{"as_of":"2026-08-04T19:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:67992993313346c8420d83fef0b726126eae9cc503e8e4aa83414aac73037c44","coverage":[{"denominator":124,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-22T13:34:27.152447Z","state":"measured"},{"denominator":101,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":101,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T16:10:06.564268Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.17086","snapshot_observed_at":"2026-08-01T16:10:06.564268Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18102","last_updated":"2026-07-21T15:53:04Z","snapshot_observed_at":"2026-08-02T22:00:09.838023Z","submitted_at":"2026-07-20T16:03:15Z","title":"FinSAgent: Corpus-Aligned Multi-Agent RAG Framework for Evidence-Grounded SEC Filing Question Answering","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T16:10:06.564268Z"},"links":{"cited_paper":"/paper/2505.17086","citing_paper":"/paper/2607.18102"},"observation_digest":"sha256:5329caeb0a608b6a311ae039fa1dd2ed3e3357448468e28251331061439ccb8c","observation_id":"e41afb32-9fe0-4b29-b785-a5a74478efa8","resolution":{"observed_at":"2026-08-01T16:10:06.564268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.17086/citation-record","integrity":"/paper/2505.17086/integrity","json":"/paper/2505.17086/citation-record.json","paper":"/paper/2505.17086"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":"2303.08774","doi":"10.1002/tea.20265","metadata_source":"pith","pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"GPT-4 Technical Report","venue":"cs.CL","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","year":2023},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:fdd6e5e64854501930eb7e538496b4f7761e7b6fee6183b6efeb4c6c244dffe3","observation_id":"c3e53cb1-ebd0-4c7c-a552-6bda95b151f5","resolution":{"observed_at":"2026-05-22T13:34:53.061140Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2024.acl-long.545","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"7cf4a055-ad77-4d39-93f2-5fdfb3479844","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:8aa46c4d5a03dd1b6298b6694dfa77eca4c54ee92fd7f3dda5c10e7dfe60a2dc","observation_id":"6dc05c2c-9f56-41f0-b7e8-0a2e8ebbcf8c","resolution":{"observed_at":"2026-05-22T13:34:52.958724Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"1247660a-e843-46ec-af8c-cd8a0a462c49","year":2023},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:74c5d45047fc87366a5667b69413b004f471c0162b88a6842af5648eedbfa930","observation_id":"93076ea8-79f7-4b33-8cf8-bf66412e49af","resolution":{"observed_at":"2026-05-22T13:34:54.010025Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.14740","last_updated":"2024-02-26T18:26:25Z","snapshot_observed_at":"2026-07-06T17:34:07.737296Z","submitted_at":"2024-02-22T17:52:34Z","title":"Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs","version":2},"cited_work":{"arxiv_id":"2402.14740","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.14740","snapshot_observed_at":"2026-07-09T08:56:06.435604Z","title":"Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs","venue":"cs.LG","work_id":"7bb8f9ec-1241-4472-a4fa-c636c6d79892","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2402.14740","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:abe220e45bb1fd3e3eca82687456452543dbf3d5f1077ae7b7c0a195603876ab","observation_id":"aa9543ae-9ede-448c-9588-cd8323be6273","resolution":{"observed_at":"2026-05-22T13:34:53.062849Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-09T08:46:06.874657Z","title":null,"venue":null,"work_id":"7789f786-76d0-4cc1-b01d-adfe8d140e8f","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:dc5982d54af74974e293a45d2a5d80a12be887cb2076b9f495bb1c5f29b1a802","observation_id":"01b51e4e-a9d4-4bbe-a3ac-1753bdbd0614","resolution":{"observed_at":"2026-05-22T13:34:53.986081Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"InThe Twelfth International Conference on Learning Representations","venue":null,"work_id":"ac609627-1a42-4546-9123-4e81f9914025","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:8aa85fee60cbe42c33632a36151519ee0f89e320af720739d51cba9dfe17cb7e","observation_id":"a5eb2931-e5ad-4230-b801-0a29a7ff016a","resolution":{"observed_at":"2026-05-22T13:34:53.999681Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.01540","last_updated":"2016-06-05T17:54:48Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2016-06-05T17:54:48Z","title":"OpenAI Gym","version":1},"cited_work":{"arxiv_id":"1606.01540","doi":"10.1109/jssc.2019","metadata_source":"pith","pith_arxiv_id":"1606.01540","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"OpenAI Gym","venue":"cs.LG","work_id":"6af98f3f-f074-41ae-a689-7dd7b4b8efde","year":2016},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/1606.01540","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:e2819ed45a8abfd59436d4dcb5fa386ecac2337556fcb2b3c6d5833ec6569915","observation_id":"ec28b629-adad-41dc-8d0f-e5676fc14723","resolution":{"observed_at":"2026-05-22T13:34:53.040650Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"cba17096-9394-4580-9be9-e3f4b6af1417","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:4d39ecc7be04aa57e1ac21162a9393ce30db5d5f1b7ecc839b92d8ac0cd7ed3b","observation_id":"4bbf7ae1-2004-4a1b-b8d3-4ed828463337","resolution":{"observed_at":"2026-05-22T13:34:54.006338Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-08T18:25:26.397231Z","title":null,"venue":null,"work_id":"ef350748-fad7-41ba-a8c3-2be10bfcd6c3","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:ed0880f9a70190bccaaca95defb9b9cacfc731ac1d40f89265656d72e012d6de","observation_id":"f570b6a2-2d4e-4191-b922-26e98f6ac7be","resolution":{"observed_at":"2026-05-22T13:34:53.990196Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03216","last_updated":"2025-12-12T11:26:32Z","snapshot_observed_at":"2026-07-06T17:25:35.493362Z","submitted_at":"2024-02-05T17:26:49Z","title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","version":5},"cited_work":{"arxiv_id":"2402.03216","doi":"10.48550/arxiv.2402.03216","metadata_source":"pith","pith_arxiv_id":"2402.03216","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","venue":"cs.CL","work_id":"a9435752-4e49-42bd-95b4-0fec975633c8","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2402.03216","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:01779112c6eea520613ab60b64959337b04f75f9dfa9c04af5cfe497b5db9a24","observation_id":"32f1a6da-88fd-4f65-860d-6eda1a50d85c","resolution":{"observed_at":"2026-05-22T13:34:53.051298Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"8f21fa04-f943-41d5-ade3-39985b82d491","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:e07018ec19c3ccc1b3fdfa7299cbd71c432af39f0a3aed610656dd39f8e0f8e8","observation_id":"1bba08f2-eb2a-4215-8203-97923389cd04","resolution":{"observed_at":"2026-05-22T13:34:54.003246Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"InThe