{"as_of":"2026-08-18T06:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:151da42fdf3c20920a6b5225a5c0396472ed31d82f5c4f1b6173e2d6ee78c8ae","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T04:30:09.163795Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":6,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":6,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T16:30:36.863963Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-01T08:25:33.102243Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.10408","snapshot_observed_at":"2026-08-15T16:30:36.863963Z","title":"Xi Victoria Lin, Xilun Chen, Mingda Chen, Weijia Shi, Maria Lomeli, Richard James, Pedro Rodriguez, Ja- cob Kahn, Gergely Szilvasy, Mike Lewis, and 1 oth- ers","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.04820","last_updated":"2025-09-05T05:44:50Z","snapshot_observed_at":"2026-08-17T10:59:43.879283Z","submitted_at":"2025-09-05T05:44:50Z","title":"Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented Generation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T16:30:36.863963Z"},"links":{"cited_paper":"/paper/2506.10408","citing_paper":"/paper/2509.04820"},"observation_digest":"sha256:f9ad47fc4cb230f1b07a9fe916b4c7f9a410068b189c07fddb464fe0248d0d5a","observation_id":"ae7d1827-d86b-4377-a424-0fa299bbd59e","resolution":{"observed_at":"2026-08-15T16:30:36.863963Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.10408","snapshot_observed_at":"2026-08-04T09:50:47.142987Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.13272","last_updated":"2026-06-03T06:16:13Z","snapshot_observed_at":"2026-08-15T12:17:18.554444Z","submitted_at":"2025-10-15T08:17:52Z","title":"Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation","version":3},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-04T09:50:47.142987Z"},"links":{"cited_paper":"/paper/2506.10408","citing_paper":"/paper/2510.13272"},"observation_digest":"sha256:abc5f35d4c030f67408725a00f6e652d46e76edeafab9244e23899145f276c94","observation_id":"94ca7c1f-0236-42ef-a232-656251d590ff","resolution":{"observed_at":"2026-08-04T09:50:47.142987Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"cited_work":{"arxiv_id":"2506.10408","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.10408","snapshot_observed_at":"2026-07-01T08:25:33.102243Z","title":"arXiv preprint arXiv:2506.10408 , year=","venue":null,"work_id":"1a95dde4-e795-49ed-a0bb-6dca6b37f9ce","year":2024},"citing_paper":{"arxiv_id":"2512.13564","last_updated":"2026-01-13T09:33:57Z","snapshot_observed_at":"2026-08-13T14:23:02.090859Z","submitted_at":"2025-12-15T17:22:34Z","title":"Memory in the Age of AI Agents","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-05-11T18:18:19.911342Z"},"links":{"cited_paper":"/paper/2506.10408","citing_paper":"/paper/2512.13564"},"observation_digest":"sha256:aba158abc663643be5f35ad3c56adcf6523768dfd6ff5334558a84151fbeddfb","observation_id":"ebb83b8f-a5df-400a-bbf7-bbe5f14b2229","resolution":{"observed_at":"2026-05-11T18:18:20.422824Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"cited_work":{"arxiv_id":"2506.10408","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.10408","snapshot_observed_at":"2026-07-01T08:25:33.102243Z","title":"arXiv preprint arXiv:2506.10408 , year=","venue":null,"work_id":"1a95dde4-e795-49ed-a0bb-6dca6b37f9ce","year":2024},"citing_paper":{"arxiv_id":"2604.05952","last_updated":"2026-04-07T14:46:26Z","snapshot_observed_at":"2026-08-11T06:35:19.917778Z","submitted_at":"2026-04-07T14:46:26Z","title":"Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-05-10T19:41:00.530274Z"},"links":{"cited_paper":"/paper/2506.10408","citing_paper":"/paper/2604.05952"},"observation_digest":"sha256:424bc031f46ef0c97262a0bd9f406d87bd679bc67645f2de640e3ffac860a644","observation_id":"b1d0bf17-1dca-416a-88e6-e7307b70faef","resolution":{"observed_at":"2026-05-10T22:35:52.179488Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"cited_work":{"arxiv_id":"2506.10408","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.10408","snapshot_observed_at":"2026-07-01T08:25:33.102243Z","title":"arXiv preprint arXiv:2506.10408 , year=","venue":null,"work_id":"1a95dde4-e795-49ed-a0bb-6dca6b37f9ce","year":2024},"citing_paper":{"arxiv_id":"2605.00063","last_updated":"2026-04-30T08:35:06Z","snapshot_observed_at":"2026-07-06T23:13:33.799847Z","submitted_at":"2026-04-30T08:35:06Z","title":"A Survey of Reasoning-Intensive Retrieval: Progress and