{"as_of":"2026-08-06T21:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e768498600b654471be74126eca65bcefa3b9db947dd07e97154968513513d09","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":22,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":22,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+00:00","state":"measured"},{"denominator":22,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":22,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T17:26:29.063843Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"pith","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":0,"observed_at":"2026-08-05T02:28:24.338817Z","source":"pith"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T17:26:29.063843Z","title":"A survey of llm-based deep search agents: Paradigm, optimization, evaluation, and challenges","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.16279","last_updated":"2025-08-22T10:35:56Z","snapshot_observed_at":"2026-08-06T11:01:05.912134Z","submitted_at":"2025-08-22T10:35:56Z","title":"AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications","version":1},"reference_index":108,"source":"arxiv_source","source_observed_at":"2026-08-05T17:26:29.063843Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2508.16279"},"observation_digest":"sha256:e16e0942cf9b6b8e51451eae8db2e9c1a63670ad24e385466d20cdaa09c3c546","observation_id":"fd40398d-4e15-4daf-b7ab-e6fe59d0ebb1","resolution":{"observed_at":"2026-08-05T17:26:29.063843Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":"2508.05668","doi":"10.48550/arxiv.2508.05668","metadata_source":"pith","pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2508.05668 , year=","venue":"cs.IR","work_id":"d504829e-614b-4812-bb38-8ee43f2a863f","year":2025},"citing_paper":{"arxiv_id":"2510.00861","last_updated":"2026-04-20T08:17:44Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-10-01T13:10:36Z","title":"Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-18T11:06:20.058342Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2510.00861"},"observation_digest":"sha256:f90003c9fa5456c77934cdb97adf5b7560d0e16b4f4411ef3211ab7a97a40426","observation_id":"4266b1db-1aad-4bdb-b26b-791ebcb31019","resolution":{"observed_at":"2026-05-18T11:11:18.254256Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":"2508.05668","doi":"10.48550/arxiv.2508.05668","metadata_source":"pith","pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2508.05668 , year=","venue":"cs.IR","work_id":"d504829e-614b-4812-bb38-8ee43f2a863f","year":2025},"citing_paper":{"arxiv_id":"2510.14703","last_updated":"2026-04-28T18:17:43Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-10-16T14:06:03Z","title":"ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-18T06:30:39.858246Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2510.14703"},"observation_digest":"sha256:6d38cace7ff3f8441003e19e12a3485b4e3289f39110fbb21239573b49f7b346","observation_id":"43344374-0792-4759-a849-971fb36ac07d","resolution":{"observed_at":"2026-05-18T06:30:59.569559Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-03T09:22:24.031110Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.14224","last_updated":"2026-06-01T03:09:08Z","snapshot_observed_at":"2026-08-03T09:22:21.728148Z","submitted_at":"2026-01-20T18:38:35Z","title":"Rerank Before You Reason: Analyzing Reranking Tradeoffs through Effective Token Cost in Deep Search Agents","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-03T09:22:24.031110Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2601.14224"},"observation_digest":"sha256:3ee4dbac0c50ed2e36cc8dafa5178328efa050d6d617308db71cb9c944c5122a","observation_id":"464da0e5-f8a2-4f4c-984f-9ba853564ee0","resolution":{"observed_at":"2026-08-03T09:22:24.031110Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-02T23:04:38.875335Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.14878","last_updated":"2026-05-31T05:10:10Z","snapshot_observed_at":"2026-08-02T23:04:25.658810Z","submitted_at":"2026-02-16T16:10:11Z","title":"Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions","version":3},"reference_index":108,"source":"pdf_text","source_observed_at":"2026-08-02T23:04:38.875335Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2602.14878"},"observation_digest":"sha256:fcc028784e1b640bbb997cbd44b5469ea161b4dbcf2fd630144daa9b3e9afdfb","observation_id":"2e94120d-74fc-466b-9d30-21a16f45df08","resolution":{"observed_at":"2026-08-02T23:04:38.875335Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":"2508.05668","doi":"10.48550/arxiv.2508.05668","metadata_source":"pith","pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2508.05668 , year=","venue":"cs.IR","work_id":"d504829e-614b-4812-bb38-8ee43f2a863f","year":2025},"citing_paper":{"arxiv_id":"2604.04949","last_updated":"2026-03-30T17:59:02Z","snapshot_observed_at":"2026-07-06T22:53:46.999911Z","submitted_at":"2026-03-30T17:59:02Z","title":"Learning to Retrieve from Agent