Thirty-eighth Annual Conference on Neural Information Processing Systems","venue":null,"work_id":"54a402fd-6278-4929-be78-3572086382d8","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:cf31231d0e69f47d1bfb678f75d113847097a4bd34038c5d22cc8f8fdaa8715b","observation_id":"76164afb-cf1e-4624-97a1-f7e57cfb2728","resolution":{"observed_at":"2026-05-22T13:34:53.992553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.19470","last_updated":"2025-09-23T03:45:42Z","snapshot_observed_at":"2026-07-06T20:58:19.305457Z","submitted_at":"2025-03-25T09:00:58Z","title":"ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"2503.19470","doi":"10.48550/arxiv.2503.19470","metadata_source":"pith","pith_arxiv_id":"2503.19470","snapshot_observed_at":"2026-07-10T12:15:01.137692Z","title":"ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning","venue":"cs.AI","work_id":"cc9775d9-2fbd-4690-a641-2b50ae4a59dc","year":2025},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2503.19470","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:fd2c5223ea0153a73c48850fcf37384e941d9cb26539a4bcd49d7c123938c138","observation_id":"456cff23-58e2-4a7a-8438-ba2ca4ebc2d5","resolution":{"observed_at":"2026-05-22T13:34:53.029691Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.12958","last_updated":"2024-09-17T17:25:40Z","snapshot_observed_at":"2026-07-06T17:47:13.814205Z","submitted_at":"2024-03-19T17:57:58Z","title":"Dated Data: Tracing Knowledge Cutoffs in Large Language Models","version":2},"cited_work":{"arxiv_id":"2403.12958","doi":"10.48550/arxiv.2403.12958","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.12958","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Dated data: Tracing knowledge cutoffs in large language models","venue":null,"work_id":"42f5f09c-2a88-48ad-bf87-387d0cac0d06","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2403.12958","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:fe876e76766a7aacc0b97333a649191242b01c6b55bf8dce0453913f5a6bfe16","observation_id":"faf063fb-933e-4f29-9580-ed20e2ca9024","resolution":{"observed_at":"2026-05-22T13:34:53.057256Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2504.02546","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T09:09:43.573095Z","title":"arXiv preprint arXiv:2504.02546 , year=","venue":null,"work_id":"cdcdaf53-666f-4c7f-8a7f-df8e9b3a4c49","year":2025},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:587b0e1316bc539f91c3581facfcef8f087c7d5c56e8e45f340f40d20486c74e","observation_id":"fff636c9-9793-4b52-a103-0b4dfef09d6c","resolution":{"observed_at":"2026-05-22T13:34:53.058095Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"f6ddd3e4-221d-44be-af66-843232499a4b","year":2023},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:cc9121e6b3801d6c7072017f7f827c98935a59f81e621ece5ff80a535d7ca0d1","observation_id":"9161d51e-b540-4c18-aa5c-7d6787dd2450","resolution":{"observed_at":"2026-05-22T13:34:53.952111Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2024.emnlp-main.64","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T02:47:48.611592Z","title":"A Survey on In-context Learning","venue":null,"work_id":"a881a941-300a-48ff-aa5c-99d2559ddfcb","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:bac339f9552698f240e45660d0ee426e3ed21ba69ae2286385e52917ac1072db","observation_id":"c39c1b8c-2f08-45ac-adf2-f8a89e69adc1","resolution":{"observed_at":"2026-05-22T13:34:52.894610Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T03:18:52.818767+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T03:18:52.818767+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.20995","last_updated":"2024-12-30T14:58:46Z","snapshot_observed_at":"2026-07-06T20:14:40.579474Z","submitted_at":"2024-12-30T14:58:46Z","title":"KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model's Reasoning Path Aggregation","version":1},"cited_work":{"arxiv_id":"2412.20995","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.20995","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Qingyu Guo, Fuzhen Zhuang, Chuan Qin, Hengshu Zhu, Xing Xie, Hui Xiong, and Qing He","venue":null,"work_id":"163c964b-eaa3-43ec-b45c-941dc457bb9e","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2412.20995","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:d714a21710e7ce70fa4970fc57aff840fb6e89713ebf1e266a42871112e01a8e","observation_id":"eaec61d6-1d0f-46a3-98ab-27af44397d12","resolution":{"observed_at":"2026-05-22T13:34:53.184917Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-10T01:36:44.806431Z","title":null,"venue":null,"work_id":"bc431a76-e7c8-439d-a773-74519111076f","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:3bc9515fe411c04c6fb15d0aa9ed0980845a49d1fbedfdd360fac24d93c52456","observation_id":"8fde6133-fb66-4a08-948f-12c5074c1553","resolution":{"observed_at":"2026-05-22T13:34:53.962160Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"InThe Thirty-eighth Annual Conference on Neural Information Processing Systems","venue":null,"work_id":"63e88528-4a07-4f58-9701-c5b9cd347e4c","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:113b5f150601c6d2a894ea6c2a01a89fe2b70b1909ae792326135e42799d5dac","observation_id":"b500ae7e-ec51-4adb-b5c3-057a6578b8ca","resolution":{"observed_at":"2026-05-22T13:34:53.944975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"303c96ab-6369-4c0a-92c8-be8c3c85c6b4","year":2020},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:b1503d15cefdeba0c07d1b84e44924b311338deb16fb31c933aa45afc213bd72","observation_id":"d6ea4b75-c922-4497-96ea-316c910e668f","resolution":{"observed_at":"2026-05-22T13:34:53.811901Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2020.coling-main.580","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T19:08:49.111773Z","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","venue":"Proceedings of the 28th International Conference on Computational