{"as_of":"2026-08-08T21:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8e8616d69c42bcb80aed269b56ce7362b8ce3718b7816fa76454303f582ed32c","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":"2026-08-08T06:32:00.761636+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":"2026-08-05T00:28:25.991755Z","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":"2026-05-11T05:16:32.885338Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1502.02362","last_updated":"2015-05-20T23:29:49Z","snapshot_observed_at":"2026-07-06T04:08:35.216545Z","submitted_at":"2015-02-09T05:09:25Z","title":"Counterfactual Risk Minimization: Learning from Logged Bandit Feedback","version":2},"cited_work":{"arxiv_id":"1502.02362","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1502.02362","snapshot_observed_at":"2026-07-04T19:44:05.158840Z","title":"Counterfactual risk minimization: Learning from logged bandit feedback","venue":null,"work_id":"f3f77e90-8970-4a4c-a0a1-555eb864272e","year":2015},"citing_paper":{"arxiv_id":"1606.06565","last_updated":"2016-07-25T17:23:29Z","snapshot_observed_at":"2026-07-06T05:00:46.434335Z","submitted_at":"2016-06-21T13:37:05Z","title":"Concrete Problems in AI Safety","version":2},"reference_index":152,"source":"pdf_text","source_observed_at":"2026-05-11T05:16:31.970352Z"},"links":{"cited_paper":"/paper/1502.02362","citing_paper":"/paper/1606.06565"},"observation_digest":"sha256:be9484d47d5bb73ad0d0a10a9d5ca6e669a7a312bf40025bc2199feda076dbf4","observation_id":"71412fdf-9f0f-470f-be84-ad3cc5d8f4f6","resolution":{"observed_at":"2026-07-04T19:44:05.158840Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1502.02362","last_updated":"2015-05-20T23:29:49Z","snapshot_observed_at":"2026-07-06T04:08:35.216545Z","submitted_at":"2015-02-09T05:09:25Z","title":"Counterfactual Risk Minimization: Learning from Logged Bandit Feedback","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1502.02362","snapshot_observed_at":"2026-08-05T00:28:25.991755Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.00750","last_updated":"2026-08-01T16:33:15Z","snapshot_observed_at":"2026-08-06T23:19:16.536876Z","submitted_at":"2026-08-01T16:33:15Z","title":"Hierarchical Residual Policy Optimization for Generative Recommendations","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-05T00:28:25.991755Z"},"links":{"cited_paper":"/paper/1502.02362","citing_paper":"/paper/2608.00750"},"observation_digest":"sha256:3b36fffc64c896bf1a9081fdd342b0bc7477ea0266d38717a4147d62e860f634","observation_id":"64229d29-411d-45c4-beff-db359364cd2d","resolution":{"observed_at":"2026-08-05T00:28:25.991755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1502.02362/citation-record","integrity":"/paper/1502.02362/integrity","json":"/paper/1502.02362/citation-record.json","paper":"/paper/1502.02362"},"outbound":[],"paper":{"arxiv_id":"1502.02362","last_updated":"2015-05-20T23:29:49Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T04:08:35.216545Z","submitted_at":"2015-02-09T05:09:25Z","title":"Counterfactual Risk Minimization: Learning from Logged Bandit 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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:1502.02362."}