{"as_of":"2026-08-20T16:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c87285537732bd3cd0d4b395959839266f6e8810e75b23ed89f44f70fa3b4d72","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":"2026-08-20T06:33:59.587034+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":"2026-08-15T21:32:35.030666Z","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":"2026-05-17T06:49:11.527210Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.06176","last_updated":"2024-03-05T05:18:54Z","snapshot_observed_at":"2026-08-16T15:34:24.581660Z","submitted_at":"2023-05-09T17:06:06Z","title":"Fine-tuning Language Models with Generative Adversarial Reward Modelling","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.06176","snapshot_observed_at":"2026-08-15T21:32:35.030666Z","title":"Fine-tuning language models with generative adversarial reward modelling, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.09602","last_updated":"2025-05-14T17:52:10Z","snapshot_observed_at":"2026-08-17T22:49:04.456989Z","submitted_at":"2025-05-14T17:52:10Z","title":"Adversarial Suffix Filtering: a Defense Pipeline for LLMs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T21:32:35.030666Z"},"links":{"cited_paper":"/paper/2305.06176","citing_paper":"/paper/2505.09602"},"observation_digest":"sha256:eb262cc937fe68bce8a69769528d44ed700f7ad85cb479698fa3bd87dbfd1355","observation_id":"db22b0bd-e267-4afb-a91c-c15a05bf232e","resolution":{"observed_at":"2026-08-15T21:32:35.030666Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.06176","last_updated":"2024-03-05T05:18:54Z","snapshot_observed_at":"2026-08-16T15:34:24.581660Z","submitted_at":"2023-05-09T17:06:06Z","title":"Fine-tuning Language Models with Generative Adversarial Reward Modelling","version":3},"cited_work":{"arxiv_id":"2305.06176","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.06176","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fine-tuning language models with generative adversarial reward modelling","venue":null,"work_id":"10c0865f-6391-4577-a70b-5b7660e4ecd5","year":2023},"citing_paper":{"arxiv_id":"2511.17879","last_updated":"2026-05-11T05:35:39Z","snapshot_observed_at":"2026-08-15T10:08:06.643133Z","submitted_at":"2025-11-22T02:12:41Z","title":"Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction","version":4},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-17T06:46:21.474224Z"},"links":{"cited_paper":"/paper/2305.06176","citing_paper":"/paper/2511.17879"},"observation_digest":"sha256:b4b1e8df58846f72583d0ceb341f3f6045f59b57cab4edfa656af589b7411b0a","observation_id":"2f71ae80-07dc-46cc-aaa3-46557aa183af","resolution":{"observed_at":"2026-05-17T06:49:11.530196Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2305.06176/citation-record","integrity":"/paper/2305.06176/integrity","json":"/paper/2305.06176/citation-record.json","paper":"/paper/2305.06176"},"outbound":[],"paper":{"arxiv_id":"2305.06176","last_updated":"2024-03-05T05:18:54Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T15:34:24.581660Z","submitted_at":"2023-05-09T17:06:06Z","title":"Fine-tuning Language Models with Generative Adversarial Reward Modelling"},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2305.06176."}