{"as_of":"2026-08-08T04:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9eb7766eb9b9b3d1c9bc85416d9dd733df3254881cf0d5f141076b9f0e5abb15","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":"2026-08-07T06:34:17.273281+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":"2026-08-06T04:39:06.014406Z","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":"2026-05-11T12:46:27.860463Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.07523","last_updated":"2025-05-22T12:39:27Z","snapshot_observed_at":"2026-07-06T20:34:44.083385Z","submitted_at":"2025-02-11T12:55:32Z","title":"Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.07523","snapshot_observed_at":"2026-08-06T04:39:06.014406Z","title":"Scaling off-policy reinforcement learning with batch and weight normalization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.03194","last_updated":"2025-08-05T08:03:12Z","snapshot_observed_at":"2026-08-06T11:32:36.516059Z","submitted_at":"2025-08-05T08:03:12Z","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T04:39:06.014406Z"},"links":{"cited_paper":"/paper/2502.07523","citing_paper":"/paper/2508.03194"},"observation_digest":"sha256:6b10e71d6cac3c2f58e8c71b0432a5a97c896f8e257358cdacdc0ebf66f10815","observation_id":"47bb1096-30d7-43a5-a96a-02dbf597181b","resolution":{"observed_at":"2026-08-06T04:39:06.014406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.07523","last_updated":"2025-05-22T12:39:27Z","snapshot_observed_at":"2026-07-06T20:34:44.083385Z","submitted_at":"2025-02-11T12:55:32Z","title":"Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization","version":2},"cited_work":{"arxiv_id":"2502.07523","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.07523","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Scaling off-policy reinforcement learning with batch and weight normalization","venue":null,"work_id":"3d775a8d-5923-498f-8fc0-459f008f96fb","year":2025},"citing_paper":{"arxiv_id":"2604.18978","last_updated":"2026-05-07T15:47:31Z","snapshot_observed_at":"2026-08-02T06:20:27.077117Z","submitted_at":"2026-04-21T01:59:54Z","title":"Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-10T02:55:22.577012Z"},"links":{"cited_paper":"/paper/2502.07523","citing_paper":"/paper/2604.18978"},"observation_digest":"sha256:4d3393a2dd11a0d7702ccc3d7899a7f8c56a98dac5efe9dc037fc1599ab7527c","observation_id":"8e5df350-6c5b-40a5-8584-b9664a6ecbbb","resolution":{"observed_at":"2026-05-11T12:46:27.863900Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.07523","last_updated":"2025-05-22T12:39:27Z","snapshot_observed_at":"2026-07-06T20:34:44.083385Z","submitted_at":"2025-02-11T12:55:32Z","title":"Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization","version":2},"cited_work":{"arxiv_id":"2502.07523","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.07523","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Scaling off-policy reinforcement learning with batch and weight normalization","venue":null,"work_id":"3d775a8d-5923-498f-8fc0-459f008f96fb","year":2025},"citing_paper":{"arxiv_id":"2605.04368","last_updated":"2026-05-06T00:10:17Z","snapshot_observed_at":"2026-07-06T23:17:09.246351Z","submitted_at":"2026-05-06T00:10:17Z","title":"Extending Differential Temporal Difference Methods for Episodic Problems","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-08T18:19:57.472765Z"},"links":{"cited_paper":"/paper/2502.07523","citing_paper":"/paper/2605.04368"},"observation_digest":"sha256:0166473299ed0248617f5fc9fd0f55bc96c17585314ddd512250164d7390642d","observation_id":"a3db05dd-9295-402a-bc36-ca5c22c7c0fe","resolution":{"observed_at":"2026-05-09T06:35:38.842202Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.07523/citation-record","integrity":"/paper/2502.07523/integrity","json":"/paper/2502.07523/citation-record.json","paper":"/paper/2502.07523"},"outbound":[],"paper":{"arxiv_id":"2502.07523","last_updated":"2025-05-22T12:39:27Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T20:34:44.083385Z","submitted_at":"2025-02-11T12:55:32Z","title":"Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2502.07523."}