Challenges","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-05-09T20:53:05.314601Z"},"links":{"cited_paper":"/paper/2506.10408","citing_paper":"/paper/2605.00063"},"observation_digest":"sha256:be0131bed72affc7fbe5f433ee06e3dac7b2654a670f2cb383c4714195bb18fc","observation_id":"c1b95d17-f709-4531-91ff-5e914621071c","resolution":{"observed_at":"2026-05-11T14:56:05.343140Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"cited_work":{"arxiv_id":"2506.10408","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.10408","snapshot_observed_at":"2026-07-01T08:25:33.102243Z","title":"arXiv preprint arXiv:2506.10408 , year=","venue":null,"work_id":"1a95dde4-e795-49ed-a0bb-6dca6b37f9ce","year":2024},"citing_paper":{"arxiv_id":"2606.00042","last_updated":"2026-04-28T15:39:53Z","snapshot_observed_at":"2026-08-13T09:38:42.454944Z","submitted_at":"2026-04-28T15:39:53Z","title":"TransResAI: A Compound AI System for Coastal Transportation Resilience","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-01T08:23:09.471328Z"},"links":{"cited_paper":"/paper/2506.10408","citing_paper":"/paper/2606.00042"},"observation_digest":"sha256:83eb4ba35ac2bb980f350097ead27b428edbdf6cedf5e9b3b5c368db52da899e","observation_id":"53803730-837a-4636-bbb1-41cbf0783499","resolution":{"observed_at":"2026-07-01T08:25:33.104571Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.10408/citation-record","integrity":"/paper/2506.10408/integrity","json":"/paper/2506.10408/citation-record.json","paper":"/paper/2506.10408"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:30:13.969964Z","title":"Self-rag: Learning to retrieve, generate, and critique through self- reflection,","venue":null,"work_id":"b5b3374d-ea3d-4ff7-bc9a-adc771b5d8ec","year":2023},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:05.985448Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:f9359d8320783bd3b9ea71f994d7564f293199e14b2238de7d0bbff0b9c3e50f","observation_id":"d1bccbce-ea6f-4987-8bad-17cd24fbe6d4","resolution":{"observed_at":"2026-08-07T04:30:14.061457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:13.104608Z","title":"Function call- ing and other api updates, June","venue":null,"work_id":"4840e814-ec9c-4e89-99bc-da24726c7eac","year":2023},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:06.255978Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:2d856e3511e6eb185197a508256e9bcc96d96ebb9f90e0d26da11d7e7b5c60cc","observation_id":"965de259-5abd-4d7a-8df5-653ab16b6e11","resolution":{"observed_at":"2026-08-07T04:30:13.262623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.10997","last_updated":"2024-03-27T09:16:57Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-18T07:47:33Z","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.10997","snapshot_observed_at":"2026-08-07T04:30:06.327471Z","title":"Retrieval- augmented generation for large language models: A survey","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:06.327471Z"},"links":{"cited_paper":"/paper/2312.10997","citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:d7dca9fa897270a1dbf3b5028868dd62c88870484e6821222faefb4f86419176","observation_id":"4434c6c7-f304-4468-b2e3-190b817aa898","resolution":{"observed_at":"2026-08-07T04:30:06.327471Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:30:12.888062Z","title":"Modular rag: Transforming rag systems into lego-like reconfigurable frameworks,","venue":null,"work_id":"630dc838-651c-490e-9bce-d4a7cdb5bef9","year":2024},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:06.395502Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:e2f42d0db4eafc3bb95ab6a08dc4af3384cbc49ff4c486211d74e86ff43ee3e2","observation_id":"731a7a50-8c6e-432b-bf77-b4c1dd6a20f5","resolution":{"observed_at":"2026-08-07T04:30:12.974675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:12.734328Z","title":"Mcts-rag: En- hancing retrieval-augmented generation with monte carlo tree search,","venue":null,"work_id":"9de35da8-fad9-4dd2-879b-b555e7323dc7","year":2025},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:06.454269Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:9cee098db050e56718746f7874e52e0b930ea8c9360eb37a33164d9262ab2610","observation_id":"33d92bdb-47a6-4422-8c3f-0075a16cbae7","resolution":{"observed_at":"2026-08-07T04:30:12.820384Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:12.518743Z","title":"A survey on hallucination in large language models: Principles, tax- onomy, challenges, and open