{"as_of":"2026-08-19T23:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f07c30186f7c711810cfe257a12cb09ce6144f4abb39560abb5daa5d80419565","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":"2026-08-19T06:32:44.657259+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":"2026-08-12T00:30:33.400576Z","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":"2026-08-07T12:35:30.314941Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.09345","last_updated":"2024-11-01T06:30:11Z","snapshot_observed_at":"2026-08-16T14:18:33.995819Z","submitted_at":"2024-02-14T17:49:07Z","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09345","snapshot_observed_at":"2026-08-11T10:41:23.993491Z","title":"Mitigating reward hacking via information-theoretic reward modeling","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.16475","last_updated":"2024-12-21T04:07:17Z","snapshot_observed_at":"2026-08-18T01:37:48.564993Z","submitted_at":"2024-12-21T04:07:17Z","title":"When Can Proxies Improve the Sample Complexity of Preference Learning?","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-11T10:41:23.993491Z"},"links":{"cited_paper":"/paper/2402.09345","citing_paper":"/paper/2412.16475"},"observation_digest":"sha256:95f20b481b656e51e654f037096519662f4be4b42378a78af7487797641a85f9","observation_id":"5ccb960a-0681-47fb-aa64-390ab974365a","resolution":{"observed_at":"2026-08-11T10:41:23.993491Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09345","last_updated":"2024-11-01T06:30:11Z","snapshot_observed_at":"2026-08-16T14:18:33.995819Z","submitted_at":"2024-02-14T17:49:07Z","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","version":5},"cited_work":{"arxiv_id":"2402.09345","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.09345","snapshot_observed_at":"2026-08-07T12:35:30.314941Z","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","venue":"cs.LG","work_id":"9c5a8d87-ceae-4a46-8fdf-2cc2356fee33","year":2024},"citing_paper":{"arxiv_id":"2505.24519","last_updated":"2025-05-30T12:30:50Z","snapshot_observed_at":"2026-08-16T09:07:36.122949Z","submitted_at":"2025-05-30T12:30:50Z","title":"AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:27.696015Z"},"links":{"cited_paper":"/paper/2402.09345","citing_paper":"/paper/2505.24519"},"observation_digest":"sha256:be63a98a6ce38149277ceb8182217607bd0457df31a3246a9898090f497780f7","observation_id":"b5eb8da3-2fb5-4a0b-a87f-592c7f958673","resolution":{"observed_at":"2026-08-07T12:35:30.381649Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09345","last_updated":"2024-11-01T06:30:11Z","snapshot_observed_at":"2026-08-16T14:18:33.995819Z","submitted_at":"2024-02-14T17:49:07Z","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09345","snapshot_observed_at":"2026-08-12T00:30:33.400576Z","title":"InfoRM: Mit- igating reward hacking in RLHF via information-theoretic reward modeling","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.08158","last_updated":"2026-08-08T14:35:29Z","snapshot_observed_at":"2026-08-14T20:47:59.935303Z","submitted_at":"2026-08-08T14:35:29Z","title":"A Unified Framework for Dynamic Reward Shaping in Reinforcement Learning","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-12T00:30:33.400576Z"},"links":{"cited_paper":"/paper/2402.09345","citing_paper":"/paper/2608.08158"},"observation_digest":"sha256:47e1dc8b5f15048ac0c9cd6aab657f8983138d8861371c81964baae7869dd034","observation_id":"dfafb29f-ee29-4220-a9a3-2eca840c1fcf","resolution":{"observed_at":"2026-08-12T00:30:33.400576Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2402.09345/citation-record","integrity":"/paper/2402.09345/integrity","json":"/paper/2402.09345/citation-record.json","paper":"/paper/2402.09345"},"outbound":[],"paper":{"arxiv_id":"2402.09345","last_updated":"2024-11-01T06:30:11Z","latest_version":5,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T14:18:33.995819Z","submitted_at":"2024-02-14T17:49:07Z","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling"},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2402.09345."}