{"as_of":"2026-08-08T10:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:468411b14e9d1854f82ef00fe7ecb4d71e437c33ef5eb4064df36be63f057245","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T14:27:03.720278Z","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":"2026-08-05T15:38:56.326987Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.18349","last_updated":"2024-08-08T08:57:23Z","snapshot_observed_at":"2026-08-06T14:40:09.150498Z","submitted_at":"2024-03-27T08:39:56Z","title":"Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18349","snapshot_observed_at":"2026-08-07T14:27:03.720278Z","title":"Rejection improves reliability: Training llms to refuse un- known questions using rl from knowledge feedback","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18889","last_updated":"2025-08-24T03:15:13Z","snapshot_observed_at":"2026-08-08T09:26:48.848517Z","submitted_at":"2025-05-24T22:22:43Z","title":"Security Concerns for Large Language Models: A Survey","version":5},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-07T14:27:03.720278Z"},"links":{"cited_paper":"/paper/2403.18349","citing_paper":"/paper/2505.18889"},"observation_digest":"sha256:42e7a35a302997dfd0fad54d9df3caf95f07e5cecc890de244734274a1a72152","observation_id":"702d2ad4-02d6-4f69-82be-ff06d645237e","resolution":{"observed_at":"2026-08-07T14:27:03.720278Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18349","last_updated":"2024-08-08T08:57:23Z","snapshot_observed_at":"2026-08-06T14:40:09.150498Z","submitted_at":"2024-03-27T08:39:56Z","title":"Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18349","snapshot_observed_at":"2026-08-07T13:30:24.985286Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21701","last_updated":"2025-05-30T14:39:34Z","snapshot_observed_at":"2026-08-07T13:22:29.565307Z","submitted_at":"2025-05-27T19:39:49Z","title":"Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T13:30:24.985286Z"},"links":{"cited_paper":"/paper/2403.18349","citing_paper":"/paper/2505.21701"},"observation_digest":"sha256:abf9bab6427539fb974d1a4198ec66b504b332c16d8bfbfb98706984d74a74ec","observation_id":"3509225c-0ef7-4b5f-a713-76e4a1114a3e","resolution":{"observed_at":"2026-08-07T13:30:24.985286Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18349","last_updated":"2024-08-08T08:57:23Z","snapshot_observed_at":"2026-08-06T14:40:09.150498Z","submitted_at":"2024-03-27T08:39:56Z","title":"Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback","version":3},"cited_work":{"arxiv_id":"2403.18349","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.18349","snapshot_observed_at":"2026-08-05T15:38:56.326987Z","title":"Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback","venue":"cs.CL","work_id":"28c9516d-b280-4bd1-82a1-cdcc204e9cba","year":2024},"citing_paper":{"arxiv_id":"2508.19689","last_updated":"2025-08-27T08:52:47Z","snapshot_observed_at":"2026-08-07T07:48:25.655053Z","submitted_at":"2025-08-27T08:52:47Z","title":"Building Task Bots with Self-learning for Enhanced Adaptability, Extensibility, and Factuality","version":1},"reference_index":201,"source":"arxiv_source","source_observed_at":"2026-08-05T15:38:55.221247Z"},"links":{"cited_paper":"/paper/2403.18349","citing_paper":"/paper/2508.19689"},"observation_digest":"sha256:f69f92e9fb4584a7598c9fd8946cabb1ab1fdaab955e211cf9a5b6f84f97820a","observation_id":"cb0e920c-de7e-41a8-8e2a-6c3551cf4553","resolution":{"observed_at":"2026-08-05T15:38:56.332107Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18349","last_updated":"2024-08-08T08:57:23Z","snapshot_observed_at":"2026-08-06T14:40:09.150498Z","submitted_at":"2024-03-27T08:39:56Z","title":"Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18349","snapshot_observed_at":"2026-08-04T00:53:26.819594Z","title":"Rejection Improves Reliability: Training","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.00301","last_updated":"2026-07-31T21:31:07Z","snapshot_observed_at":"2026-08-06T23:12:19.979776Z","submitted_at":"2026-07-31T21:31:07Z","title":"Abstention as an Action Can Kill Both the Reward Gradient and the KL Anchor: Collapse Law and Repair for Error-Penalized Reinforcement Learning","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-04T00:53:26.819594Z"},"links":{"cited_paper":"/paper/2403.18349","citing_paper":"/paper/2608.00301"},"observation_digest":"sha256:65fb10713a1c5d80883f5edca139f17a8f20a89dc012233ee54c9a80e4a2cde5","observation_id":"74247269-072c-4a8b-a849-8dbaae796dad","resolution":{"observed_at":"2026-08-04T00:53:26.819594Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2403.18349/citation-record","integrity":"/paper/2403.18349/integrity","json":"/paper/2403.18349/citation-record.json","paper":"/paper/2403.18349"},"outbound":[],"paper":{"arxiv_id":"2403.18349","last_updated":"2024-08-08T08:57:23Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-06T14:40:09.150498Z","submitted_at":"2024-03-27T08:39:56Z","title":"Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2403.18349."}