{"as_of":"2026-08-18T20:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f6d4b9733935c78f31ed571d631a4f7ae1851c9c82ac66c35f7692c5e88fb8d1","coverage":[{"denominator":52,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":52,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-15T02:48:50.608858Z","state":"measured"},{"denominator":52,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":52,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2605.14212/citation-record","integrity":"/paper/2605.14212/integrity","json":"/paper/2605.14212/citation-record.json","paper":"/paper/2605.14212"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2603.22918","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Yujie Zhao, Hejia Zhang, Hanxian Huang, Zhongming Yu, and Jishen Zhao","venue":null,"work_id":"e6d87867-de15-4827-b740-f4aa603f708a","year":2024},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:ec0ecccb1e6792bac5db7505ae61cbb569794182a0cb5f976ab399549b40fd9e","observation_id":"b197a18c-349e-460f-ae2f-727f5c00ec64","resolution":{"observed_at":"2026-05-15T02:49:41.462747Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"14 Figure 4: Sensitivity analysis on the stage length for designer–executor alternation","venue":null,"work_id":"3590c28c-4ac0-41c9-b839-a869f25bb253","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:037dc2ca22a57c5be95df0f1b96c6c46890cbd6e0d8fb11feefd7215c44cf63b","observation_id":"cd2d2f74-0482-4be2-b1db-dc21cf3bc76a","resolution":{"observed_at":"2026-05-15T04:04:59.002520Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"(...)","venue":null,"work_id":"cadd2d18-128e-43b1-918c-7001c4cce933","year":2025},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:19f09d1a8d2f865afdb31406c227bedb4941d13276d3911b9c6fafbfb86e5431","observation_id":"f72aec39-cb40-43ae-b72f-b8e7a2cbe420","resolution":{"observed_at":"2026-05-15T04:04:58.977237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"2aa90731-24bf-47c6-9ffd-29d736a4d47c","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:0aefc1d557acece7d673fc7ff9c0b541cfe1b57ade02760849623867f0eefaf0","observation_id":"bfbe3bbd-7f6b-44a3-bcea-49dbabe00eba","resolution":{"observed_at":"2026-05-15T04:04:58.884617Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"df92995a-93fa-4a13-8312-47293fb49251","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:2f1129e98f2d981a08e13fb12cb0c8ffdd70735d0eb3de72d303c69868a6f11b","observation_id":"355a50ef-03ae-4906-9414-0a490764ff5d","resolution":{"observed_at":"2026-05-15T04:04:58.897190Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"732830d3-98d5-4124-8e62-00c40b8677e6","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:009d689457e73fdba8cd5a461f0775b543717c13932af55ec9ba8b3188045c59","observation_id":"69672104-c9ea-48e2-9e28-b54b20cd5d84","resolution":{"observed_at":"2026-05-15T04:04:58.980782Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"68c263c8-51c1-49e7-bdd2-cd48428062cd","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:e09206c044c4a3dde38f8c988dcd1623cdc94d8c34f0def9246eea82f5b0fe36","observation_id":"833d554e-33cb-427f-b218-65b48eb44d28","resolution":{"observed_at":"2026-05-15T04:04:58.933517Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"ff5fd280-2d87-4489-86c4-86880c99f24b","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:b8d83dacfb86e240e3dbd98d97dc80681b6151c373bbde2e85394c70045146e7","observation_id":"10a0a766-138f-4f95-9cbc-77d9a7276170","resolution":{"observed_at":"2026-05-15T04:04:58.969827Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"316292fc-d492-43eb-9129-e7b307f595b5","year":2024},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:3c0ff7e7f25cef9a01e9837fa009d827adb6b07869c94bd9bde0c0fbb09d0d78","observation_id":"b10b5724-fff4-465d-a589-52ca92107ac9","resolution":{"observed_at":"2026-05-15T04:04:58.900940Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"16f12b9b-fc81-406e-b117-35feff378f1c","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:a37290debf15e77db654a63c151f8aa044a54ea494386b39391bc7ab51f0a246","observation_id":"408e5425-cfc5-4714-9090-aadc0753469c","resolution":{"observed_at":"2026-05-15T04:04:59.016465Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"53a5e384-a0e6-4d49-a98d-83fc32c765c7","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:1092f4546fd17c6f1ab909c4b6a3cf3a1aae36f317cb86a38a65f2b88886b197","observation_id":"043e218a-c289-49bd-b560-47192730151a","resolution":{"observed_at":"2026-05-15T04:04:58.995239Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"6df3a53b-e63b-4c8e-8078-e3a4204cd6cc","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:cf1d9f6fef8c5160b7d89a995576b8fe2b88e312226e23697e8c456fe6e3d64a","observation_id":"fa941ff8-4777-4a83-ab1b-48422ad77193","resolution":{"observed_at":"2026-05-15T04:04:58.998884Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"e70e7951-35d4-4b66-abe4-441936f377c8","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:075520144467cbe535f2a71a21a9ac91980097f08e3d0cb183d55511d44f6cc7","observation_id":"04a3511d-13d8-4f5b-bf1f-72ede22df9b7","resolution":{"observed_at":"2026-05-15T04:04:59.012595Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"d289cbae-5f68-4a5e-85c0-2c6f3e0c2e1c","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:1c3b9a86caf1c756b7d41bdcd7bdbe91a6bd95a0688eec245c7a44b24a9cf948","observation_id":"6426924d-1b2c-4e7a-af8d-e7f6c12454d9","resolution":{"observed_at":"2026-05-15T04:04:58.818084Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"5ed7d2bc-21a1-4ed6-b6c2-de26222149a4","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:20bd4332f2e93d077d4a0fbf250c0bc8fc889f71de6c3c4c151d2ca684fd80aa","observation_id":"08308e11-4d4a-433d-9ca8-9ee77d8b7056","resolution":{"observed_at":"2026-05-15T04:04:58.772609Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"This is a combinatorial counting problem with linear constraints","venue":null,"work_id":"83e137ce-aad3-49f9-8e79-c07a29c48714","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:670b333fcad2bd510fdef450b3af12f341ba9e1dc9bd3a72a6963252fa061652","observation_id":"4cf2484d-6cd1-4828-8e91-d6f7a5e107af","resolution":{"observed_at":"2026-05-15T04:04:58.823014Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"65e92a16-e48b-4f32-94d7-01a611528e68","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:e9043c9dc410b3487668b200dc18bc3f9c6f94c6f5dc28ce24e576fd649ee7ba","observation_id":"3e892142-58f1-42fd-8035-badfca15d5d3","resolution":{"observed_at":"2026-05-15T04:04:58.991334Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"32e64aed-c5a0-4aaa-9b98-3309a9b6a378","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:e6628c8643961387004d810db26803f2a117fe8383d6bfd240b7c82a908b105d","observation_id":"40bf0500-cfe3-4d4e-bf67-33897874a5dc","resolution":{"observed_at":"2026-05-15T04:04:58.791094Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"69fc4d8e-0c9f-4b20-b24f-91e0c7c02101","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:418fd579376701506f50137623f4055eebd8cca906e7bbfe6c59cf374c2ccf3d","observation_id":"a8882a28-5b5b-4fee-8b94-df020549033f","resolution":{"observed_at":"2026-05-15T04:04:58.857753Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"AlgebraicSolver","venue":null,"work_id":"9662c652-26b6-4096-ba55-da76a99877ca","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:68991d12a458d3420f56f3657b8aa599fa546edb20c86b60a9e61068dda5a1ca","observation_id":"2858cdaa-c3de-4ac1-a423-b7ce3f533de1","resolution":{"observed_at":"2026-05-15T04:04:59.020593Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"eversions","venue":null,"work_id":"134343c1-dec0-46f9-9859-61bb62bf6d46","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:78f2b752a25ce2bc245