questions","venue":null,"work_id":"abcd5349-c53d-4eb8-9004-3c3ddb880fef","year":2025},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:06.536813Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:1efac67ea45fcb6b9ef987b508b051d7029b32033bdf1cf2e7b872818ba14f40","observation_id":"c8bf8266-c3bf-4944-b32e-00c6a271c1f9","resolution":{"observed_at":"2026-08-07T04:30:12.619040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:12.302399Z","title":"Adaptive-rag: Learning to adapt retrieval-augmented large language models through question complexity,","venue":null,"work_id":"7a2824bb-41a1-4a82-960b-f63948ddc5f4","year":2024},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:06.622446Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:168d4dcbd0b611eeac79d646cf7be7a2c972f38f33dd240984dba91764ac0446","observation_id":"cc640923-1db2-4118-af75-7a7bd828d1c0","resolution":{"observed_at":"2026-08-07T04:30:12.395031Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:12.106306Z","title":"Deepretrieval: Hacking real search engines and retriev- ers with large language models via reinforcement learning,","venue":null,"work_id":"a2d9ede0-2e92-4949-82f3-63a6e532d67f","year":2025},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:06.714759Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:14694bd2cecfb2f8df3815830063e61e59f51daa4f6e303e4866b5b82faad95e","observation_id":"32bbb949-cb99-4606-9406-2ea78d1fd460","resolution":{"observed_at":"2026-08-07T04:30:12.190635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:11.975015Z","title":"Search-r1: Training llms to reason and leverage search engines with reinforcement learning,","venue":null,"work_id":"e6c27056-0e7a-45cd-a33a-22bb31d8b88b","year":2025},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:06.775932Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:43d61392c1a4aa57ff9b22d35df2e613bb26d94f0ab0c06492d53e4b8ff19e35","observation_id":"702403c4-b669-4c95-9806-47b58b5f7ea7","resolution":{"observed_at":"2026-08-07T04:30:12.044117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:11.829759Z","title":"Tptu- v2: Boosting task planning and tool usage of large language model-based agents in real-world industry systems","venue":null,"work_id":"9097babb-9f5f-4e04-9184-8122da4c1414","year":2024},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:06.853660Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:2db4424b8d83639f602806d4dfc634af0a696138c1ec2176aa068b5158d71288","observation_id":"9b488c47-05f8-4184-b473-afb94c42c7b6","resolution":{"observed_at":"2026-08-07T04:30:11.894756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:11.605085Z","title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","venue":null,"work_id":"a4657a70-19f4-4758-a089-1dd464d8c0a1","year":2020},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:06.925020Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:fb145628863b1baabb3270b483d4fca417ba2b6cad6c925641e43fc5cb4ad04e","observation_id":"0b184179-ada3-4000-95dc-96d89c4e79fb","resolution":{"observed_at":"2026-08-07T04:30:11.706947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.17419","last_updated":"2025-06-25T02:24:46Z","snapshot_observed_at":"2026-08-10T09:42:17.185681Z","submitted_at":"2025-02-24T18:50:52Z","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.17419","snapshot_observed_at":"2026-08-07T04:30:07.062366Z","title":"From system 1 to system 2: A survey of reasoning large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:07.062366Z"},"links":{"cited_paper":"/paper/2502.17419","citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:ed70a97247f55e8c20dd74032a3b42749ecf60d82b3197a92259cad6d1febb9d","observation_id":"5e22f85d-2f1f-4d78-82c7-350e7522f634","resolution":{"observed_at":"2026-08-07T04:30:07.062366Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:30:11.446629Z","title":"Query rewrit- ing in retrieval-augmented large language models","venue":null,"work_id":"a0caebf6-6d55-43f8-901c-f237788d671f","year":2023},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:07.141978Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:e8177cbc4f8782b968f2ed60b0c9931570aac2c6f077a11a6a52ceb2d6b5e1d8","observation_id":"89dffebc-c6b6-41c9-9285-b5e962eb9880","resolution":{"observed_at":"2026-08-07T04:30:11.530603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.16365","last_updated":"2025-05-23T14:05:39Z","snapshot_observed_at":"2026-08-15T15:01:44.472578Z","submitted_at":"2024-11-25T13:20:19Z","title":"Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong