{"as_of":"2026-08-17T13:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cf9cf044415a7ff5479c4a585a3066f82871a5cb93eede5bc590f91bf8d38e2f","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":"2026-08-17T06:30:58.91139+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":"2026-08-16T11:13:53.652373Z","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":"2026-05-16T16:28:05.645091Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.20703","last_updated":"2024-03-14T08:05:18Z","snapshot_observed_at":"2026-08-16T14:47:06.873463Z","submitted_at":"2023-10-31T17:59:05Z","title":"Vanishing Gradients in Reinforcement Finetuning of Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.20703","snapshot_observed_at":"2026-08-16T11:13:53.652373Z","title":"Vanishing gradients in reinforcement finetuning of language models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.16272","last_updated":"2025-04-22T21:09:33Z","snapshot_observed_at":"2026-08-16T17:39:00.881138Z","submitted_at":"2025-04-22T21:09:33Z","title":"Learning Explainable Dense Reward Shapes via Bayesian Optimization","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-16T11:13:53.652373Z"},"links":{"cited_paper":"/paper/2310.20703","citing_paper":"/paper/2504.16272"},"observation_digest":"sha256:4514537280914177274d454c12eb93d52d489258dcced1c6e0e88138512b868b","observation_id":"b0101030-01d9-421d-8a35-a662453e089f","resolution":{"observed_at":"2026-08-16T11:13:53.652373Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.20703","last_updated":"2024-03-14T08:05:18Z","snapshot_observed_at":"2026-08-16T14:47:06.873463Z","submitted_at":"2023-10-31T17:59:05Z","title":"Vanishing Gradients in Reinforcement Finetuning of Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.20703","snapshot_observed_at":"2026-08-15T20:31:20.459475Z","title":"Vanishing gradients in reinforcement finetuning of language models.arXiv preprint arXiv:2310.20703, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.12951","last_updated":"2025-05-19T10:44:49Z","snapshot_observed_at":"2026-08-15T20:20:42.866766Z","submitted_at":"2025-05-19T10:44:49Z","title":"DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance Management","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:20.459475Z"},"links":{"cited_paper":"/paper/2310.20703","citing_paper":"/paper/2505.12951"},"observation_digest":"sha256:562c600c8ef9d56cb0c4e4f5c78df2cb51e8b94daa7ea9d8891351c1e2714044","observation_id":"fbe4f1d8-2ca6-4ba5-b41b-280e2913fd18","resolution":{"observed_at":"2026-08-15T20:31:20.459475Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.20703","last_updated":"2024-03-14T08:05:18Z","snapshot_observed_at":"2026-08-16T14:47:06.873463Z","submitted_at":"2023-10-31T17:59:05Z","title":"Vanishing Gradients in Reinforcement Finetuning of Language Models","version":3},"cited_work":{"arxiv_id":"2310.20703","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.20703","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Vanishing gradients in reinforcement finetuning of language models","venue":null,"work_id":"1868c81f-6ce8-4747-821d-0b402489e89b","year":2023},"citing_paper":{"arxiv_id":"2601.04809","last_updated":"2026-05-04T13:55:24Z","snapshot_observed_at":"2026-08-14T00:52:49.914352Z","submitted_at":"2026-01-08T10:42:04Z","title":"SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning","version":5},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-16T16:24:04.132572Z"},"links":{"cited_paper":"/paper/2310.20703","citing_paper":"/paper/2601.04809"},"observation_digest":"sha256:1e1a46b283c39c59dcffb48f299684cf3d59602019987f8d8a53696177532ee8","observation_id":"b9b8c2c9-76d6-4051-8401-5bab14caf8f1","resolution":{"observed_at":"2026-05-16T16:28:05.647406Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.20703","last_updated":"2024-03-14T08:05:18Z","snapshot_observed_at":"2026-08-16T14:47:06.873463Z","submitted_at":"2023-10-31T17:59:05Z","title":"Vanishing Gradients in Reinforcement Finetuning of Language Models","version":3},"cited_work":{"arxiv_id":"2310.20703","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.20703","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Vanishing gradients in reinforcement finetuning of language models","venue":null,"work_id":"1868c81f-6ce8-4747-821d-0b402489e89b","year":2023},"citing_paper":{"arxiv_id":"2602.14868","last_updated":"2026-05-08T13:05:12Z","snapshot_observed_at":"2026-08-11T17:40:08.904023Z","submitted_at":"2026-02-16T16:01:27Z","title":"Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-15T21:38:56.393217Z"},"links":{"cited_paper":"/paper/2310.20703","citing_paper":"/paper/2602.14868"},"observation_digest":"sha256:31315c06fc3640ae1f0ddcc166b1cab0faca0e40e54256108a43ee9129a815e2","observation_id":"7f49cdb9-0e17-420c-8875-b45131c5558c","resolution":{"observed_at":"2026-05-15T21:40:20.933757Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2310.20703/citation-record","integrity":"/paper/2310.20703/integrity","json":"/paper/2310.20703/citation-record.json","paper":"/paper/2310.20703"},"outbound":[],"paper":{"arxiv_id":"2310.20703","last_updated":"2024-03-14T08:05:18Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T14:47:06.873463Z","submitted_at":"2023-10-31T17:59:05Z","title":"Vanishing Gradients in Reinforcement Finetuning of 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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2310.20703."}