Linguistics","work_id":"fd3a2c44-aeea-48a7-b162-d3f0c6d43f35","year":2020},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:77a5fc8b3da59bbc3c7dda80daf47dc4e794810f2a75821344b96d3d1a2733e3","observation_id":"ffb0c239-8923-4143-81bc-c8b25d934b43","resolution":{"observed_at":"2026-05-22T13:34:52.929135Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-14T05:50:02.713939+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-14T05:50:02.713939+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.03262","last_updated":"2025-11-10T15:11:13Z","snapshot_observed_at":"2026-08-02T05:27:47.490711Z","submitted_at":"2025-01-04T02:08:06Z","title":"REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization","version":9},"cited_work":{"arxiv_id":"2501.03262","doi":"10.48550/arxiv.2501.03262","metadata_source":"pith","pith_arxiv_id":"2501.03262","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization","venue":"cs.CL","work_id":"557f9e99-cb00-4dd2-92fd-67ddcddbb35d","year":2025},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2501.03262","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:abce81d2f94d070fba4e7fe75d43a1c60fa5630f958701492488b5a9764ed590","observation_id":"2307f248-44f0-46bb-bef2-5198833b060a","resolution":{"observed_at":"2026-05-22T13:34:53.166475Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:52:56.973979+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:52:56.973979+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-07T08:23:30.898891Z","title":null,"venue":null,"work_id":"5f463bfb-dce6-41dc-8293-b0fe5356b531","year":2025},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:ff3889128551faf9db7697131fa14d282dd006aaf272169cc2443806f820ad45","observation_id":"429b2595-7e4a-4a30-8ec5-e728865091ea","resolution":{"observed_at":"2026-05-22T13:34:53.971769Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"d545c0bd-5774-4cf3-a3fb-962ba0182970","year":2025},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:b50364407fd714124ff929b45696089bf421061990724d03aa81d59a40bece22","observation_id":"ef8452ae-cf20-44da-afa6-ddf1ba77f78a","resolution":{"observed_at":"2026-05-22T13:34:53.937671Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.13101","last_updated":"2025-01-30T04:51:41Z","snapshot_observed_at":"2026-07-06T18:48:12.383629Z","submitted_at":"2024-07-18T02:19:00Z","title":"Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach","version":2},"cited_work":{"arxiv_id":"2407.13101","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.13101","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Retrieve, summarize, plan: Advancing multi-hop question answering with an iterative approach","venue":null,"work_id":"3aeecbd4-db5a-4642-8e8c-35a75bc24045","year":2025},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2407.13101","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:85424c7d31fa58bbc409f32984c0fdd26889caee5f3f772a0981f658a13657ce","observation_id":"187474a9-8226-4269-b1ea-7866cf7a20c0","resolution":{"observed_at":"2026-05-22T13:34:53.200359Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-09T11:26:12.355423Z","title":null,"venue":null,"work_id":"bd28195d-ffb0-4a09-8e4f-ee408da3bd25","year":2020},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:07583d1b4bbfd93b4a801f45d05d8748b88a1ebeb7e8f448a5a1c2d2eb9f76bf","observation_id":"6190740c-e0af-424d-9612-f0160913ae45","resolution":{"observed_at":"2026-05-22T13:34:53.760445Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.14024","last_updated":"2023-01-23T17:00:01Z","snapshot_observed_at":"2026-07-06T14:35:37.368351Z","submitted_at":"2022-12-28T18:52:44Z","title":"Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP","version":2},"cited_work":{"arxiv_id":"2212.14024","doi":"10.48550/arxiv.2212.14024","metadata_source":"pith","pith_arxiv_id":"2212.14024","snapshot_observed_at":"2026-07-10T13:37:06.933383Z","title":"Demonstrate-search-predict: Composing retrieval and language models for knowledge-intensive nlp","venue":"cs.CL","work_id":"8d4545f4-9530-4521-8def-7d279b7c0dd8","year":2022},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2212.14024","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:88e5caf564afc9760ac91aaea8778caf1d506e875aeaa0eff3b8377fdc01c978","observation_id":"a6235a94-d23e-4e13-a5a9-72ac6907191e","resolution":{"observed_at":"2026-05-22T13:34:53.191442Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-06T23:13:03.714466Z","title":null,"venue":null,"work_id":"8e1a9aba-d698-49e6-912c-5fe5fa49f673","year":2017},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:3b1d4ff7b347fa160f4c7a4151d81ac253111853c32bb70b6d6d3f20fde3e244","observation_id":"ac6c86e8-7876-4b6d-a40b-1922c4f3ca56","resolution":{"observed_at":"2026-05-22T13:34:53.931263Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-05T22:31:29.345190Z","title":null,"venue":null,"work_id":"4dc5956c-6b7f-44a0-b648-46d27c5f6eed","year":2023},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:f0bd909bc61b3f1c3f01f499bfa291e36ab5d09b539ba33d728f686acdd108b2","observation_id":"65f74364-8890-4880-8755-7d7620c686bd","resolution":{"observed_at":"2026-05-22T13:34:53.880531Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2020.acl-main.91","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Query graph generation for answering multi-hop complex questions from knowledge bases","venue":null,"work_id":"e10c9185-c581-4a67-aa51-3acebdbbc05d","year":2020},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:50739079dccd86a62e402f659bc207f8b8cea27398ec13b39a4156298a2500a1","observation_id":"0c0cde25-a6bd-43f1-8d90-b170a21edd32","resolution":{"observed_at":"2026-05-22T13:34:52.950282Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-07T08:23:30.905688Z","title":null,"venue":null,"work_id":"1fff674f-0b8c-4105-a19f-1c11fc2da7e9","year":2020},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:b9f2f6efe67281b993ac838d109454fb5704f3d0ed0419633045434e56b5ed94","observation_id":"63ab7ec0-78e5-4435-aa0a-139cc13825e1","resolution":{"observed_at":"2026-05-22T13:34:53.883424Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-06T15:42:38.538343Z","title":null,"venue":null,"work_id":"b6977970-42fa-4df3-bebb-1864dda844b5","year":2020},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:643c7fc6e0aef196b24b8ab203e1af209c15f94c75c282be93cd75d448b233eb","observation_id":"94bd5507-b51f-40c8-bfa3-1aa2d2883d1b","resolution":{"observed_at":"2026-05-22T13:34:53.934439Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"db25a82a-8a39-497e-a4bc-454f31586713","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:407e4679298389f002135942ef2fe9d096c14e3bd9b1394e265172e20fcfb3a7","observation_id":"32ee246e-7a91-4e48-9a6c-4f5b7863f9a9","resolution":{"observed_at":"2026-05-22T13:34:53.959262Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.18415","last_updated":"2024-10-24T04:01:40Z","snapshot_observed_at":"2026-08-04T16:12:44.810124Z","submitted_at":"2024-10-24T04:01:40Z","title":"Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains","version":1},"cited_work":{"arxiv_id":"2410.18415","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.18415","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv:2410.18415 [cs.CL] https: //arxiv.org/abs/2410.18415","venue":null,"work_id":"a5715d89-083f-49d1-ac3a-488833d83b00","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2410.18415","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:f6a4972267f4086faca2111daf59d2229c1333579ab7eecb0c8244b57e427549","observation_id":"f9d1e7b9-4d3c-4dbf-8099-c5d8bd1b7a5b","resolution":{"observed_at":"2026-05-22T13:34:53.186760Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"d479f6fa-8df7-4a75-a475-5ac47c49b62b","year":2025},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:7e57031ae92edd0db7e275a3ce79f71abc45e8dc05429c6928a70890e6e5ae37","observation_id":"84f4a756-54c4-4a23-a9da-163fee41d858","resolution":{"observed_at":"2026-05-22T13:34:53.892348Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"911e3420-9b37-4912-a028-e6b5ebb2bb58","year":2025},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:16b4475321547144ac34f9d3e832334487dfeec4cea29bf13acd20f7e75e7098","observation_id":"2f8961d4-2eac-4ad8-b027-c772dabfa430","resolution":{"observed_at":"2026-05-22T13:34:53.871756Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1609/aaai.v35i15.17568","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"96a240a5-ee58-48a6-99e4-04d788a5e773","year":2021},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:c1edfc75ec7bf0e731d09fed999ccb5ab0dfe34e67f0e60b636e024b7551205d","observation_id":"ed2f3971-c3dd-411d-9bca-3805c3132d21","resolution":{"observed_at":"2026-05-22T13:34:52.951715Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.05366","last_updated":"2025-01-09T16:48:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-09T16:48:17Z","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","version":1},"cited_work":{"arxiv_id":"2501.05366","doi":"10.48550/arxiv.2501.05366","metadata_source":"pith","pith_arxiv_id":"2501.05366","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","venue":"cs.AI","work_id":"6246e99b-7b4e-4424-be78-3e1983932cdc","year":2025},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2501.05366","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:650cd95bd810d1af8be1cede9879a277fe2654594e3b7c8726cae26736ac77a0","observation_id":"ba2bde33-b128-4ab4-bf9a-f2d569215be6","resolution":{"observed_at":"2026-05-22T13:34:53.152893Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"16138a69-433c-4227-938a-d5ae47c01ef5","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:a72828f9317f03e547070fd0c3295a51e541b11172c75a8d848474d53993e33c","observation_id":"a4bab77e-0261-4780-9279-fa56a389b30b","resolution":{"observed_at":"2026-05-22T13:34:53.874258Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1609/aaai.v39i23.34635","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"e7a80cba-0519-4e20-a2a7-add58690c9ca","year":2025},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:043294af030e9f6c4beb8878d9622bcd3472cf59de824578bd0bfd1d2b2ba686","observation_id":"65c6fac2-4c93-40fa-9e45-ba143fa31d35","resolution":{"observed_at":"2026-05-22T13:34:52.943968Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2023.findings-emnlp.423","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"28883ac2-835e-4827-abe4-321036503aa8","year":2023},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:97c787063ccc0e7344f5a8762e8c76fadbee77efbd0b146d0e04093fca3a5a43","observation_id":"db850d96-cebf-45f6-9983-35760ceb37a5","resolution":{"observed_at":"2026-05-22T13:34:52.923580Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.01990","last_updated":"2025-08-02T12:44:02Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-03-31T18:00:29Z","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","version":2},"cited_work":{"arxiv_id":"2504.01990","doi":"10.48550/arxiv.2504.01990","metadata_source":"pith","pith_arxiv_id":"2504.01990","snapshot_observed_at":"2026-07-10T12:15:01.137692Z","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","venue":"cs.AI","work_id":"984dfe5e-1c5c-4b65-920e-15121a85ee7e","year":2025},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2504.01990","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:745f189bc454106b36654860db16caeca47a85c607de8782673ba1ddbbe040a3","observation_id":"f215d781-bf47-443b-9beb-a8b2cf9787a5","resolution":{"observed_at":"2026-05-22T13:34:53.078882Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"33b15393-ed37-4adb-a8ba-c6d0581531ab","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:d6a18d18e14761ca4033bb3d3f675f26ad5ca4558d10aef9ac09771a0c6ea7a9","observation_id":"aa683c86-7f77-46fd-9dab-9d4d4be53d32","resolution":{"observed_at":"2026-05-22T13:34:53.861305Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08632","last_updated":"2025-03-03T12:01:27Z","snapshot_observed_at":"2026-07-06T17:44:00.848335Z","submitted_at":"2024-03-13T15:46:37Z","title":"A Decade's Battle on Dataset Bias: Are We There Yet?","version":2},"cited_work":{"arxiv_id":"2403.08632","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.08632","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2403.08632 , year=","venue":null,"work_id":"a8e96247-87c1-4bc7-a196-38271d643182","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2403.08632","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:42b2b08c05b8d70aaa11e04657e4bf63360e94f9aa1878c965a4c6108da40317","observation_id":"75832a51-976c-45a1-ae3d-dddaa45c694a","resolution":{"observed_at":"2026-05-22T13:34:53.116274Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"72848dc6-0eca-4d37-a7b2-66a1a660f5cb","year":2017},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:e41386b2bfe9d8d81ae02e39a34150839d721a041d8e04379ceb99ddf3a7d39b","observation_id":"6670b300-d590-483f-9b0c-cabfa0b639a6","resolution":{"observed_at":"2026-05-22T13:34:53.905073Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-09T13:26:17.019108Z","title":null,"venue":null,"work_id":"7fcb55d6-6bb2-456a-b13b-ed7ae9868cae","year":2019},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:1466d4dc3559442d2cb8212685fbbb149f3cb3d02c2a2d565c717a8d404bf68b","observation_id":"028e2ac9-6b93-4be6-ade5-d8df259bef38","resolution":{"observed_at":"2026-05-22T13:34:53.843196Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"5c5470c3-235d-4620-b778-91d090bbd036","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:064ae9c7af70a9c3607f9c71667996ce12c672481843b1e249b9fbcbcbb58405","observation_id":"82b37ab0-2107-4ce3-b784-45d35f9df4c8","resolution":{"observed_at":"2026-05-22T13:34:53.994028Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"7a5f4fdd-f3f7-4341-abbf-edeaa5200e16","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:16c298db2182616f8e571fa707a697871dd67c5e39faa329362193926f0b9e69","observation_id":"e15f87c5-ac98-4923-89c5-6e2026ed3cf8","resolution":{"observed_at":"2026-05-22T13:34:53.996138Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"https://openreview.net/forum?id=6embY8aclt","venue":null,"work_id":"808e2e53-3462-4e50-9073-bc8726faf2eb","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:a571f0134daa29e47deb9b221d660f47689d4f93329b825edc16a1b15dddb5f0","observation_id":"30ca05af-b088-427e-b211-140b24cec8a0","resolution":{"observed_at":"2026-05-22T13:34:53.846063Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"67d12017-c136-4dc4-b6b8-f7b970754806","year":2025},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:e846efd32fc76c58408547e98ee07159ba2d0dd21464586f8cda9b83ad1929f8","observation_id":"46ef7f3b-93e4-4fd1-87e0-234576b26c6d","resolution":{"observed_at":"2026-05