{"as_of":"2026-08-10T18:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:40ff545aca15e03c31736247b70b915b507421811da36fb69383e8be2b3362cc","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":"2026-08-10T06:31:04.303077+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":"2026-08-07T13:05:01.915820Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T22:46:01.660805Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.03173","last_updated":"2024-03-18T21:44:47Z","snapshot_observed_at":"2026-08-04T00:02:13.267299Z","submitted_at":"2023-10-04T21:40:36Z","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03173","snapshot_observed_at":"2026-08-07T13:05:01.915820Z","title":"B -coder: Value-based deep reinforcement learning for program synthesis, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.22704","last_updated":"2025-05-28T17:57:47Z","snapshot_observed_at":"2026-08-09T22:36:48.949951Z","submitted_at":"2025-05-28T17:57:47Z","title":"Training Language Models to Generate Quality Code with Program Analysis Feedback","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T13:05:01.915820Z"},"links":{"cited_paper":"/paper/2310.03173","citing_paper":"/paper/2505.22704"},"observation_digest":"sha256:f601f3554a60e76dacb7c7f8e112eea361ca85a6a4a71bea372fd236874e7c84","observation_id":"3e1a162d-cc09-49fd-90a7-e166cce82c6c","resolution":{"observed_at":"2026-08-07T13:05:01.915820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03173","last_updated":"2024-03-18T21:44:47Z","snapshot_observed_at":"2026-08-04T00:02:13.267299Z","submitted_at":"2023-10-04T21:40:36Z","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","version":2},"cited_work":{"arxiv_id":"2310.03173","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.03173","snapshot_observed_at":"2026-08-06T22:46:01.660805Z","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","venue":"cs.CL","work_id":"15a828c3-4bbd-453d-a096-c817559fef4c","year":2023},"citing_paper":{"arxiv_id":"2506.21037","last_updated":"2025-06-26T06:28:56Z","snapshot_observed_at":"2026-08-07T22:19:57.815374Z","submitted_at":"2025-06-26T06:28:56Z","title":"RL-Selector: Reinforcement Learning-Guided Data Selection via Redundancy Assessment","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:00.717321Z"},"links":{"cited_paper":"/paper/2310.03173","citing_paper":"/paper/2506.21037"},"observation_digest":"sha256:5d9a6ba626c07f628d2363874f6bc998c6d4e0817b7d6948bbd1ffd3b2fda17c","observation_id":"a5cd0c3f-029c-4e47-adb5-8f3e4aebfd35","resolution":{"observed_at":"2026-08-06T22:46:01.668249Z","resolver_source":"local_arxiv","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"}}],"links":{"evidence":"/evidence","html":"/paper/2310.03173/citation-record","integrity":"/paper/2310.03173/integrity","json":"/paper/2310.03173/citation-record.json","paper":"/paper/2310.03173"},"outbound":[],"paper":{"arxiv_id":"2310.03173","last_updated":"2024-03-18T21:44:47Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-04T00:02:13.267299Z","submitted_at":"2023-10-04T21:40:36Z","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis"},"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 2 inbound Pith citation observations for arXiv:2310.03173."}