{"as_of":"2026-08-21T16:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8c43c475d76a23d0ae576fbcd6ae388f019c671d4822fefff148a7fdd6b21b4f","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":"2026-08-21T06:32:19.484+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":"2026-06-28T14:18:02.880239Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":12,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.14151","last_updated":"2024-07-19T09:29:38Z","snapshot_observed_at":"2026-08-17T10:16:50.173332Z","submitted_at":"2024-07-19T09:29:38Z","title":"A Comparative Study of Deep Reinforcement Learning Models: DQN vs PPO vs A2C","version":1},"cited_work":{"arxiv_id":"2407.14151","doi":"10.48550/arxiv.2407.14151","metadata_source":"arxiv_reference","pith_arxiv_id":"2407.14151","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Acomparativestudyofdeep reinforcement learning models: Dqn vs ppo vs a2c","venue":"arXiv (Cornell University)","work_id":"df03b2ba-bd6a-45a4-a34e-5880f27036a1","year":2024},"citing_paper":{"arxiv_id":"2604.12667","last_updated":"2026-04-16T08:32:15Z","snapshot_observed_at":"2026-08-12T19:15:31.689593Z","submitted_at":"2026-04-14T12:38:21Z","title":"Safe reinforcement learning with online filtering for fatigue-predictive human-robot task planning and allocation in production","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-10T14:49:27.919651Z"},"links":{"cited_paper":"/paper/2407.14151","citing_paper":"/paper/2604.12667"},"observation_digest":"sha256:d9c7db078dfdf3e36f47992c9528ac7ce05f66214d194278a342932b531b9e4f","observation_id":"05e40a0c-1aab-4e82-8335-dc99b16a3a0a","resolution":{"observed_at":"2026-05-10T14:50:30.209009Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14151","last_updated":"2024-07-19T09:29:38Z","snapshot_observed_at":"2026-08-17T10:16:50.173332Z","submitted_at":"2024-07-19T09:29:38Z","title":"A Comparative Study of Deep Reinforcement Learning Models: DQN vs PPO vs A2C","version":1},"cited_work":{"arxiv_id":"2407.14151","doi":"10.48550/arxiv.2407.14151","metadata_source":"arxiv_reference","pith_arxiv_id":"2407.14151","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Acomparativestudyofdeep reinforcement learning models: Dqn vs ppo vs a2c","venue":"arXiv (Cornell University)","work_id":"df03b2ba-bd6a-45a4-a34e-5880f27036a1","year":2024},"citing_paper":{"arxiv_id":"2606.02049","last_updated":"2026-06-01T10:39:34Z","snapshot_observed_at":"2026-08-11T08:30:47.102021Z","submitted_at":"2026-06-01T10:39:34Z","title":"Explainable Data-driven Deep Reinforcement Learning Methods for Optimal Energy Management in Buildings","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-06-28T14:18:02.880239Z"},"links":{"cited_paper":"/paper/2407.14151","citing_paper":"/paper/2606.02049"},"observation_digest":"sha256:1e8195ff6f8a7aab70bd9dc9878904191949e62383e51ce773cc3a7eae2d210c","observation_id":"ca8f7977-1004-49ea-bcc0-f96369c494d6","resolution":{"observed_at":"2026-07-01T23:26:23.232896Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2407.14151/citation-record","integrity":"/paper/2407.14151/integrity","json":"/paper/2407.14151/citation-record.json","paper":"/paper/2407.14151"},"outbound":[],"paper":{"arxiv_id":"2407.14151","last_updated":"2024-07-19T09:29:38Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T10:16:50.173332Z","submitted_at":"2024-07-19T09:29:38Z","title":"A Comparative Study of Deep Reinforcement Learning Models: DQN vs PPO vs A2C"},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2407.14151."}