{"as_of":"2026-08-04T23:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:683bc3a18df338cf97193d03510bed4cfe6303a62271bae56b50f1527811ee9c","coverage":[{"denominator":3,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-11T11:50:26.030339Z","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":"2026-08-04T06:34:03.388597+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2604.26733/citation-record","integrity":"/paper/2604.26733/integrity","json":"/paper/2604.26733/citation-record.json","paper":"/paper/2604.26733"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.01600","last_updated":"2025-03-08T05:23:57Z","snapshot_observed_at":"2026-07-06T20:30:26.881629Z","submitted_at":"2025-02-03T18:35:42Z","title":"Reinforcement Learning for Long-Horizon Interactive LLM Agents","version":3},"cited_work":{"arxiv_id":"2502.01600","doi":"10.48550/arxiv.2502.01600","metadata_source":"arxiv_reference","pith_arxiv_id":"2502.01600","snapshot_observed_at":"2026-07-10T12:15:01.137692Z","title":"Reinforcement learning for long-horizon interactive llm agents","venue":null,"work_id":"7e929792-6a2a-42ff-a1db-763f890d8b4e","year":2025},"citing_paper":{"arxiv_id":"2604.26733","last_updated":"2026-05-15T12:03:42Z","snapshot_observed_at":"2026-07-06T23:12:19.460065Z","submitted_at":"2026-04-29T14:34:45Z","title":"FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards","version":4},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-19T17:20:07.747499Z"},"links":{"cited_paper":"/paper/2502.01600","citing_paper":"/paper/2604.26733"},"observation_digest":"sha256:63281d77ece419b3d352db33c52f59f7e20dd31cf997e2d0ea85f207eaa84b14","observation_id":"25088d7d-5bec-46f7-bc20-57dbb390f5d3","resolution":{"observed_at":"2026-05-19T17:22:42.017929Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2501.12948","doi":"10.1016/j.artmed.2024.103001","metadata_source":"pith","pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","venue":"cs.CL","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","year":2025},"citing_paper":{"arxiv_id":"2604.26733","last_updated":"2026-05-15T12:03:42Z","snapshot_observed_at":"2026-07-06T23:12:19.460065Z","submitted_at":"2026-04-29T14:34:45Z","title":"FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards","version":4},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-11T11:50:26.030339Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2604.26733"},"observation_digest":"sha256:656a407277db9a1ebf62e80e19191b9ddf19138cddbfd17c2961afc7881a0806","observation_id":"27bde80e-076b-48e8-9e59-49b15b015e0a","resolution":{"observed_at":"2026-05-19T17:22:41.691326Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2024.acl-long.50","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T13:38:18.285940Z","title":"VisualWebArena: Evaluating multimodal agents on realistic visual web tasks","venue":null,"work_id":"7a18db33-5a35-436c-ba83-41b4602aea68","year":2024},"citing_paper":{"arxiv_id":"2604.26733","last_updated":"2026-05-15T12:03:42Z","snapshot_observed_at":"2026-07-06T23:12:19.460065Z","submitted_at":"2026-04-29T14:34:45Z","title":"FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-19T17:20:07.747499Z"},"links":{"citing_paper":"/paper/2604.26733"},"observation_digest":"sha256:c1ccaa35d702252b20e4b81338d9e9935e4219c832f0a83ab1f88474b262618a","observation_id":"8457dff8-85e5-45cb-b037-9d27563d8ebc","resolution":{"observed_at":"2026-05-19T17:22:41.693769Z","resolver_source":"doi","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-15T19:20:32.353486+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-15T19:20:32.353486+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2604.26733","last_updated":"2026-05-15T12:03:42Z","latest_version":4,"primary_category":"cs.AI","snapshot_observed_at":"2026-07-06T23:12:19.460065Z","submitted_at":"2026-04-29T14:34:45Z","title":"FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards"},"reference_resolution":{"displayed":3,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":0,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":3},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 3 of 3 outbound references and 0 inbound Pith citation observations for arXiv:2604.26733."}