-22T13:34:53.855670Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2024.findings-emnlp.49","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"797b4587-ddd2-4c3b-918b-b20cacb5681d","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:ff358632087c141e4399b039999e66122955f3fc201070f82c6c02ea9e2f85d9","observation_id":"c9369a94-b6f2-4b77-b73b-37ea4795e6f7","resolution":{"observed_at":"2026-05-22T13:34:52.937035Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"8eaca4c5-1db0-471c-b62b-1fdb22d86716","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:d0119664023f4b14422411c6d5f5f5e9661d9a4e1e16dd0304d77ad6c4eb414e","observation_id":"ff7254b5-0989-46cc-936d-ab263c124ad5","resolution":{"observed_at":"2026-05-22T13:34:53.843682Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.20139","last_updated":"2024-05-30T15:14:24Z","snapshot_observed_at":"2026-07-06T18:22:44.129954Z","submitted_at":"2024-05-30T15:14:24Z","title":"GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning","version":1},"cited_work":{"arxiv_id":"2405.20139","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.20139","snapshot_observed_at":"2026-07-02T18:47:17.231591Z","title":"and Karypis, G","venue":null,"work_id":"7fbe1a28-6a3b-4e93-a813-7ac7a59e6ae1","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2405.20139","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:417f121281dbef7253fb30d811d4eb3c931465ed56f045c4944d6389c141ff64","observation_id":"69df683a-c45e-4a71-a3a2-bb69d6605ed1","resolution":{"observed_at":"2026-05-22T13:34:53.142856Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-09T11:26:12.372824Z","title":null,"venue":null,"work_id":"b2b8e4c9-2223-47d1-b0bb-83573eb2e28b","year":2022},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:065a7517b1b09938b7110a7cd26dedf523ad8adb34d5c6ab2f5b80d10695fca4","observation_id":"14250196-9e63-422f-a59a-6d6c32e24ec9","resolution":{"observed_at":"2026-05-22T13:34:53.840951Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"5064.2022","doi":"10.1109/ijcnn55064.2022","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Liang, Y.-C","venue":null,"work_id":"78495e4b-a848-4bb6-8bb4-3a59e4e275f9","year":2022},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:6dfc5e087cd39a68ede31f2c78af146192806592c0ed6f99f3b8925210e24103","observation_id":"81cfd157-a3ca-4b9d-8f9a-01bfec9f6305","resolution":{"observed_at":"2026-05-22T13:34:52.903307Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"9c4e2f7e-eb62-4a5b-9df5-a953d50dba71","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:4f4b66f30a40c6c34165f4a043c9dc564d2a66ef880f7ca2028eaf0dd3d03e13","observation_id":"b8620f26-cf82-4662-bc82-f76be9a04c4e","resolution":{"observed_at":"2026-05-22T13:34:53.840325Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"a2528368-8a67-44ab-a46a-f1bc8f2c0891","year":2023},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:34c287f4dc263a44b2b2f5d46e1ac2ed4ff1e7a5fafe8d647936c79c90979d38","observation_id":"e0d20a82-8765-4136-831f-f8377869dd0a","resolution":{"observed_at":"2026-05-22T13:34:53.852460Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1561/1500000019","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-08T19:25:32.314017Z","title":"Robertson and Hugo Zaragoza , title =","venue":"Foundations and Trends® in Information Retrieval","work_id":"3dfaa21d-3751-420b-84f7-aeceda058b63","year":2009},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:5ab71c67cefd6bbc50be088510d914c6d3917c873deeb56c0cf0f7bb4f4742f3","observation_id":"5eb9df8d-c109-41d5-9be3-7aa126110235","resolution":{"observed_at":"2026-05-22T13:34:52.931638Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-11T05:49:40.364415+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T05:49:40.364415+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+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":"8032a314-4311-4980-95b7-6e1ea6b1891d","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:1ca32a324133142bcb150f93c3c630c9c9a26b03545bef52a75a1df4fe115490","observation_id":"e2ee5bfa-4dfa-4cf6-8980-92c1b92c6d78","resolution":{"observed_at":"2026-05-22T13:34:53.941039Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"InInternational conference on machine learning","venue":null,"work_id":"f9e561d2-a95e-45d8-b19b-0bd714f07ba8","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:c31f2d281cfb055c08a7cc47091a9ea9a2170537a6e8d2056108fe0e1ff2240c","observation_id":"228b8b47-96c9-436f-860e-615fc6d554b9","resolution":{"observed_at":"2026-05-22T13:34:53.867969Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1506.02438","last_updated":"2018-10-20T18:55:07Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2015-06-08T11:12:48Z","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","version":6},"cited_work":{"arxiv_id":"1506.02438","doi":"10.48550/arxiv.1506.02438","metadata_source":"pith","pith_arxiv_id":"1506.02438","snapshot_observed_at":"2026-07-11T03:57:46.887146Z","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","venue":"cs.LG","work_id":"38e3ca94-96f0-4b19-a355-0754931af8be","year":2015},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/1506.02438","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:74e11d97f60584619a7e9ed2f8cf7a5258283e6ade2fec1c3b7293677c06d7db","observation_id":"12167cee-1ac8-482f-811a-d6d5e41c3157","resolution":{"observed_at":"2026-05-22T13:34:53.181982Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-10T03:26:44.692677Z","title":null,"venue":null,"work_id":"d5783126-8b9e-46a0-be2a-7b4ccf458ca9","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:11902f65192ae0f3fe464828bf0a5dd93462642cd11869892ad53895f90c8fa2","observation_id":"797c5836-3941-4e07-a42f-de4606297130","resolution":{"observed_at":"2026-05-22T13:34:53.938468Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":"1707.06347","doi":"10.1016/j.artint.2010.12.005","metadata_source":"pith","pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Proximal Policy Optimization