{"as_of":"2026-08-11T11:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:16ada2cdd94fa80fbf985188bc308b8805e7ac8a45832f7a5808f36dc2abbecf","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":"2026-08-11T06:34:44.6726+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":"2026-08-06T14:10:34.084263Z","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":"2026-05-21T00:03:51.905235Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2010.03956","last_updated":"2020-10-05T03:43:06Z","snapshot_observed_at":"2026-07-06T10:02:38.963347Z","submitted_at":"2020-10-05T03:43:06Z","title":"Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy Games","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.03956","snapshot_observed_at":"2026-08-06T14:10:34.084263Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.19725","last_updated":"2025-07-26T00:49:25Z","snapshot_observed_at":"2026-08-10T09:29:02.250938Z","submitted_at":"2025-07-26T00:49:25Z","title":"Minding Motivation: The Effect of Intrinsic Motivation on Agent Behaviors","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-06T14:10:34.084263Z"},"links":{"cited_paper":"/paper/2010.03956","citing_paper":"/paper/2507.19725"},"observation_digest":"sha256:a2358cfb39231053c7872cf326c93b0b115236d25f08d3e75b1f42bf3e7bd406","observation_id":"5416424b-c227-4207-bae4-0219b47b4a12","resolution":{"observed_at":"2026-08-06T14:10:34.084263Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.03956","last_updated":"2020-10-05T03:43:06Z","snapshot_observed_at":"2026-07-06T10:02:38.963347Z","submitted_at":"2020-10-05T03:43:06Z","title":"Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy Games","version":1},"cited_work":{"arxiv_id":"2010.03956","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2010.03956","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy Games","venue":null,"work_id":"a53ec52b-22ef-4743-b56b-ff7d391397c5","year":2020},"citing_paper":{"arxiv_id":"2605.02075","last_updated":"2026-05-16T16:12:11Z","snapshot_observed_at":"2026-08-11T02:47:14.534012Z","submitted_at":"2026-05-03T22:26:52Z","title":"Graph Transformers and Stabilized Reinforcement Learning for Large-Scale Dynamic Routing Modulation and Spectrum Allocation in Elastic Optical Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-08T18:47:04.091987Z"},"links":{"cited_paper":"/paper/2010.03956","citing_paper":"/paper/2605.02075"},"observation_digest":"sha256:3e7e7b00ed689e15adecf9bbdcb984d9977a77092020c5164900ed5a79e15b83","observation_id":"13ff3d6c-8f74-4abb-a1e5-9100a5f0310c","resolution":{"observed_at":"2026-05-09T06:10:43.161333Z","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":"2010.03956","last_updated":"2020-10-05T03:43:06Z","snapshot_observed_at":"2026-07-06T10:02:38.963347Z","submitted_at":"2020-10-05T03:43:06Z","title":"Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy Games","version":1},"cited_work":{"arxiv_id":"2010.03956","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2010.03956","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy Games","venue":null,"work_id":"a53ec52b-22ef-4743-b56b-ff7d391397c5","year":2020},"citing_paper":{"arxiv_id":"2605.02075","last_updated":"2026-05-16T16:12:11Z","snapshot_observed_at":"2026-08-11T02:47:14.534012Z","submitted_at":"2026-05-03T22:26:52Z","title":"Graph Transformers and Stabilized Reinforcement Learning for Large-Scale Dynamic Routing Modulation and Spectrum Allocation in Elastic Optical Networks","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-21T00:02:01.826213Z"},"links":{"cited_paper":"/paper/2010.03956","citing_paper":"/paper/2605.02075"},"observation_digest":"sha256:1232627e182336e9f502b7c7aa80ef3b87aa0a01f9532084b4f094aa00298087","observation_id":"5561a79d-0344-4912-83e4-94236026458b","resolution":{"observed_at":"2026-05-21T00:03:51.909659Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2010.03956/citation-record","integrity":"/paper/2010.03956/integrity","json":"/paper/2010.03956/citation-record.json","paper":"/paper/2010.03956"},"outbound":[],"paper":{"arxiv_id":"2010.03956","last_updated":"2020-10-05T03:43:06Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T10:02:38.963347Z","submitted_at":"2020-10-05T03:43:06Z","title":"Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy Games"},"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 3 inbound Pith citation observations for arXiv:2010.03956."}