c8cd5844b6dd0c45178260f1daf671e5b426f83255add","observation_id":"a262460f-b86f-4f79-8a93-952836cf5a67","resolution":{"observed_at":"2026-05-15T04:04:58.945050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"fd69695b-880a-46c8-b0d7-12d5b1ae347d","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:8cef69bb5e0ca3a003587ec3d3aa09b906ea8052c69ef21a07d921607102c46f","observation_id":"c6de38e2-5f6e-46b1-80a6-2568868f178f","resolution":{"observed_at":"2026-05-15T04:04:58.764284Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"fb2af083-7298-4b68-a866-0567a2c71cb2","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:b80a961c250825db479daf447f3410a5f01264a77ffd8aa721c2b309f9422a79","observation_id":"1ee58716-8ace-4f1c-8acd-3b27214b1fcd","resolution":{"observed_at":"2026-05-15T04:04:58.836024Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"We need to compute the number of eversions until this happens","venue":null,"work_id":"4711816c-a429-4f43-ab1b-89c93e3f42c3","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:baa532b605ee2f7658c53893a5d64cf5b8abb7e00e3926f9e33724e579be39d7","observation_id":"6c23e20f-0e00-4264-a70c-952cb3a6e663","resolution":{"observed_at":"2026-05-15T04:04:58.948760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"65ec76b9-2406-4947-8d41-3bf1dc950c5c","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:e2425bce39c8a699cc3ee6ba37ccceff40fd8ec4813d7c2434cfba250a3b353a","observation_id":"0e392a22-2801-44fd-8a0e-6d6dea01d46a","resolution":{"observed_at":"2026-05-15T04:04:58.843828Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"31ed0b0b-2d21-43eb-a435-c019083fee81","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:2e88eacb344fee0459aa022f27c0b90bc6ef97be3407832f89629c2c4ecbf82c","observation_id":"1e433f53-bae9-435d-966a-1da25aad7e4f","resolution":{"observed_at":"2026-05-15T04:04:58.861568Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"189390b5-ecd2-4181-ac0e-3952d315c372","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:0c76968bc192ec6575fe6817a01994c73c229b4fd25a49dfd54ffbcbfb3608fc","observation_id":"f71727ce-ebf3-4fd8-87b6-53de6e52a3e2","resolution":{"observed_at":"2026-05-15T04:04:58.922755Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"81ae4e54-a196-4b43-b237-87601b7775a4","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:fb5ac5061d532a2fcf03a1fa516cdfc794185d1cbaa747fac4062c8eea4591a3","observation_id":"74ecce02-09be-46ab-8108-dbaab4306bdf","resolution":{"observed_at":"2026-05-15T04:04:58.850145Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"\"\"Execute Python code and return stdout/stderr","venue":null,"work_id":"e45f1cea-4a44-4234-9b87-123648c82402","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:afb32b9888b28dd451e08603e3d33f4c1cbb78102f7f9764e18af6142845e7a7","observation_id":"6d6bb50d-589d-4cf9-93ab-bb6a5e71ebb9","resolution":{"observed_at":"2026-05-15T04:04:58.917552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"9cc1dc6e-3e38-4a4e-9aa7-449bc9add54f","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:e7afad308f303b44dfd9150bc87cedafe4e4960dc5c5f2d6fae15c3c3911763a","observation_id":"c3a2a93a-f48f-433b-97c3-d7b1788c78b5","resolution":{"observed_at":"2026-05-15T04:04:58.937068Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"06bda28e-f520-42ea-90ad-23717d899693","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:e5a0c4694d33f800ff10251a4dbc952e16cbb5c25f33cd56dcaea1def3cc4e22","observation_id":"a3fbcb87-b90e-4712-9fe3-fa5095c1290e","resolution":{"observed_at":"2026-05-15T04:04:58.786199Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Let me test with the example","venue":null,"work_id":"c072db21-f278-4789-933a-a5a00b535b91","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:e9920ffd5389792c1c4fd684f20d5a9f7249f00fc3eddcf67cb3912c2021880c","observation_id":"6eb09084-9df5-4ce0-be60-28a16b7e038c","resolution":{"observed_at":"2026-05-15T04:04:58.984117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"if