Baselines","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.16365","snapshot_observed_at":"2026-08-07T04:30:07.231258Z","title":"Multi-modal retrieval augmented multi-modal generation: A bench- mark, evaluate metrics and strong baselines","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:07.231258Z"},"links":{"cited_paper":"/paper/2411.16365","citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:dad4616977f4dd48acb79811e9d0a66d5848b3e52a4852712a3edbe8883c5d05","observation_id":"ff225eb9-6fda-40fb-8efc-6da852dc8b6a","resolution":{"observed_at":"2026-08-07T04:30:07.231258Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:30:11.302605Z","title":"Openai o1 system card,","venue":null,"work_id":"81c78df7-93bf-43eb-88ed-720db3f41e8e","year":2024},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:07.329657Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:d7e280ae9394675ed9ae91c03bebf244f9b4a338b5321ca68033bb4c4b7f7072","observation_id":"a522b360-cfd2-4a85-9412-3c3e5ab08b1b","resolution":{"observed_at":"2026-08-07T04:30:11.376078Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:11.295414Z","title":"Deep research system card, Febru- ary","venue":null,"work_id":"39300064-2078-4a52-b696-ae35c28a0959","year":2025},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:07.442300Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:9ccdb8c0f2378cdabc3aebc4f4bd7b3dc684508718d065462e37817737a3ead6","observation_id":"adc7ec38-2afc-4f54-aece-a7f061507358","resolution":{"observed_at":"2026-08-07T04:30:11.297935Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:11.207861Z","title":"Measuring and narrowing the compositionality gap in language models,","venue":null,"work_id":"0d8de6b1-95c3-4fdd-8275-5c47218d7cf3","year":2023},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:07.505770Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:8509e749eff012d11200f0304f187f1ec839166d8da979947379d8d62f7edad4","observation_id":"c2c00811-b776-4b89-aedc-d3899a56eb49","resolution":{"observed_at":"2026-08-07T04:30:11.290536Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.14484","last_updated":"2024-08-18T11:47:55Z","snapshot_observed_at":"2026-08-16T13:25:44.920616Z","submitted_at":"2024-08-18T11:47:55Z","title":"Agentic Retrieval-Augmented Generation for Time Series Analysis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.14484","snapshot_observed_at":"2026-08-07T04:30:07.576555Z","title":"Agentic retrieval-augmented generation for time series analysis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:07.576555Z"},"links":{"cited_paper":"/paper/2408.14484","citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:e4edfb4bfe9c382b712a2a3b1dfb1213cead9197012a11b8a7c3a66751deb4ee","observation_id":"0d66e4a9-790e-4b44-b96c-19534c876fe8","resolution":{"observed_at":"2026-08-07T04:30:07.576555Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:30:11.058792Z","title":"The troubling emergence of hallucination in large lan- guage models-an extensive definition, quantification, and prescriptive remediations","venue":null,"work_id":"66130a7c-0c28-43c4-b3b5-0a7caafed7f9","year":2023},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:07.643540Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:ababd3ce46d6a609287b1b66f549eec3e58e6e99493e8d86ede0b0c8545fc2bb","observation_id":"6b143e2d-5b25-4878-9d77-4328e665d740","resolution":{"observed_at":"2026-08-07T04:30:11.142070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:10.903377Z","title":"The probabilistic relevance framework: Bm25 and beyond","venue":null,"work_id":"5b03704a-b541-49e7-996b-c376deb9ab89","year":2009},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:07.720903Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:cae823fff0a8b45371acabc69dab045d38a50fedb9b63ff6e595c212425270ff","observation_id":"783285ad-0144-499c-abf2-e2801ae0ad85","resolution":{"observed_at":"2026-08-07T04:30:10.990475Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:10.615412Z","title":"Rap- tor: Recursive abstractive processing for tree-organized retrieval,","venue":null,"work_id":"32e77087-dea8-4490-96e4-a0c6e1a47ee3","year":2024},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:07.869662Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:2f257cf08003de68151fcc51cb9d443b99143b11ba429c8500b6ad755a189f3b","observation_id":"7dfbb8d4-207e-4a28-97fa-4ee74c964c49","resolution":{"observed_at":"2026-08-07T04:30:10.679538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:10.513094Z","title":"Proximal policy optimization