Algorithms","venue":"cs.LG","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","year":2017},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:7bd6561065d75ed39a7fd8751d888e2f47ec3d71f29a6e1f5e6473848586f5a6","observation_id":"2706d255-9682-4cc4-ba20-b831588acbf5","resolution":{"observed_at":"2026-05-22T13:34:53.179900Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"aff3621e-7eee-49d9-9e64-1d6821856d19","year":2023},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:3282e194362a8b811f789028c92ddfaf1863c3a6d65920dbbc453e62b9a788ce","observation_id":"2d4a8903-2457-42b3-8a14-0e123a2c1a51","resolution":{"observed_at":"2026-05-22T13:34:53.880175Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2023.findings-emnlp.620","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T00:19:12.554760Z","title":"Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy","venue":null,"work_id":"2c5a8029-763e-4158-bc9f-488bb052d946","year":2023},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:b1cf09b941fae3915d19a64fda432a98466a64227effd39944207195c7bca7dc","observation_id":"2bac2fb5-2872-48f9-9b5a-7fc6c15102d9","resolution":{"observed_at":"2026-05-22T13:34:52.955461Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03300","last_updated":"2024-04-27T15:25:53Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-02-05T18:55:32Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","version":3},"cited_work":{"arxiv_id":"2402.03300","doi":"10.1016/0004-3702(73)90011-8","metadata_source":"pith","pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","venue":"cs.CL","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:b9ef7cbec35c37cf45351e64bb1d32a020369b823c764f0ef2868908c9f2528d","observation_id":"7c20d264-2b2b-4b7e-b31e-3fac4fc8d913","resolution":{"observed_at":"2026-05-22T13:34:53.121735Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2022","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T17:29:59.328028Z","title":"37 Wenyue Hua, Lizhou Fan, Lingyao Li, Kai Mei, Jianchao Ji, Yingqiang Ge, Libby Hemphill, and Yongfeng Zhang","venue":null,"work_id":"ed940a1a-3e19-4658-88d1-34194ac465ee","year":2022},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:7f8da6804a8872a29520623c265c7f32edf3a0ed9cce2372a355e9a148132e2e","observation_id":"ca894031-08bc-42f6-8360-3416e12ea9eb","resolution":{"observed_at":"2026-05-22T13:34:52.942199Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-03T02:08:06.032511+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-03T02:08:06.032511+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.05592","last_updated":"2025-03-18T08:32:24Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-03-07T17:14:44Z","title":"R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2503.05592","doi":"10.48550/arxiv.2503.05592","metadata_source":"pith","pith_arxiv_id":"2503.05592","snapshot_observed_at":"2026-07-10T12:15:01.137692Z","title":"R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning","venue":"cs.AI","work_id":"f5ed73d2-f2ff-4cf6-853d-3586333e44ef","year":2025},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2503.05592","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:4acd8ec4815f4728f1e6371d1a8698d44632c921dd60e4849c4088e3abec4f38","observation_id":"fd15051a-ee70-40cf-b320-c3c937fe93b6","resolution":{"observed_at":"2026-05-22T13:34:53.126608Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.13873","last_updated":"2025-05-22T08:07:01Z","snapshot_observed_at":"2026-07-06T18:18:07.839497Z","submitted_at":"2024-05-22T17:56:53Z","title":"FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering","version":4},"cited_work":{"arxiv_id":"2405.13873","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.13873","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"d6da62e2-ca57-423f-bb86-cf057c1ce634","year":2025},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2405.13873","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:1879e0ad59d16033725b3a6b79974c6a7a3c8f0447ad8924ee4d9d4502156132","observation_id":"889a08a8-7a6e-4973-ba6a-b0f9fe017e5a","resolution":{"observed_at":"2026-05-22T13:34:53.175061Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.04588","last_updated":"2026-05-19T11:51:42Z","snapshot_observed_at":"2026-08-04T18:36:41.979541Z","submitted_at":"2025-05-07T17:30:22Z","title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","version":3},"cited_work":{"arxiv_id":"2505.04588","doi":"10.48550/arxiv.2505.04588","metadata_source":"pith","pith_arxiv_id":"2505.04588","snapshot_observed_at":"2026-07-10T12:15:01.137692Z","title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","venue":"cs.CL","work_id":"0ea11521-4603-4e7a-abe3-bbc2f3e3f71c","year":2025},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2505.04588","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:778ddf17b6e2e98671ea8793bb32c26f5e0be05ad945a350ac6e05bfacf1450d","observation_id":"79501cbb-1579-41cb-a840-1559fde82470","resolution":{"observed_at":"2026-05-22T13:34:53.194692Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"a529f639-5a27-4634-b4a0-408f242f89c7","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:fb85d6fced41355dbda4f82637afe273560ca445c2ef7d7f24391c1fb8044f39","observation_id":"71256b7f-e2f4-4600-b20d-a03f10b55eab","resolution":{"observed_at":"2026-05-22T13:34:53.816985Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"6e5d7f6d-09ae-4eb5-956e-b04e680373e3","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:cffd86a63f4ee81e31efcd0f9ee4c56e98a7a6ea205f4bcd8b239a06cd9cc0ec","observation_id":"b0e5bb44-0db6-4927-bedc-d5343411dff7","resolution":{"observed_at":"2026-05-22T13:34:53.870897Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.14211","last_updated":"2025-03-12T23:45:13Z","snapshot_observed_at":"2026-07-06T19:35:48.603411Z","submitted_at":"2024-10-18T06:57:19Z","title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","version":4},"cited_work":{"arxiv_id":"2410.14211","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.14211","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv:2410.14211 [cs.CL] https://arxiv.org/abs/2410.14211","venue":null,"work_id":"d64ba2a8-869d-4d6e-99c2-7028343407c7","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2410.14211","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:476d2428e927c0dd5b5a760373eec5faab643fc65536e45eb779d51825399219","observation_id":"964319b7-0fdb-42e6-b593-2559a1415f93","resolution":{"observed_at":"2026-05-22T13:34:53.201008Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.08448","last_updated":"2024-05-14T09:12:30Z","snapshot_observed_at":"2026-07-06T18:14:03.830337Z","submitted_at":"2024-05-14T09:12:30Z","title":"Understanding the performance gap between online and offline alignment algorithms","version":1},"cited_work":{"arxiv_id":"2405.08448","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.08448","snapshot_observed_at":"2026-07-02T03:46:33.108981Z","title":"Understanding the performance gap between online and offline alignment algorithms","venue":null,"work_id":"92c35cdc-3e32-404d-a038-8a1f4228a044","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2405.08448","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:33b6baf829e321279aa50cf3a009b791c31177f28fa27436b69505ec10eead9d","observation_id":"34518477-89fe-4da5-abbc-e97a0e2281e9","resolution":{"observed_at":"2026-05-22T13:34:53.134007Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"Transactions of the Association for Computational