{"as_of":"2026-08-08T07:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a0c51ee11fbd6cff8fd7288574cc94a6ec20cf3ac582271fc21785dff55e57c8","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T23:49:05.199743Z","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":"2026-06-28T19:52:35.528605Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.18587","last_updated":"2025-04-24T01:31:05Z","snapshot_observed_at":"2026-08-07T15:59:41.578088Z","submitted_at":"2025-04-24T01:31:05Z","title":"Training Large Language Models to Reason via EM Policy Gradient","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.18587","snapshot_observed_at":"2026-08-05T23:49:05.199743Z","title":"arXiv preprint arXiv:2504.18587","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.04848","last_updated":"2025-08-06T19:51:29Z","snapshot_observed_at":"2026-08-07T23:52:59.955522Z","submitted_at":"2025-08-06T19:51:29Z","title":"Large Language Models Reasoning Abilities Under Non-Ideal Conditions After RL-Fine-Tuning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T23:49:05.199743Z"},"links":{"cited_paper":"/paper/2504.18587","citing_paper":"/paper/2508.04848"},"observation_digest":"sha256:8f9605e34b637ae6aa9ffaf6549790ec2a6db71e18efc704a6d830fe193e0f73","observation_id":"4dd15b6d-ed00-430b-b9bf-739dc07bb09e","resolution":{"observed_at":"2026-08-05T23:49:05.199743Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.18587","last_updated":"2025-04-24T01:31:05Z","snapshot_observed_at":"2026-08-07T15:59:41.578088Z","submitted_at":"2025-04-24T01:31:05Z","title":"Training Large Language Models to Reason via EM Policy Gradient","version":1},"cited_work":{"arxiv_id":"2504.18587","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.18587","snapshot_observed_at":"2026-06-28T19:52:35.528605Z","title":"arXiv preprint arXiv:2504.18587 , year =","venue":null,"work_id":"348d0af4-6192-4937-b932-70d7cc51326f","year":null},"citing_paper":{"arxiv_id":"2606.00726","last_updated":"2026-07-10T01:15:34Z","snapshot_observed_at":"2026-08-02T05:37:27.284595Z","submitted_at":"2026-05-30T13:38:06Z","title":"Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-06-28T18:49:56.917505Z"},"links":{"cited_paper":"/paper/2504.18587","citing_paper":"/paper/2606.00726"},"observation_digest":"sha256:fbc6b90ab1bf185fb3d4064563853920a55a34c2335f6144072055fb2798a68c","observation_id":"f747e75b-63c4-466f-9683-25d39e9aacff","resolution":{"observed_at":"2026-06-28T19:52:35.530081Z","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/2504.18587/citation-record","integrity":"/paper/2504.18587/integrity","json":"/paper/2504.18587/citation-record.json","paper":"/paper/2504.18587"},"outbound":[],"paper":{"arxiv_id":"2504.18587","last_updated":"2025-04-24T01:31:05Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T15:59:41.578088Z","submitted_at":"2025-04-24T01:31:05Z","title":"Training Large Language Models to Reason via EM Policy Gradient"},"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 2 inbound Pith citation observations for arXiv:2504.18587."}