current < M , then M is the maximum element > current","venue":null,"work_id":"4065e27b-1206-413d-aea0-c920ea660330","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:84d5b59150c9d46d127ef2171b61d241d02f2597d4f5b05583005de36a418e29","observation_id":"05108c5e-bcbb-4b3f-aeff-2d8bf4ff62ea","resolution":{"observed_at":"2026-05-15T04:04:58.876933Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"It only describes the problem and the insight but doesn’t give a working solution","venue":null,"work_id":"883a3778-33c8-438f-ba7c-2631a3d643d6","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:cbe9c727440c50db366be0e8b865708224a0cd6c4db88fb6ffc55c3a462721b4","observation_id":"c03b683a-0b7d-41d7-ad56-ead13c54a175","resolution":{"observed_at":"2026-05-15T04:04:58.888956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"c2a39040-20e7-4209-986b-5d743b0d5191","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:6e5aa6dd57e52ce7a480e67b650254b3aa0c6292fce052828823f99aa9ee28a2","observation_id":"acf96b50-5de3-492f-89ef-22e8669551a6","resolution":{"observed_at":"2026-05-15T04:04:58.941446Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"6bbadc8b-c91e-4575-ae3e-c3328ef46c60","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:105b711dd859358021eb2cb74c072244443aa05708891f4f6e7ab3eb59d9297c","observation_id":"75d899d0-3126-43e1-9172-fbb89053f550","resolution":{"observed_at":"2026-05-15T04:04:58.973285Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"max of elements > current","venue":null,"work_id":"48624504-e59f-48af-a0fd-5b48442476e7","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:520bb330e22903a78f6ba0d995fe61de4cdb1e9263139d03ab7b6366ac2eadb7","observation_id":"a1b4e00f-f1f5-4230-ae0b-26c4084f912b","resolution":{"observed_at":"2026-05-15T04:04:58.872067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"99e580ca-0649-4efa-9e0d-4f3ef1bfdede","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:b456fa2c19ceacab5bc7f2ad3a765aa014a534e844027727b8ab45a2d1aaf700","observation_id":"77c3956e-6c09-462b-ba2d-f73e252ffd47","resolution":{"observed_at":"2026-05-15T04:04:58.830344Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"27912cbd-b6fa-4f89-a887-f67d9720cd33","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:4f43445d686349b1d4ae89e764fc584c00bde1ae7c7220811704b0eaefde6753","observation_id":"3bab8f90-e416-4ae2-aced-ce5bdd607f24","resolution":{"observed_at":"2026-05-15T04:04:58.910346Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"f1e91355-d8f3-4dec-bf09-08e727a606bc","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:a94c4c863a2c2371bf5961f2833443c8244ef5620d4fecb9c8fd5464c160d156","observation_id":"c8175efe-ed9e-4430-87e7-b6b86a204458","resolution":{"observed_at":"2026-05-15T04:04:58.951969Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"\\n\".join(map(str, results))) if __name__ ==","venue":null,"work_id":"c6bc8cc9-26a5-408f-a446-14102fa5c768","year":2024},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:369954d0d38a9127ce18d9eb2e6e9c24dd9d965f7888e8cfc1acf077832e4197","observation_id":"dbb267c0-d8b6-48a6-bb78-ab09efc9dcb2","resolution":{"observed_at":"2026-05-15T04:04:58.892589Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"b1da2a4f-a12d-4627-9e80-bdd271d61b5b","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:dcebcac274f55c1149607cfd4dec4a0dd7107ea95dae45ecdd477cd881ad05e7","observation_id":"12ea2b69-6678-488a-9242-de7eefa9801a","resolution":{"observed_at":"2026-05-15T04:04:58.955270Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"MathSolver","venue":null,"work_id":"2b27c8fb-a586-4095-b3e7-e41a971797b4","year":2024},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:077759bc13f1494cb8750d59bd027df9ae2e8b3d4c5c6f2df1ee0f27