Linguistics(2022)","venue":null,"work_id":"173836e1-1210-4938-82be-c919dedce7a6","year":2022},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:183a5c3c7e3b5d00cc2cb06df7367f7e4e47aff74fec39f00cfdc7714f3e2dfe","observation_id":"33f444d3-985b-4343-b106-162249ed29ba","resolution":{"observed_at":"2026-05-22T13:34:53.860458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-07T08:23:30.926135Z","title":null,"venue":null,"work_id":"c261ea03-7667-4f54-9096-31a177264728","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:bec83e00a331154466634a4526167a8825bb60829653f534127f25c1c34f1370","observation_id":"d8dfacda-bfec-4f13-bf01-362c0cab971e","resolution":{"observed_at":"2026-05-22T13:34:53.810470Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2023.acl-","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T23:09:00.740362Z","title":"Diverse demonstrations improve in-context compositional generalization","venue":null,"work_id":"d6692343-8429-42f2-aa4d-69c9f7b7cdaa","year":2023},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:a61458117857bf34bc51094ad4c5e072702ab5545b4c3e03f25d569360bfa2b9","observation_id":"116dad29-f9cb-42b0-b061-23f89c84286d","resolution":{"observed_at":"2026-05-22T13:34:52.946232Z","resolver_source":"doi_truncated","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.3233/sw-233471","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"a8de2f51-250d-408a-84d3-07e7b5fb1016","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:64e661f20144355bf16773ee15673863bd0eb93b8f0beddaf547ba5353399243","observation_id":"2a118e1e-8340-4c57-990a-720af121c6dd","resolution":{"observed_at":"2026-05-22T13:34:52.912149Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"332e025c-57e0-4ee8-aa7d-ecbbe9fe81ee","year":2014},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:2d2c74702d6483ed91d0ad446a4d4b5a12cba51ba7b3635f288b6455d9dd885a","observation_id":"0c3093e0-ab25-4f99-a493-68928a426006","resolution":{"observed_at":"2026-05-22T13:34:53.873564Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.13259","last_updated":"2023-10-28T12:19:29Z","snapshot_observed_at":"2026-07-06T16:10:19.589022Z","submitted_at":"2023-08-25T09:23:55Z","title":"Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering","version":2},"cited_work":{"arxiv_id":"2308.13259","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.13259","snapshot_observed_at":"2026-07-08T03:04:28.397125Z","title":"Knowledge-driven cot: Exploring faithful reasoning in llms for knowledge-intensive question answering","venue":"cs.CL","work_id":"9c261523-18e1-4ec9-92ad-0425923ef73c","year":2023},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2308.13259","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:481aa307b974dd42a134c9c12e9604f8b2f23a39ceb16a01cc1324d2bc04361f","observation_id":"83848d29-549d-4c99-869b-e010215a0e85","resolution":{"observed_at":"2026-05-22T13:34:53.127980Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"6f9923be-bb2b-419e-815e-5029ff10dcd1","year":1992},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:c070fe06b8c19bf3f86bc4dd1d42d18cf6f324aba52792082c9d7ed0c91f9a21","observation_id":"73d52bed-eb41-4079-8ce1-ed541ba811ab","resolution":{"observed_at":"2026-05-22T13:34:53.892178Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"255a6c05-d2fd-4afe-85d1-0436c9830c4d","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:3315b158db9273d687d351878c114a36b3b95cf9a15192df45cff9cc76f684f0","observation_id":"85f14fd2-7ca6-4689-ae6b-8f56afd6a595","resolution":{"observed_at":"2026-05-22T13:34:53.850984Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.11206","last_updated":"2023-09-21T04:43:46Z","snapshot_observed_at":"2026-07-06T16:20:56.717809Z","submitted_at":"2023-09-20T10:42:08Z","title":"Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering","version":2},"cited_work":{"arxiv_id":"2309.11206","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.11206","snapshot_observed_at":"2026-07-02T15:57:07.348654Z","title":"Retrieve-rewrite- answer: A kg-to-text enhanced llms framework for knowledge graph question answering","venue":null,"work_id":"aafa10dc-ee79-4e61-8973-43de6090040e","year":2023},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2309.11206","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:c7d5d04294dced5d7e7cd9a83853b11ae4ac1ff806f3d73aa281db7ce22ff1a4","observation_id":"5635aa0e-60d7-438b-829f-58327abdc44a","resolution":{"observed_at":"2026-05-22T13:34:53.099678Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.11343","last_updated":"2025-06-12T06:03:24Z","snapshot_observed_at":"2026-07-06T21:09:50.780345Z","submitted_at":"2025-04-15T16:15:02Z","title":"A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce","version":2},"cited_work":{"arxiv_id":"2504.11343","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.11343","snapshot_observed_at":"2026-07-09T04:05:55.456269Z","title":"A minimalist approach to llm reasoning: from rejection sampling to reinforce.arXiv preprint arXiv:2504.11343","venue":"cs.LG","work_id":"90392907-b8b0-4771-9ac8-6cd50245b1dd","year":2025},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2504.11343","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:e7ea30558f2ec659f6e942862eab82358b3b931ca9f685a0f8e4629e3eb6f7e7","observation_id":"55773bad-37ca-41b8-a1eb-2acc1865b435","resolution":{"observed_at":"2026-05-22T13:34:53.196041Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"b1c81f45-ed90-4795-815f-a82bc25280d2","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:0acfb78c9f193599ac4f4d9acdc7b0954becdd9f9ccdc66948bd50d7c365129c","observation_id":"744025e2-7327-4f65-9798-649308419808","resolution":{"observed_at":"2026-05-22T13:34:53.857388Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.12643","last_updated":"2025-03-07T07:14:33Z","snapshot_observed_at":"2026-07-06T20:08:20.905061Z","submitted_at":"2024-12-17T08:07:16Z","title":"LLM-based Discriminative Reasoning for Knowledge Graph Question Answering","version":2},"cited_work":{"arxiv_id":"2412.12643","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.12643","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv:2412.12643 [cs.CL] https://arxiv.org/abs/2412.12643","venue":null,"work_id":"7a5a95ed-3f57-4995-9312-bba74c86e787","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2412.12643","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:36f11bb4d1f51e8ea0ef6a449b5344a04df860c1d754c2f784e03edfd7740d49","observation_id":"26d1666a-6f4c-4031-8025-cbbd37736ba2","resolution":{"observed_at":"2026-05-22T13:34:53.189924Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2024.emnlp-main.1023","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T21:53:58.682603Z","title":null,"venue":null,"work_id":"b48fabca-478c-480f-9262-db2337dec8b8","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:020d6880905204c5d62eed99854876960b6d494ed018a57c97c678c0a6d568a4","observation_id":"c34a6781-781d-4b64-a7a0-0c0878f5ffc8","resolution":{"observed_at":"2026-05-22T13:34:52.953701Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10671","last_updated":"2024-09-10T13:25:53Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-07-15T12:35:42Z","title":"Qwen2 