{"as_of":"2026-08-06T16:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:90bfe2091a76147edd469a1580a4deb9d5c900174c2c9c66f508963d98e41091","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":"2026-08-06T06:34:29.942622+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":"2026-05-21T13:06:54.002248Z","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":"2026-05-21T13:10:10.507373Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.17827","last_updated":"2025-01-29T18:18:00Z","snapshot_observed_at":"2026-08-04T08:49:09.558304Z","submitted_at":"2025-01-29T18:18:00Z","title":"Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning","version":1},"cited_work":{"arxiv_id":"2501.17827","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.17827","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Langevin soft actor-critic: Efficient exploration through uncertainty-driven critic learning.arXiv preprint arXiv:2501.17827","venue":null,"work_id":"73e91b83-a475-418f-b3ce-0a00f27ac693","year":null},"citing_paper":{"arxiv_id":"2510.23448","last_updated":"2026-04-06T16:08:29Z","snapshot_observed_at":"2026-08-02T08:25:05.148797Z","submitted_at":"2025-10-27T15:52:23Z","title":"An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learning","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-18T03:51:46.824517Z"},"links":{"cited_paper":"/paper/2501.17827","citing_paper":"/paper/2510.23448"},"observation_digest":"sha256:61c0e32616deb1e4871711cc622c9945ddc3bbd6cab96e07c9bedcf5baf421e0","observation_id":"72bcbac5-c4a8-4b96-ac66-56d555996e13","resolution":{"observed_at":"2026-05-18T03:52:22.062180Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.17827","last_updated":"2025-01-29T18:18:00Z","snapshot_observed_at":"2026-08-04T08:49:09.558304Z","submitted_at":"2025-01-29T18:18:00Z","title":"Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning","version":1},"cited_work":{"arxiv_id":"2501.17827","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.17827","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Langevin soft actor-critic: Efficient exploration through uncertainty-driven critic learning.arXiv preprint arXiv:2501.17827","venue":null,"work_id":"73e91b83-a475-418f-b3ce-0a00f27ac693","year":null},"citing_paper":{"arxiv_id":"2602.06239","last_updated":"2026-05-15T16:18:46Z","snapshot_observed_at":"2026-07-06T22:44:46.690576Z","submitted_at":"2026-02-05T22:31:07Z","title":"Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-16T06:35:30.479542Z"},"links":{"cited_paper":"/paper/2501.17827","citing_paper":"/paper/2602.06239"},"observation_digest":"sha256:c17764c207a2d33e706960198cda9831bdcf56186f7ca29a97063394b5fdc719","observation_id":"d52a2ce2-fb6f-4cdb-a4e5-fb2b57bbbe27","resolution":{"observed_at":"2026-05-16T06:37:28.595944Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.17827","last_updated":"2025-01-29T18:18:00Z","snapshot_observed_at":"2026-08-04T08:49:09.558304Z","submitted_at":"2025-01-29T18:18:00Z","title":"Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning","version":1},"cited_work":{"arxiv_id":"2501.17827","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.17827","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Langevin soft actor-critic: Efficient exploration through uncertainty-driven critic learning.arXiv preprint arXiv:2501.17827","venue":null,"work_id":"73e91b83-a475-418f-b3ce-0a00f27ac693","year":null},"citing_paper":{"arxiv_id":"2602.06239","last_updated":"2026-05-15T16:18:46Z","snapshot_observed_at":"2026-07-06T22:44:46.690576Z","submitted_at":"2026-02-05T22:31:07Z","title":"Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-21T13:06:54.002248Z"},"links":{"cited_paper":"/paper/2501.17827","citing_paper":"/paper/2602.06239"},"observation_digest":"sha256:6fb8f9b4baf27154f352d711527b4c7827893018181234201ff711bd7a6885c8","observation_id":"0ab61ee1-e5c0-4242-bfdf-b6753a8ef268","resolution":{"observed_at":"2026-05-21T13:10:10.509657Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.17827/citation-record","integrity":"/paper/2501.17827/integrity","json":"/paper/2501.17827/citation-record.json","paper":"/paper/2501.17827"},"outbound":[],"paper":{"arxiv_id":"2501.17827","last_updated":"2025-01-29T18:18:00Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T08:49:09.558304Z","submitted_at":"2025-01-29T18:18:00Z","title":"Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2501.17827."}