{"as_of":"2026-08-13T02:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:25ac7130d16e6a7a9337274f911a72849f0484b1872c9bb0d22de22cdc6eb662","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":"2026-08-12T06:34:41.77262+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":"2026-08-12T00:20:30.924964Z","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":"2026-05-18T15:01:31.346814Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.04617","last_updated":"2025-07-18T17:06:00Z","snapshot_observed_at":"2026-08-12T22:49:41.167525Z","submitted_at":"2024-09-06T21:00:57Z","title":"Sparse Rewards Can Self-Train Dialogue Agents","version":3},"cited_work":{"arxiv_id":"2409.04617","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2409.04617","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Sparse rewards can self-train dialogue agents","venue":null,"work_id":"4a2d3168-9526-480a-adc7-7bd571b86ab6","year":2024},"citing_paper":{"arxiv_id":"2509.18847","last_updated":"2026-04-15T06:57:52Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-09-23T09:35:49Z","title":"Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-18T15:00:51.162221Z"},"links":{"cited_paper":"/paper/2409.04617","citing_paper":"/paper/2509.18847"},"observation_digest":"sha256:b93a12a26c8c2b3eb3cb95c9bd2bf3dcbcc349e26e880fe7b9710dd3e6018288","observation_id":"c1cac734-bc74-4806-ab7b-15c7a44c6f55","resolution":{"observed_at":"2026-05-18T15:01:31.350419Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.04617","last_updated":"2025-07-18T17:06:00Z","snapshot_observed_at":"2026-08-12T22:49:41.167525Z","submitted_at":"2024-09-06T21:00:57Z","title":"Sparse Rewards Can Self-Train Dialogue Agents","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.04617","snapshot_observed_at":"2026-08-12T00:20:30.924964Z","title":"Barrett Martin Lattimer, Varun Gangal, Ryan Mcdonald, and Yi Yang","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.08255","last_updated":"2026-08-08T17:32:34Z","snapshot_observed_at":"2026-08-13T01:12:28.614123Z","submitted_at":"2026-08-08T17:32:34Z","title":"Learning from Environmental Feedback: Credit Assignment across Multiple Timescales for Agentic Reinforcement Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T00:20:30.924964Z"},"links":{"cited_paper":"/paper/2409.04617","citing_paper":"/paper/2608.08255"},"observation_digest":"sha256:bdb015567b2d237e8619e12e644b4f90ac9b23fd08150f557b8eed95948733ad","observation_id":"20d99a4f-11f2-4944-b987-753ae45f1b6c","resolution":{"observed_at":"2026-08-12T00:20:30.924964Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2409.04617/citation-record","integrity":"/paper/2409.04617/integrity","json":"/paper/2409.04617/citation-record.json","paper":"/paper/2409.04617"},"outbound":[],"paper":{"arxiv_id":"2409.04617","last_updated":"2025-07-18T17:06:00Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-12T22:49:41.167525Z","submitted_at":"2024-09-06T21:00:57Z","title":"Sparse Rewards Can Self-Train Dialogue Agents"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2409.04617."}