Technical Report","version":4},"cited_work":{"arxiv_id":"2407.10671","doi":"10.18653/v1/2024.naacl-long.246","metadata_source":"pith","pith_arxiv_id":"2407.10671","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Qwen2 Technical Report","venue":"cs.CL","work_id":"a1857881-ab9b-4b80-9b5f-9ae4b5c2566d","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2407.10671","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:4b5cd279b7a25ede32e607eaed5817bdb945ecd8359f792c42efac1d2307b224","observation_id":"96cb2585-a28b-469f-906f-1e56ba80d457","resolution":{"observed_at":"2026-05-22T13:34:53.154410Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"6772.365776","doi":"10.1145/3626772.3657760","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"InProceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","venue":null,"work_id":"626b8dec-9cf0-47ca-8dd2-9c4bb723aebb","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:b7772703890c24d29b9048e4c82d98eca061bba24006bb87d442a35cf7beb687","observation_id":"bbf6eed6-121f-4527-9d61-d8102f12107a","resolution":{"observed_at":"2026-05-22T13:34:52.938704Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1809.09600","last_updated":"2018-09-25T17:28:20Z","snapshot_observed_at":"2026-07-31T11:19:06.421362Z","submitted_at":"2018-09-25T17:28:20Z","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","version":1},"cited_work":{"arxiv_id":"1809.09600","doi":"10.48550/arxiv.1809.09600","metadata_source":"pith","pith_arxiv_id":"1809.09600","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","venue":"cs.CL","work_id":"c87d7e5f-b81a-41c8-beca-f0b9d598aae4","year":2018},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/1809.09600","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:9b50d35d1a5b5880f80b4de57127266caeadecde9caa70cde738e11b8b00788c","observation_id":"f1ca34e9-8d19-4c81-8015-61a9d5580aea","resolution":{"observed_at":"2026-05-22T13:34:53.159287Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"dff5be6e-f57c-4636-ba46-561d9886355d","year":2023},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:7fcd13ca6c6454356598b3d37fccde7bb1de75e279be948bcf0d69b2550b52db","observation_id":"d2b11e15-31da-40f1-93d4-652075c327c3","resolution":{"observed_at":"2026-05-22T13:34:53.815042Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"d21e6bfa-b6d0-44b7-aba8-c084dcd57bfb","year":2023},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:c1723eb5e6898641b055a2dcd180b7c5c5d513c06b408fe5faf2232499c05d0c","observation_id":"553067e3-c901-4d4e-8ae6-15ec35ae4f9b","resolution":{"observed_at":"2026-05-22T13:34:53.826203Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"f66c90af-a4af-4a12-939f-9421a12d138d","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:4f10e4cf69f38975ac2e2bd6333dc1981c5e70d221487b6536113aead76cd5cc","observation_id":"114f9d0c-204a-4d3b-b4f3-de7ccea98f83","resolution":{"observed_at":"2026-05-22T13:34:53.974645Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.04343","last_updated":"2025-03-02T19:44:37Z","snapshot_observed_at":"2026-07-06T19:28:30.731752Z","submitted_at":"2024-10-06T03:42:15Z","title":"Inference Scaling for Long-Context Retrieval Augmented Generation","version":2},"cited_work":{"arxiv_id":"2410.04343","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.04343","snapshot_observed_at":"2026-07-11T03:17:50.738757Z","title":"arXiv:2410.04343 [cs.CL] https://arxiv.org/abs/2410.04343","venue":"cs.CL","work_id":"9e4fec63-85d0-49b9-94ea-6e5f55779d95","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2410.04343","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:cfee4fd93a922c5605469ee737b3056af902869454e623c1507046a923ea8419","observation_id":"89b8b538-6fd2-4371-83d3-5370d9340ba5","resolution":{"observed_at":"2026-05-22T13:34:53.100003Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"39685d73-7d6b-4a14-a26a-dbe44323664b","year":2022},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:d2ee94fd5f898f1e5b580c5ba20aaa39df55a09c8dd50a00a9fee9deec868b5d","observation_id":"6f642769-e39f-4326-b254-a2ea2e2b33a4","resolution":{"observed_at":"2026-05-22T13:34:53.883215Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"ca9b619b-83fe-4b00-94ee-312628b1d1fe","year":null},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:7ab8820cdf2a12d2a1b9e8e37012147f3ad7933d3b429574b7f693256c1dc526","observation_id":"e701eb92-8fa7-4964-8b84-e16ccf2652f2","resolution":{"observed_at":"2026-05-22T13:34:53.837971Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2024.naacl-long.96","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T01:00:20.250271Z","title":"End-to-End Beam Retrieval for Multi-Hop Question Answering","venue":null,"work_id":"5f719142-470b-4c4a-b275-c9faea03f568","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:f4765a44fb2a22faa4a71bb1db73ace7652e9150c90b113149265e0c1f94c0a1","observation_id":"d60bc1d6-5595-4421-9139-991e946b924c","resolution":{"observed_at":"2026-05-22T13:34:52.926586Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"d8abc91f-5302-4716-9d64-23c1ca7b7671","year":2025},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:c53b9eeac5ee6ac120e0d1be4439322505b9148b1ea8776d30ebb137ae247ee3","observation_id":"ea46880a-be4d-4622-b18f-ec5f87dea494","resolution":{"observed_at":"2026-05-22T13:34:53.854075Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.10131","last_updated":"2024-06-05T17:27:51Z","snapshot_observed_at":"2026-07-06T17:45:07.023305Z","submitted_at":"2024-03-15T09:26:02Z","title":"RAFT: Adapting Language Model to Domain Specific RAG","version":2},"cited_work":{"arxiv_id":"2403.10131","doi":"10.48550/arxiv.2403.10131","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.10131","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Raft: Adapting language model to domain specific rag","venue":null,"work_id":"a778bc2e-ab2e-43de-babe-53288bc85919","year":2024},"citing_paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","version":4},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-05-22T13:34:27.152447Z"},"links":{"cited_paper":"/paper/2403.10131","citing_paper":"/paper/2505.17086"},"observation_digest":"sha256:f16a6c691b13d36f15ca46feb8bd1b069f640f465fb785166a2147fcb4b4364e","observation_id":"54048b82-c392-4f35-874b-a38894ada681","resolution":{"observed_at":"2026-05-22T13:34:53.170772Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.17086","last_updated":"2026-04-14T00:27:30Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T18:33:03Z","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":1,"metadata_mismatch":6,"parse_uncertain":0,"unresolved":45,"verified_exact":42,"verified_fuzzy":6},"total_outbound_references":124},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 100 of 124 outbound references and 1 inbound Pith citation observation for arXiv:2505.17086."}