{"as_of":"2026-08-10T10:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:428bbc3d4b69ba0b7c4dda3f4cd9b0da45bbc8679f028b378efff2ba14b7ff7f","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:37:47.590688Z","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":"2026-05-15T01:48:28.550913Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.15821","last_updated":"2024-05-23T14:01:44Z","snapshot_observed_at":"2026-07-06T18:19:33.945119Z","submitted_at":"2024-05-23T14:01:44Z","title":"Reinforcing Language Agents via Policy Optimization with Action Decomposition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.15821","snapshot_observed_at":"2026-08-07T14:37:47.590688Z","title":"Reinforcing language agents via policy optimization with action decomposition","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18121","last_updated":"2025-05-23T17:23:11Z","snapshot_observed_at":"2026-08-10T01:45:33.256858Z","submitted_at":"2025-05-23T17:23:11Z","title":"ProgRM: Build Better GUI Agents with Progress Rewards","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T14:37:47.590688Z"},"links":{"cited_paper":"/paper/2405.15821","citing_paper":"/paper/2505.18121"},"observation_digest":"sha256:1363d784923d1c80bd7cf7914aa3035cbf03638cb485aa24abe2ff476894cc00","observation_id":"8029fb17-4eaa-44da-a0b9-37a8b23ba8c9","resolution":{"observed_at":"2026-08-07T14:37:47.590688Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15821","last_updated":"2024-05-23T14:01:44Z","snapshot_observed_at":"2026-07-06T18:19:33.945119Z","submitted_at":"2024-05-23T14:01:44Z","title":"Reinforcing Language Agents via Policy Optimization with Action Decomposition","version":1},"cited_work":{"arxiv_id":"2405.15821","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.15821","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Reinforcing language agents via policy optimization with action decomposition","venue":null,"work_id":"7a369f88-9b85-448e-868a-e9b01d6ce891","year":2024},"citing_paper":{"arxiv_id":"2604.09459","last_updated":"2026-04-13T12:08:22Z","snapshot_observed_at":"2026-07-06T22:58:21.624968Z","submitted_at":"2026-04-10T16:17:44Z","title":"From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-10T17:09:36.341574Z"},"links":{"cited_paper":"/paper/2405.15821","citing_paper":"/paper/2604.09459"},"observation_digest":"sha256:bf11b37a3a6ebd8fd1e5b75ad490765df54fac405817f8120ca25174f0f1b175","observation_id":"c6e8579a-c8a1-4ccf-b5e2-58311378a9dd","resolution":{"observed_at":"2026-05-11T07:30:58.541659Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15821","last_updated":"2024-05-23T14:01:44Z","snapshot_observed_at":"2026-07-06T18:19:33.945119Z","submitted_at":"2024-05-23T14:01:44Z","title":"Reinforcing Language Agents via Policy Optimization with Action Decomposition","version":1},"cited_work":{"arxiv_id":"2405.15821","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.15821","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Reinforcing language agents via policy optimization with action decomposition","venue":null,"work_id":"7a369f88-9b85-448e-868a-e9b01d6ce891","year":2024},"citing_paper":{"arxiv_id":"2605.14558","last_updated":"2026-05-14T08:33:02Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:33:02Z","title":"Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-15T01:46:24.724553Z"},"links":{"cited_paper":"/paper/2405.15821","citing_paper":"/paper/2605.14558"},"observation_digest":"sha256:68bb5feb5f32e5ffd9bfe431e6cb452eca8edbd3cc62e51303e8864717191568","observation_id":"ee7f9348-e1a5-4dd5-b9ff-df2570a48912","resolution":{"observed_at":"2026-05-15T01:48:28.553279Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15821","last_updated":"2024-05-23T14:01:44Z","snapshot_observed_at":"2026-07-06T18:19:33.945119Z","submitted_at":"2024-05-23T14:01:44Z","title":"Reinforcing Language Agents via Policy Optimization with Action Decomposition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.15821","snapshot_observed_at":"2026-08-06T00:23:00.148968Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.01321","last_updated":"2026-08-02T15:41:57Z","snapshot_observed_at":"2026-08-09T21:23:32.151764Z","submitted_at":"2026-08-02T15:41:57Z","title":"BiCAA: Bidirectional Credit Assignment for Search-Augmented Agent","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T00:23:00.148968Z"},"links":{"cited_paper":"/paper/2405.15821","citing_paper":"/paper/2608.01321"},"observation_digest":"sha256:6aedec9f8aaa441a62e63847b0030d4953eb790888789211707ef30de86ce099","observation_id":"053a9567-4e62-4d7c-8e96-0d99d0544034","resolution":{"observed_at":"2026-08-06T00:23:00.148968Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2405.15821/citation-record","integrity":"/paper/2405.15821/integrity","json":"/paper/2405.15821/citation-record.json","paper":"/paper/2405.15821"},"outbound":[],"paper":{"arxiv_id":"2405.15821","last_updated":"2024-05-23T14:01:44Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-07-06T18:19:33.945119Z","submitted_at":"2024-05-23T14:01:44Z","title":"Reinforcing Language Agents via Policy Optimization with Action Decomposition"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2405.15821."}