Trajectories","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-14T01:47:44.558384Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2604.04949"},"observation_digest":"sha256:15a084b8c7e2a6a4657bc72481458f5b7675c4f4ea63e787691f911628003e1c","observation_id":"16a6bc5d-085b-44a9-a6b6-d22fd7bc0982","resolution":{"observed_at":"2026-05-14T01:48:36.104459Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":"2508.05668","doi":"10.48550/arxiv.2508.05668","metadata_source":"pith","pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2508.05668 , year=","venue":"cs.IR","work_id":"d504829e-614b-4812-bb38-8ee43f2a863f","year":2025},"citing_paper":{"arxiv_id":"2604.05952","last_updated":"2026-04-07T14:46:26Z","snapshot_observed_at":"2026-08-02T13:02:05.536176Z","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":23,"source":"arxiv_source","source_observed_at":"2026-05-10T19:41:00.530274Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2604.05952"},"observation_digest":"sha256:ff1a600c0bd5549475dc8b7b36537b5140f039d52a40a56b32e4eca90dc43f1b","observation_id":"7b690d0e-3f97-4e57-9427-fc43f264d21b","resolution":{"observed_at":"2026-05-10T22:35:52.035835Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":"2508.05668","doi":"10.48550/arxiv.2508.05668","metadata_source":"pith","pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2508.05668 , year=","venue":"cs.IR","work_id":"d504829e-614b-4812-bb38-8ee43f2a863f","year":2025},"citing_paper":{"arxiv_id":"2604.08224","last_updated":"2026-04-09T13:19:41Z","snapshot_observed_at":"2026-08-02T22:56:00.067549Z","submitted_at":"2026-04-09T13:19:41Z","title":"Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering","version":1},"reference_index":162,"source":"arxiv_source","source_observed_at":"2026-05-10T17:40:14.733882Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2604.08224"},"observation_digest":"sha256:c6221480871465303fcc06ff31260567f4bc58155a6b774fcbf1843f4cba244f","observation_id":"4d2b283c-6527-4909-becf-3e922f46bb7f","resolution":{"observed_at":"2026-05-11T06:20:59.186406Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":"2508.05668","doi":"10.48550/arxiv.2508.05668","metadata_source":"pith","pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2508.05668 , year=","venue":"cs.IR","work_id":"d504829e-614b-4812-bb38-8ee43f2a863f","year":2025},"citing_paper":{"arxiv_id":"2604.12890","last_updated":"2026-04-25T02:32:57Z","snapshot_observed_at":"2026-07-06T23:01:00.830207Z","submitted_at":"2026-04-14T15:40:28Z","title":"Towards Long-horizon Agentic Multimodal Search","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-10T15:40:32.137708Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2604.12890"},"observation_digest":"sha256:cdf4376eb6047516a68a0aee7df77f12241659606da7dc3bacb16251e8c501e1","observation_id":"58b40efd-2edb-4470-ae4d-18b47fd8c12a","resolution":{"observed_at":"2026-05-11T10:06:00.211792Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":"2508.05668","doi":"10.48550/arxiv.2508.05668","metadata_source":"pith","pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2508.05668 , year=","venue":"cs.IR","work_id":"d504829e-614b-4812-bb38-8ee43f2a863f","year":2025},"citing_paper":{"arxiv_id":"2604.27859","last_updated":"2026-05-15T06:25:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-30T13:43:25Z","title":"Rethinking Agentic Reinforcement Learning In Large Language Models","version":1},"reference_index":103,"source":"pdf_text","source_observed_at":"2026-05-07T06:30:09.945371Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2604.27859"},"observation_digest":"sha256:1390af39eab3d90780fecb7f10edc718e82aa8707c62c0559708f7e8e1a214b2","observation_id":"5b7e3d95-3900-4719-ad00-bca5dc1e4e81","resolution":{"observed_at":"2026-05-12T10:21:29.997032Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":"2508.05668","doi":"10.48550/arxiv.2508.05668","metadata_source":"pith","pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2508.05668 , year=","venue":"cs.IR","work_id":"d504829e-614b-4812-bb38-8ee43f2a863f","year":2025},"citing_paper":{"arxiv_id":"2604.27859","last_updated":"2026-05-15T06:25:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-30T13:43:25Z","title":"Rethinking Agentic Reinforcement Learning In Large Language Models","version":2},"reference_index":103,"source":"pdf_text","source_observed_at":"2026-05-08T03:12:19.414358Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2604.27859"},"observation_digest":"sha256:9dce2dac3b720eea2844274c74405b6455dee34b6c03ea5ca269843d0375f9e9","observation_id":"bd0760be-d400-46b0-b4ac-ce327f4be458","resolution":{"observed_at":"2026-05-11T22:11:16.875985Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":"2508.05668","doi":"10.48550/arxiv.2508.05668","metadata_source":"pith","pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2508.05668 , year=","venue":"cs.IR","work_id":"d504829e-614b-4812-bb38-8ee43f2a863f","year":2025},"citing_paper":{"arxiv_id":"2604.27859","last_updated":"2026-05-15T06:25:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-30T13:43:25Z","title":"Rethinking Agentic Reinforcement Learning In Large Language