9b1b3e24ac9c6dd9d597e87f0995b0dbe9717d30baa","observation_id":"517b542d-bdcc-4ec7-93c5-334138941159","resolution":{"observed_at":"2026-05-11T18:46:07.348994Z","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":"2503.20194","last_updated":"2025-03-26T03:37:52Z","snapshot_observed_at":"2026-07-06T20:58:46.814850Z","submitted_at":"2025-03-26T03:37:52Z","title":"GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization","version":1},"cited_work":{"arxiv_id":"2503.20194","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.20194","snapshot_observed_at":"2026-06-29T00:02:49.975961Z","title":"arXiv preprint arXiv:2503.20194 , year=","venue":null,"work_id":"1ffb39a6-7543-4c31-8d99-5b4f6d535be2","year":2025},"citing_paper":{"arxiv_id":"2605.30789","last_updated":"2026-06-02T09:15:19Z","snapshot_observed_at":"2026-08-02T15:38:17.906891Z","submitted_at":"2026-05-29T03:25:56Z","title":"Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-28T23:54:32.621093Z"},"links":{"cited_paper":"/paper/2503.20194","citing_paper":"/paper/2605.30789"},"observation_digest":"sha256:986eb7eddd1d46ee859e719286e2c3b16abc10dfa3be48b70962351358b0e30a","observation_id":"b8ea111c-6918-4653-8877-3d35b65f6623","resolution":{"observed_at":"2026-06-29T00:02:49.977641Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2503.20194/citation-record","integrity":"/paper/2503.20194/integrity","json":"/paper/2503.20194/citation-record.json","paper":"/paper/2503.20194"},"outbound":[],"paper":{"arxiv_id":"2503.20194","last_updated":"2025-03-26T03:37:52Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T20:58:46.814850Z","submitted_at":"2025-03-26T03:37:52Z","title":"GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization"},"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:2503.20194."}