{"as_of":"2026-08-11T00:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:32d9341bad9be7d24704a796eb5f23a48f2dc9ed45f89d0c33985e0606d6d097","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":"2026-08-09T13:14:34.000270Z","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":"2026-08-09T13:14:34.567324Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.09520","last_updated":"2024-01-02T00:04:13Z","snapshot_observed_at":"2026-08-10T17:45:47.437016Z","submitted_at":"2023-10-14T07:19:47Z","title":"Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model","version":4},"cited_work":{"arxiv_id":"2310.09520","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.09520","snapshot_observed_at":"2026-08-09T13:14:34.567324Z","title":"Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model","venue":"cs.CL","work_id":"8e8c6d43-f818-47de-b7f5-fc7745b12d52","year":2023},"citing_paper":{"arxiv_id":"2502.02153","last_updated":"2025-02-04T09:31:54Z","snapshot_observed_at":"2026-08-10T22:40:03.075202Z","submitted_at":"2025-02-04T09:31:54Z","title":"Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-09T13:14:34.000270Z"},"links":{"cited_paper":"/paper/2310.09520","citing_paper":"/paper/2502.02153"},"observation_digest":"sha256:f4c7d6d3644f67d6201d54100cc941db671a19816b981fb9f7d4d1668dc3a6dc","observation_id":"cb5db034-2f19-4d33-9cc9-24dbfe1d4142","resolution":{"observed_at":"2026-08-09T13:14:34.570965Z","resolver_source":"local_arxiv","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":"2310.09520","last_updated":"2024-01-02T00:04:13Z","snapshot_observed_at":"2026-08-10T17:45:47.437016Z","submitted_at":"2023-10-14T07:19:47Z","title":"Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.09520","snapshot_observed_at":"2026-08-06T16:34:24.978471Z","title":"Reward-augmented decoding: Efficient controlled text generation with a unidirectional reward model.arXiv preprint arXiv:2310.09520,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.13158","last_updated":"2025-07-17T14:22:24Z","snapshot_observed_at":"2026-08-09T20:19:53.961381Z","submitted_at":"2025-07-17T14:22:24Z","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-06T16:34:24.978471Z"},"links":{"cited_paper":"/paper/2310.09520","citing_paper":"/paper/2507.13158"},"observation_digest":"sha256:68847e0fe740bd323705def56b034856167d4e18cd21060214a79cb921b9c80d","observation_id":"7857cb24-528c-438b-ab37-dde902ea68e5","resolution":{"observed_at":"2026-08-06T16:34:24.978471Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.09520","last_updated":"2024-01-02T00:04:13Z","snapshot_observed_at":"2026-08-10T17:45:47.437016Z","submitted_at":"2023-10-14T07:19:47Z","title":"Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.09520","snapshot_observed_at":"2026-08-04T13:15:42.856054Z","title":"Reward-augmented decoding: Efficient controlled text generation with a unidirectional reward model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.01167","last_updated":"2026-05-30T06:40:26Z","snapshot_observed_at":"2026-08-09T12:10:30.690264Z","submitted_at":"2025-10-01T17:54:15Z","title":"Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-04T13:15:42.856054Z"},"links":{"cited_paper":"/paper/2310.09520","citing_paper":"/paper/2510.01167"},"observation_digest":"sha256:d7dbce6e451e8f37f5f8dd954237cf8f4a705b8902c82eaeac3953181d639fd2","observation_id":"d316d570-0520-493f-bdb5-f360b2f52fc9","resolution":{"observed_at":"2026-08-04T13:15:42.856054Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2310.09520/citation-record","integrity":"/paper/2310.09520/integrity","json":"/paper/2310.09520/citation-record.json","paper":"/paper/2310.09520"},"outbound":[],"paper":{"arxiv_id":"2310.09520","last_updated":"2024-01-02T00:04:13Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-10T17:45:47.437016Z","submitted_at":"2023-10-14T07:19:47Z","title":"Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model"},"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 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2310.09520."}