algorithms,","venue":null,"work_id":"ba29a40b-7e20-4601-91c2-78feee482d3f","year":2017},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:07.963612Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:8f9a73e9aba3f34946299dd43806ea2f88425a0d916a633b46cdeba3f9cd697f","observation_id":"74ad154f-322a-4c4e-a4f5-b252abd6fc67","resolution":{"observed_at":"2026-08-07T04:30:10.564137Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:10.237357Z","title":"Exploring language models: A comprehensive survey and analysis","venue":null,"work_id":"50baf3fe-d914-40b2-999b-9fba5f373431","year":2023},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:08.128191Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:58ea66438d749c53f6db0404ed1461612380668ce6f6179b36ca2661a3c5e7a3","observation_id":"0d7ad2a1-62eb-421a-88a0-c95742fc3f51","resolution":{"observed_at":"2026-08-07T04:30:10.299726Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:10.085389Z","title":"R1- searcher: Incentivizing the search capability in llms via reinforcement learning,","venue":null,"work_id":"9709d4b1-130b-40b0-9dcf-62fd1266bfa0","year":2025},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:08.222053Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:bf0e590e937002e666df744e04565a950c124d48da1133e7a3df79971befe08d","observation_id":"9a96dfb4-427b-4e30-a7a2-bfebb277ccc4","resolution":{"observed_at":"2026-08-07T04:30:10.168247Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.13079","last_updated":"2025-08-12T17:53:18Z","snapshot_observed_at":"2026-08-16T12:12:59.635977Z","submitted_at":"2025-04-17T16:46:11Z","title":"Retrieval-Augmented Generation with Conflicting Evidence","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.13079","snapshot_observed_at":"2026-08-07T04:30:08.292192Z","title":"Retrieval-augmented generation with conflicting evidence","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:08.292192Z"},"links":{"cited_paper":"/paper/2504.13079","citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:25f656df6d34f00e0aca13455be7ec671d0883d650dd090c86291affc6b6213d","observation_id":"5a003428-e9fe-4dde-9334-7c1ee9f72528","resolution":{"observed_at":"2026-08-07T04:30:08.292192Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:30:09.894713Z","title":"Chain- of-thought prompting elicits reasoning in large language models,","venue":null,"work_id":"5352bd07-adaa-45e6-bf21-153a73039de1","year":2023},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:08.367976Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:818cda7301dbda1c95e397821b79f00ab52864daf56bbfa808c8aae481bb1ef7","observation_id":"1a9666ea-62ce-4c43-9515-48e46c161cf9","resolution":{"observed_at":"2026-08-07T04:30:10.013791Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:09.759346Z","title":"Corrective retrieval augmented generation,","venue":null,"work_id":"19f7cea0-b230-46b1-bd1e-7cda6e7e7d12","year":2024},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:08.426792Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:45983ddc204b559d0cc385978ba27317914782e3f0400085161282c576424f95","observation_id":"88d1c67e-3838-4eb2-b38a-d779a6111b70","resolution":{"observed_at":"2026-08-07T04:30:09.832197Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.20372","last_updated":"2025-02-28T13:06:02Z","snapshot_observed_at":"2026-08-17T01:24:12.398641Z","submitted_at":"2024-12-29T06:32:36Z","title":"LLM2: Let Large Language Models Harness System 2 Reasoning","version":2},"cited_work":{"arxiv_id":"2412.20372","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.20372","snapshot_observed_at":"2026-08-07T04:30:09.294599Z","title":"LLM2: Let Large Language Models Harness System 2 Reasoning","venue":"cs.CL","work_id":"159ec0d9-e99c-4fd8-8b8b-c46aa36cb3ef","year":2024},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:08.501864Z"},"links":{"cited_paper":"/paper/2412.20372","citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:a812a343fd8ca586cc8b5b7e36c582400dd8e47c1179c84d2bb17016ef471570","observation_id":"1ace8234-f45f-4bb4-9f39-00ba628384fa","resolution":{"observed_at":"2026-08-07T04:30:09.361065Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:09.623362Z","title":"React: Synergizing reasoning and acting in language