{"as_of":"2026-08-11T08:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:51496dc55c9af57ccb92a527c159e1784b9a63408c268ee65be79e90aa5f5c3b","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":"2026-08-11T06:34:44.6726+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":"2026-08-06T19:18:22.770620Z","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":"2026-05-23T04:32:33.097962Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2211.11602","last_updated":"2022-11-21T16:00:31Z","snapshot_observed_at":"2026-08-02T11:24:16.664622Z","submitted_at":"2022-11-21T16:00:31Z","title":"Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback","version":1},"cited_work":{"arxiv_id":"2211.11602","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2211.11602","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Improving multimodal interactive agents with reinforcement learning from human feedback","venue":null,"work_id":"cc4ab2a4-9f17-4232-9a62-08e76732c3b0","year":2022},"citing_paper":{"arxiv_id":"2502.02871","last_updated":"2026-04-20T02:18:01Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-05T04:05:27Z","title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-05-23T04:30:38.804702Z"},"links":{"cited_paper":"/paper/2211.11602","citing_paper":"/paper/2502.02871"},"observation_digest":"sha256:1f04df2bbec5d1a18fc42db0f5297f0cd4e935909d2ebf0cfd2e86e2362dc8e8","observation_id":"f0c690ad-23e6-4581-9afe-d75e29c970d6","resolution":{"observed_at":"2026-05-23T04:32:33.101236Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.11602","last_updated":"2022-11-21T16:00:31Z","snapshot_observed_at":"2026-08-02T11:24:16.664622Z","submitted_at":"2022-11-21T16:00:31Z","title":"Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.11602","snapshot_observed_at":"2026-08-06T19:18:22.770620Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.06016","last_updated":"2025-07-08T14:23:41Z","snapshot_observed_at":"2026-08-09T01:12:59.777085Z","submitted_at":"2025-07-08T14:23:41Z","title":"Conditional Multi-Stage Failure Recovery for Embodied Agents","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-06T19:18:22.770620Z"},"links":{"cited_paper":"/paper/2211.11602","citing_paper":"/paper/2507.06016"},"observation_digest":"sha256:b829133b9b987466da30f3952ab11096bcdadc29b5c82e9456f75fe53f35bfeb","observation_id":"f65e64b5-3d56-4455-a2bc-a2f382acbf3d","resolution":{"observed_at":"2026-08-06T19:18:22.770620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2211.11602/citation-record","integrity":"/paper/2211.11602/integrity","json":"/paper/2211.11602/citation-record.json","paper":"/paper/2211.11602"},"outbound":[],"paper":{"arxiv_id":"2211.11602","last_updated":"2022-11-21T16:00:31Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-02T11:24:16.664622Z","submitted_at":"2022-11-21T16:00:31Z","title":"Improving Multimodal Interactive Agents with Reinforcement Learning from Human 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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2211.11602."}