{"as_of":"2026-08-09T21:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b3220402c9351b86cf9e7d7081ce7470f24979e3c0f9e99bdf7ec4b014d7ab31","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":"2026-08-09T06:31:02.800959+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":"2026-08-04T19:28:58.286475Z","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":"2026-05-10T22:20:49.395329Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.18279","last_updated":"2024-12-24T08:39:35Z","snapshot_observed_at":"2026-07-06T20:12:40.901520Z","submitted_at":"2024-12-24T08:39:35Z","title":"Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.18279","snapshot_observed_at":"2026-08-04T19:28:58.286475Z","title":"Improving multi-step reasoning abilities of large language models with direct advantage policy optimization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09265","last_updated":"2025-09-11T08:50:01Z","snapshot_observed_at":"2026-08-08T10:27:53.369430Z","submitted_at":"2025-09-11T08:50:01Z","title":"Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T19:28:58.286475Z"},"links":{"cited_paper":"/paper/2412.18279","citing_paper":"/paper/2509.09265"},"observation_digest":"sha256:93e9ec9dcdde47fc4f566a4fa8f89e2f40a8a012da757c958fa5a937081538d1","observation_id":"13723c2e-df2d-4094-92f3-2598b454f8e0","resolution":{"observed_at":"2026-08-04T19:28:58.286475Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.18279","last_updated":"2024-12-24T08:39:35Z","snapshot_observed_at":"2026-07-06T20:12:40.901520Z","submitted_at":"2024-12-24T08:39:35Z","title":"Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization","version":1},"cited_work":{"arxiv_id":"2412.18279","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.18279","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Y ., Zeng, L., Yan, R., Sun, Y ., Liu, Y ., and Zhou, Y","venue":null,"work_id":"cdf21888-b034-4b6d-b0b9-5d9eb54e6ace","year":null},"citing_paper":{"arxiv_id":"2604.06385","last_updated":"2026-04-07T19:16:50Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-07T19:16:50Z","title":"Application-Driven Pedagogical Knowledge Optimization of Open-Source LLMs via Reinforcement Learning and Supervised Fine-Tuning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-10T19:55:17.077281Z"},"links":{"cited_paper":"/paper/2412.18279","citing_paper":"/paper/2604.06385"},"observation_digest":"sha256:9218839acc0e0306cf9bca7e24c70de4d99a7847f1d87b5b45b1be0fe7f01d10","observation_id":"e8b1cd13-a158-4d77-8c29-25dfaa2c2a60","resolution":{"observed_at":"2026-05-10T22:20:49.396977Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.18279/citation-record","integrity":"/paper/2412.18279/integrity","json":"/paper/2412.18279/citation-record.json","paper":"/paper/2412.18279"},"outbound":[],"paper":{"arxiv_id":"2412.18279","last_updated":"2024-12-24T08:39:35Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-07-06T20:12:40.901520Z","submitted_at":"2024-12-24T08:39:35Z","title":"Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage 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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2412.18279."}