models,","venue":null,"work_id":"c2ee410a-24fd-462e-b518-64a921d2db75","year":2023},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:08.606526Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:85eb69343bb1c848a812995268fb7675a9ffb849d6c6e2fa5f04e9afc1034e4c","observation_id":"0d6f572b-4592-407e-a57a-27c06162eb56","resolution":{"observed_at":"2026-08-07T04:30:09.696351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10594","last_updated":"2025-03-02T01:19:51Z","snapshot_observed_at":"2026-08-13T17:45:25.269133Z","submitted_at":"2024-10-14T15:04:18Z","title":"VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10594","snapshot_observed_at":"2026-08-07T04:30:08.650785Z","title":"Visrag: Vision- based retrieval-augmented generation on multi-modality documents","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:08.650785Z"},"links":{"cited_paper":"/paper/2410.10594","citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:d3ca3b80bcf144e35790748ef10dcbd5daba286bef1f5c4120a584c583949341","observation_id":"f8f6b3b5-16ed-4479-89af-dfb1be378405","resolution":{"observed_at":"2026-08-07T04:30:08.650785Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.04176","last_updated":"2025-04-21T12:02:08Z","snapshot_observed_at":"2026-08-17T10:47:56.823907Z","submitted_at":"2025-02-06T16:07:24Z","title":"MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.04176","snapshot_observed_at":"2026-08-07T04:30:08.756767Z","title":"Mramg- bench: A beyondtext benchmark for multimodal retrieval- augmented multimodal generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:08.756767Z"},"links":{"cited_paper":"/paper/2502.04176","citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:dbda3f6d7164eef47e5717a2a79c392831f260368c66e21e1d66505925dccaf3","observation_id":"064feb79-9ef9-4f0c-996c-f11af597f472","resolution":{"observed_at":"2026-08-07T04:30:08.756767Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.01219","last_updated":"2025-09-14T09:34:46Z","snapshot_observed_at":"2026-08-16T12:38:46.158503Z","submitted_at":"2023-09-03T16:56:48Z","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.01219","snapshot_observed_at":"2026-08-07T04:30:08.810792Z","title":"Controlling large language model-based agents for large-scale decision- making: An actor-critic approach","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:08.810792Z"},"links":{"cited_paper":"/paper/2309.01219","citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:285d5ed885922da576a3828ed5fd1d78145d81879527f80073177fc9bd5275ff","observation_id":"34f51945-facc-4a88-a11f-156cc5e2d64f","resolution":{"observed_at":"2026-08-07T04:30:08.810792Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.18223","last_updated":"2026-03-18T05:34:39Z","snapshot_observed_at":"2026-08-14T10:40:26.323157Z","submitted_at":"2023-03-31T17:28:46Z","title":"A Survey of Large Language Models","version":19},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.18223","snapshot_observed_at":"2026-08-07T04:30:08.918878Z","title":"A survey of large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:08.918878Z"},"links":{"cited_paper":"/paper/2303.18223","citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:8e5363c691a8c9deab85000af94ade9d80e7b6a4d3da7353d9e3b7749666436c","observation_id":"963ef742-ebcf-4155-b2ee-256d7108dee9","resolution":{"observed_at":"2026-08-07T04:30:08.918878Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.19473","last_updated":"2024-06-21T08:26:36Z","snapshot_observed_at":"2026-08-13T05:27:55.126585Z","submitted_at":"2024-02-29T18:59:01Z","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.19473","snapshot_observed_at":"2026-08-07T04:30:08.992476Z","title":"Retrieval-augmented generation for ai-generated content: A survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:08.992476Z"},"links":{"cited_paper":"/paper/2402.19473","citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:37b5e7818b92dfad401f451b27f93fa2b52e0d5a8973846e7bf7d7a839203754","observation_id":"54e0f691-691f-4c81-a3d5-6ce99fd23b01","resolution":{"observed_at":"2026-08-07T04:30:08.992476Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:30:09.477363Z","title":"Deep- researcher: Scaling deep research via reinforcement learn- ing in real-world environments,","venue":null,"work_id":"54d0c936-ebdd-4d9d-9bc4-93020ce85243","year":2025},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:09.072214Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:0111e657c22c04fc70fc842fdd80b8b73214588a855e5a10e336094f529181fc","observation_id":"9617d8f7-9d5f-4a5b-bc1e-7464529d83fb","resolution":{"observed_at":"2026-08-07T04:30:09.547572Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07815","last_updated":"2024-10-10T06:01:10Z","snapshot_observed_at":"2026-08-16T13:43:56.911063Z","submitted_at":"2024-06-12T02:23:51Z","title":"Are Large Language Models Good Statisticians?