{"as_of":"2026-08-13T22:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e42be0d5595e662f41814ef36088121229bab06e9b716e3872ce6111ae86c6dd","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T19:51:19.836020Z","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":"2026-08-05T11:49:15.477884Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1709.06011","last_updated":"2017-09-18T15:37:45Z","snapshot_observed_at":"2026-07-06T06:00:08.350506Z","submitted_at":"2017-09-18T15:37:45Z","title":"Guided Deep Reinforcement Learning for Swarm Systems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1709.06011","snapshot_observed_at":"2026-08-11T19:51:19.836020Z","title":"arXiv preprint arXiv:1709.06011 (2017) https://doi.org/10","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.06333","last_updated":"2025-05-24T12:49:59Z","snapshot_observed_at":"2026-08-11T19:43:36.756536Z","submitted_at":"2024-12-09T09:34:40Z","title":"Augmenting the action space with conventions to improve multi-agent cooperation in Hanabi","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T19:51:19.836020Z"},"links":{"cited_paper":"/paper/1709.06011","citing_paper":"/paper/2412.06333"},"observation_digest":"sha256:1f05f2435c1d19b8d792c34dd0891f6bffbc68741db2c84f938f9d8a0a6d3e06","observation_id":"dfb9fe9c-1913-460c-be29-2afc2c1eb481","resolution":{"observed_at":"2026-08-11T19:51:19.836020Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1709.06011","last_updated":"2017-09-18T15:37:45Z","snapshot_observed_at":"2026-07-06T06:00:08.350506Z","submitted_at":"2017-09-18T15:37:45Z","title":"Guided Deep Reinforcement Learning for Swarm Systems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1709.06011","snapshot_observed_at":"2026-08-07T14:15:35.804796Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.19637","last_updated":"2025-05-26T07:54:58Z","snapshot_observed_at":"2026-08-12T06:27:30.173262Z","submitted_at":"2025-05-26T07:54:58Z","title":"Adaptive Episode Length Adjustment for Multi-agent Reinforcement Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T14:15:35.804796Z"},"links":{"cited_paper":"/paper/1709.06011","citing_paper":"/paper/2505.19637"},"observation_digest":"sha256:ba045efc0883599e7c9a6ff36fc83d5396126067cf19cd00cb93be2c9ee6b868","observation_id":"920462f9-38b6-4e5d-ac7a-2511318944c4","resolution":{"observed_at":"2026-08-07T14:15:35.804796Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1709.06011","last_updated":"2017-09-18T15:37:45Z","snapshot_observed_at":"2026-07-06T06:00:08.350506Z","submitted_at":"2017-09-18T15:37:45Z","title":"Guided Deep Reinforcement Learning for Swarm Systems","version":1},"cited_work":{"arxiv_id":"1709.06011","doi":null,"metadata_source":"pith","pith_arxiv_id":"1709.06011","snapshot_observed_at":"2026-08-05T11:49:15.477884Z","title":"Guided Deep Reinforcement Learning for Swarm Systems","venue":"cs.MA","work_id":"cd45e808-e79c-428d-b7fc-852627b4db4b","year":2017},"citing_paper":{"arxiv_id":"2509.02271","last_updated":"2025-09-02T12:48:15Z","snapshot_observed_at":"2026-08-06T17:44:05.926754Z","submitted_at":"2025-09-02T12:48:15Z","title":"VariAntNet: Learning Decentralized Control of Multi-Agent Systems","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T11:49:14.911814Z"},"links":{"cited_paper":"/paper/1709.06011","citing_paper":"/paper/2509.02271"},"observation_digest":"sha256:f045526331d3d1ecf316ada4905aa176b993b592351992c77d6d000e75eed5be","observation_id":"81c1f787-00f8-4f75-8fbe-f7641f6751a6","resolution":{"observed_at":"2026-08-05T11:49:15.551262Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"1709.06011","last_updated":"2017-09-18T15:37:45Z","snapshot_observed_at":"2026-07-06T06:00:08.350506Z","submitted_at":"2017-09-18T15:37:45Z","title":"Guided Deep Reinforcement Learning for Swarm Systems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1709.06011","snapshot_observed_at":"2026-07-31T23:51:54.705473Z","title":"arXiv preprint arXiv:1709.06011 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.23333","last_updated":"2026-07-25T19:11:15Z","snapshot_observed_at":"2026-08-03T00:37:21.399146Z","submitted_at":"2026-07-25T19:11:15Z","title":"Training with (Swap) Regret Loss in a Single-Layer Self-Attention Model: A Case Study on the Probability Simplex","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-07-31T23:51:54.705473Z"},"links":{"cited_paper":"/paper/1709.06011","citing_paper":"/paper/2607.23333"},"observation_digest":"sha256:2cdcf59519dea7a19e26d501fd3959a3e318e34b3b54b4516bc9045330ae67be","observation_id":"a9e44757-77f9-45a9-9e5e-5379dd561b55","resolution":{"observed_at":"2026-07-31T23:51:54.705473Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1709.06011/citation-record","integrity":"/paper/1709.06011/integrity","json":"/paper/1709.06011/citation-record.json","paper":"/paper/1709.06011"},"outbound":[],"paper":{"arxiv_id":"1709.06011","last_updated":"2017-09-18T15:37:45Z","latest_version":1,"primary_category":"cs.MA","snapshot_observed_at":"2026-07-06T06:00:08.350506Z","submitted_at":"2017-09-18T15:37:45Z","title":"Guided Deep Reinforcement Learning for Swarm Systems"},"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 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:1709.06011."}