{"as_of":"2026-08-14T01:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3e017aa37dc71addb5a0df35fe7a17c0f8c7d2376c2dd9ad1baba7cda063a52d","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T10:48:42.230024Z","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":"2026-08-12T10:48:44.399833Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1702.03006","last_updated":"2017-02-09T22:36:25Z","snapshot_observed_at":"2026-07-06T05:29:31.198406Z","submitted_at":"2017-02-09T22:36:25Z","title":"Multi-step Off-policy Learning Without Importance Sampling Ratios","version":1},"cited_work":{"arxiv_id":"1702.03006","doi":null,"metadata_source":"pith","pith_arxiv_id":"1702.03006","snapshot_observed_at":"2026-08-12T10:48:44.399833Z","title":"Multi-step Off-policy Learning Without Importance Sampling Ratios","venue":"cs.LG","work_id":"594204f6-ebf4-47bf-bbbd-679e68b7072d","year":2017},"citing_paper":{"arxiv_id":"2411.18892","last_updated":"2025-02-01T23:49:26Z","snapshot_observed_at":"2026-08-13T05:19:39.475481Z","submitted_at":"2024-11-28T03:53:14Z","title":"A Comprehensive Survey of Reinforcement Learning: From Algorithms to Practical Challenges","version":2},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-12T10:48:42.230024Z"},"links":{"cited_paper":"/paper/1702.03006","citing_paper":"/paper/2411.18892"},"observation_digest":"sha256:77bb883b37896b17799c0df56dfc4a3d9ec6774a5dd6a28a7e0bc3bee219acbc","observation_id":"b6dfa5e0-1fec-4b0e-bfeb-b119dbe2fbeb","resolution":{"observed_at":"2026-08-12T10:48:44.427484Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1702.03006/citation-record","integrity":"/paper/1702.03006/integrity","json":"/paper/1702.03006/citation-record.json","paper":"/paper/1702.03006"},"outbound":[],"paper":{"arxiv_id":"1702.03006","last_updated":"2017-02-09T22:36:25Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T05:29:31.198406Z","submitted_at":"2017-02-09T22:36:25Z","title":"Multi-step Off-policy Learning Without Importance Sampling Ratios"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:1702.03006."}