dd751ea1","observation_id":"cd28643a-0479-44a2-bcc7-9c0e0a01d77c","resolution":{"observed_at":"2026-05-15T04:04:58.803958Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"813dfd04-2eb2-490f-b8e6-92f7468f2c4a","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:68b899fee1034ca1c9a4ebca247cc43cd9dac17595a4f2e192277598de2709a5","observation_id":"a5339e4d-2a65-4eec-bf02-7e978c787604","resolution":{"observed_at":"2026-05-15T04:04:58.797934Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"591bfc3c-d050-41ce-a8b5-dd1bb0f1609f","year":2024},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:1bbe642f744eb7753f73ae8452bf19623b3cec08f4c49eb6a267af97d8764530","observation_id":"aea23084-f501-406a-93e4-34f35797cec9","resolution":{"observed_at":"2026-05-15T04:04:58.776929Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"68349158-66e5-4293-8db7-5d85c27e39f7","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:7c477ada79b91f4de6b522af5af3c212db549c1def2cdf9d880baa6f00557044","observation_id":"868e0ead-a7f3-468c-b141-39f25730b36f","resolution":{"observed_at":"2026-05-15T04:04:58.926501Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"b9842030-0540-4974-b140-9baea5baa7b7","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:50edbcb68fbb2c754e051db3662c0fe22e3e429747b0e458974bf16ffeb5cf00","observation_id":"57ecd853-b4ef-4f64-9a83-e50e54ad7b53","resolution":{"observed_at":"2026-05-15T04:04:58.814064Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"eca667b9-2e12-4023-b0f0-9c53809469cd","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:8a23ad86de0ac595fc4c8383cf9ed0c5df1e03ecf05f525646f22ec4a523fc44","observation_id":"affded30-a78d-4f4f-9f1c-891e47baf6dd","resolution":{"observed_at":"2026-05-15T04:04:58.966384Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"20664ba6-2da4-40c4-ace5-db7a4ad07302","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:fd9a19be0ad7f350a15bec60de53d9c4af9a93117c7044996b33965d48b47157","observation_id":"47f0e61c-3cc9-4634-a1d5-01c96cef010e","resolution":{"observed_at":"2026-05-15T04:04:58.962411Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"eight circles of radius 34 are sequentially tangent, and two of the circles are tangent to AB and BC of triangle ABC, respectively","venue":null,"work_id":"044855bc-17ec-45fe-a42e-b6c9bbca91d6","year":2024},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:2d6429ab5734ec007f6685f9239f62ee25151a0aa107e9eec9c21c97af7b93cb","observation_id":"36fe7b2f-948b-42f5-9c6d-ec44abd7fb4c","resolution":{"observed_at":"2026-05-15T04:04:58.809924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"8a30743e-9fe8-4520-9006-2c9467fa8939","year":null},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:6daa08c758dfa48b9c190bb6f3ff6800b0bd4ce876edd819c7ae5559c4e3aad3","observation_id":"f0339a00-87ee-402c-8c4b-03aebdb031d8","resolution":{"observed_at":"2026-05-15T04:04:58.866202Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"238 = 2 * 7 * 17; 2023 = 7 * 17^2","venue":null,"work_id":"0ab89606-09bb-4a3e-9ad5-636e348f7074","year":2023},"citing_paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-15T02:48:50.608858Z"},"links":{"citing_paper":"/paper/2605.14212"},"observation_digest":"sha256:df2d37cb3f1522d5f3bcae7642bf7389eb6bdbce1b88288c278c53f0a84c2c14","observation_id":"017d6586-7977-406e-883a-7d3aa6dd3b80","resolution":{"observed_at":"2026-05-15T04:04:58.905957Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.14212","last_updated":"2026-05-14T00:11:27Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-11T10:47:18.974754Z","submitted_at":"2026-05-14T00:11:27Z","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":2,"unresolved":34,"verified_exact":1,"verified_fuzzy":15},"total_outbound_references":52},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 0 inbound Pith citation observations for arXiv:2605.14212."}