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07815","snapshot_observed_at":"2026-08-07T04:30:09.163795Z","title":"Are large language models good statisticians? arXiv preprint arXiv:2406.07815, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:09.163795Z"},"links":{"cited_paper":"/paper/2406.07815","citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:850f773a0c25c8ac6d2c293be3242f22f7fdba2a2b31639985d79d76cc7a7ecb","observation_id":"68780ad4-44bb-4623-b483-b27dd852b222","resolution":{"observed_at":"2026-08-07T04:30:09.163795Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:30:10.737159Z","title":"Tptu: Task planning and tool usage of large language model- based ai agents","venue":null,"work_id":"86fa65f8-0f8a-4049-b781-09f2084dcb38","year":2023},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:07.790263Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:3b146f0f9190678df436746bdf93c7851ee360e6d838c7209f28d9f8af72e5fd","observation_id":"dc2582f4-4d40-4879-bbea-2b1a14979d86","resolution":{"observed_at":"2026-08-07T04:30:10.791317Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:10.376401Z","title":"Deepseekmath: Pushing the limits of mathematical rea- soning in open language models,","venue":null,"work_id":"ec66768d-21e9-4831-b570-c2d37d27759d","year":2024},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:08.049518Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:9d5b71b364b1a040def57e9efd23e7cb72973d9261942343e0086249212745df","observation_id":"568d48fe-d811-4273-8754-bcdc84e15bf5","resolution":{"observed_at":"2026-08-07T04:30:10.429595Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.10446","last_updated":"2024-03-15T16:30:14Z","snapshot_observed_at":"2026-08-16T14:09:23.490734Z","submitted_at":"2024-03-15T16:30:14Z","title":"Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.10446","snapshot_observed_at":"2026-08-07T04:30:06.966462Z","title":"Enhancing llm factual accuracy with rag to counter hallucinations: A case study on domain-specific queries in private knowledge- bases","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:06.966462Z"},"links":{"cited_paper":"/paper/2403.10446","citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:0610d944a4eda7d73d0ee9ed6808e3d0d65ccd4c0fe480148d8cd83a1bc7b1d7","observation_id":"2a9f8471-bff2-4b7b-a1e3-cf9be5a7eeb9","resolution":{"observed_at":"2026-08-07T04:30:06.966462Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:30:13.793171Z","title":"Bench- marking large language models in retrieval-augmented gen- eration","venue":null,"work_id":"865fad38-0415-4a25-98a8-c7153bef01ff","year":2024},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:06.027277Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:e51f467b8fc21385f02e6e63096dde05917161c66754df6757a80ac69f310490","observation_id":"97252f72-40ce-427c-9eb5-fd3186a5975c","resolution":{"observed_at":"2026-08-07T04:30:13.888091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:13.650446Z","title":"Rezero: En- hancing llm search ability by trying one-more-time,","venue":null,"work_id":"e182e408-33f3-4c3a-b13d-9e98c4db4bde","year":2025},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:06.097976Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:63a80d6c6ae30863cf8c788e908bfeb52e557add95096870d47da3a3a221e7fa","observation_id":"e6bc1334-12c7-4c11-9834-73559fcf97c2","resolution":{"observed_at":"2026-08-07T04:30:13.720771Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T04:30:13.389171Z","title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning,","venue":null,"work_id":"b3f319b6-9000-44f0-aaec-2d951b64af36","year":2025},"citing_paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:06.162442Z"},"links":{"citing_paper":"/paper/2506.10408"},"observation_digest":"sha256:82d9ee6ee1e57499cf38d8c380599b9b83f924abea2ea90218b473473700d93c","observation_id":"dcc3b8f5-1b2d-446f-aaef-792ad7d6556e","resolution":{"observed_at":"2026-08-07T04:30:13.553909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.10408","last_updated":"2025-06-12T07:01:56Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-09T17:34:32.242783Z","submitted_at":"2025-06-12T07:01:56Z","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":1,"verified_fuzzy":29},"total_outbound_references":42},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 6 inbound Pith citation observations for arXiv:2506.10408."}