{"as_of":"2026-08-10T11:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:33273d7a984f9e78940da4b31c1c9c4ac2ada395f3ccbb63ae50f5f3dd7ddc83","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":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":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T00:19:13.584966Z","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":"2026-05-14T21:19:28.307743Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.14718","last_updated":"2024-04-20T00:34:59Z","snapshot_observed_at":"2026-07-06T15:32:14.701994Z","submitted_at":"2023-05-24T04:42:17Z","title":"Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models","version":5},"cited_work":{"arxiv_id":"2305.14718","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.14718","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Baheti, X","venue":null,"work_id":"57c942f6-50b6-48e8-9ae8-30082de084d9","year":2024},"citing_paper":{"arxiv_id":"2605.11726","last_updated":"2026-05-13T15:38:02Z","snapshot_observed_at":"2026-07-06T23:23:30.499023Z","submitted_at":"2026-05-12T08:09:42Z","title":"Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-13T07:03:00.503644Z"},"links":{"cited_paper":"/paper/2305.14718","citing_paper":"/paper/2605.11726"},"observation_digest":"sha256:b7a0b6a5b5cb7ecb559142475849e75204bc33e7938d6824429764705b5d4d54","observation_id":"d0938da9-4b0a-4b8f-87c2-1171d30e40df","resolution":{"observed_at":"2026-05-13T07:07:28.026247Z","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":"2305.14718","last_updated":"2024-04-20T00:34:59Z","snapshot_observed_at":"2026-07-06T15:32:14.701994Z","submitted_at":"2023-05-24T04:42:17Z","title":"Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models","version":5},"cited_work":{"arxiv_id":"2305.14718","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.14718","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Baheti, X","venue":null,"work_id":"57c942f6-50b6-48e8-9ae8-30082de084d9","year":2024},"citing_paper":{"arxiv_id":"2605.11726","last_updated":"2026-05-13T15:38:02Z","snapshot_observed_at":"2026-07-06T23:23:30.499023Z","submitted_at":"2026-05-12T08:09:42Z","title":"Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-14T21:06:01.667173Z"},"links":{"cited_paper":"/paper/2305.14718","citing_paper":"/paper/2605.11726"},"observation_digest":"sha256:bc24a2f0b1136b934e7f7a994bcc8f4a5884aea9a4ca1eb5f70260f9b319a4b2","observation_id":"2867da3b-c4ca-486a-9170-96976ded2c36","resolution":{"observed_at":"2026-05-14T21:19:28.309888Z","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":"2305.14718","last_updated":"2024-04-20T00:34:59Z","snapshot_observed_at":"2026-07-06T15:32:14.701994Z","submitted_at":"2023-05-24T04:42:17Z","title":"Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14718","snapshot_observed_at":"2026-08-05T00:19:13.584966Z","title":"arXiv preprint arXiv:2305.14718 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.00816","last_updated":"2026-08-01T18:48:39Z","snapshot_observed_at":"2026-08-09T14:47:11.614545Z","submitted_at":"2026-08-01T18:48:39Z","title":"Exponential Reward Weighting for Fine-Tuning Generative Recommenders under Sparse and Noisy Feedback","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-05T00:19:13.584966Z"},"links":{"cited_paper":"/paper/2305.14718","citing_paper":"/paper/2608.00816"},"observation_digest":"sha256:88bb48021607a441ed3711f66df5c61079991086ad5f209f3fc47c205d167eec","observation_id":"f4729e51-fd38-4421-92ca-9cad72d06ebc","resolution":{"observed_at":"2026-08-05T00:19:13.584966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2305.14718/citation-record","integrity":"/paper/2305.14718/integrity","json":"/paper/2305.14718/citation-record.json","paper":"/paper/2305.14718"},"outbound":[],"paper":{"arxiv_id":"2305.14718","last_updated":"2024-04-20T00:34:59Z","latest_version":5,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T15:32:14.701994Z","submitted_at":"2023-05-24T04:42:17Z","title":"Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models"},"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 3 inbound Pith citation observations for arXiv:2305.14718."}