Models","version":3},"reference_index":103,"source":"pdf_text","source_observed_at":"2026-05-19T16:58:41.558250Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2604.27859"},"observation_digest":"sha256:2b37f0763ce9482a4bacab8eadd5156ee0a96dfdd8ee0bddeba3c18421d3095d","observation_id":"9182d4be-c741-47a6-916e-8ea4bc9cb1b3","resolution":{"observed_at":"2026-05-19T17:02:40.673324Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":"2508.05668","doi":"10.48550/arxiv.2508.05668","metadata_source":"pith","pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2508.05668 , year=","venue":"cs.IR","work_id":"d504829e-614b-4812-bb38-8ee43f2a863f","year":2025},"citing_paper":{"arxiv_id":"2605.00043","last_updated":"2026-04-29T06:18:07Z","snapshot_observed_at":"2026-08-02T13:23:22.858169Z","submitted_at":"2026-04-29T06:18:07Z","title":"SiriusHelper: An LLM Agent-Based Operations Assistant for Big Data Platforms","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-09T21:07:01.601808Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2605.00043"},"observation_digest":"sha256:867bbc590537c92827e937bd5096d49adcca800c7b3d5aa8a3a6e538c1e1545c","observation_id":"e643a8d9-d12c-470b-8146-91e666ad5a8f","resolution":{"observed_at":"2026-05-11T14:46:23.671715Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":"2508.05668","doi":"10.48550/arxiv.2508.05668","metadata_source":"pith","pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2508.05668 , year=","venue":"cs.IR","work_id":"d504829e-614b-4812-bb38-8ee43f2a863f","year":2025},"citing_paper":{"arxiv_id":"2605.09915","last_updated":"2026-05-11T03:07:15Z","snapshot_observed_at":"2026-08-03T01:38:17.964750Z","submitted_at":"2026-05-11T03:07:15Z","title":"Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-12T05:03:10.013340Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2605.09915"},"observation_digest":"sha256:47390781e9e468b03c808c2abf38b8221d1bef3d4bae5882d3cc2ff4dc3293b2","observation_id":"fc4ccc06-6b43-46a3-ac8d-8a1b2ba9acd6","resolution":{"observed_at":"2026-05-12T05:41:26.150940Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":"2508.05668","doi":"10.48550/arxiv.2508.05668","metadata_source":"pith","pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2508.05668 , year=","venue":"cs.IR","work_id":"d504829e-614b-4812-bb38-8ee43f2a863f","year":2025},"citing_paper":{"arxiv_id":"2605.10488","last_updated":"2026-05-11T12:48:31Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-05-11T12:48:31Z","title":"DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-12T04:19:01.836535Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2605.10488"},"observation_digest":"sha256:4443ae7c75bcfcd55ba82f0ed4ea529f8c907aacab04a9495182b2efd0588e5c","observation_id":"a91df4ae-4735-48a0-a27d-6d0410558fc8","resolution":{"observed_at":"2026-05-12T06:26:23.574460Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":"2508.05668","doi":"10.48550/arxiv.2508.05668","metadata_source":"pith","pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2508.05668 , year=","venue":"cs.IR","work_id":"d504829e-614b-4812-bb38-8ee43f2a863f","year":2025},"citing_paper":{"arxiv_id":"2605.13534","last_updated":"2026-05-13T13:46:35Z","snapshot_observed_at":"2026-08-01T07:40:39.216212Z","submitted_at":"2026-05-13T13:46:35Z","title":"Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-14T18:52:42.989888Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2605.13534"},"observation_digest":"sha256:d91d112299e79c602203e9dd81a0e642812a046dbc9c7d7bc03527df2e4c6fa4","observation_id":"4034df69-f88c-4012-9025-af2ea420a97f","resolution":{"observed_at":"2026-05-14T18:57:50.400199Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":"2508.05668","doi":"10.48550/arxiv.2508.05668","metadata_source":"pith","pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2508.05668 , year=","venue":"cs.IR","work_id":"d504829e-614b-4812-bb38-8ee43f2a863f","year":2025},"citing_paper":{"arxiv_id":"2605.16986","last_updated":"2026-07-29T10:19:54Z","snapshot_observed_at":"2026-08-02T13:52:40.874253Z","submitted_at":"2026-05-16T13:14:15Z","title":"Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-05-19T20:32:54.215770Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2605.16986"},"observation_digest":"sha256:2e583ee05e633b5ad95485b83bc4a8c27e18f7a5a6fcbbca94bec8197ce45101","observation_id":"637a08b8-a3b0-456a-ac68-5b0e52449469","resolution":{"observed_at":"2026-05-19T20:33:13.107489Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":"2508.05668","doi":"10.48550/arxiv.2508.05668","metadata_source":"pith","pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2508.05668 , year=","venue":"cs.IR","work_id":"d504829e-614b-4812-bb38-8ee43f2a863f","year":2025},"citing_paper":{"arxiv_id":"2605.29555","last_updated":"2026-05-28T08:09:35Z","snapshot_observed_at":"2026-07-06T23:38:56.014434Z","submitted_at":"2026-05-28T08:09:35Z","title":"From Blind Guess to Informed Judgment: Teaching LLMs to Evaluate Materials by Building Knowledge-Augmented Preference Signals","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-29T07:31:24.683525Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2605.29555"},"observation_digest":"sha256:4a0aef2d7c10627e0c9be99e0361e6a8b1c6dd3faa8e06f9973a3f3b1c3f5cef","observation_id":"c202f943-1dbc-4855-80a8-3da4ea0bf596","resolution":{"observed_at":"2026-06-29T07:33:13.358551Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":"2508.05668","doi":"10.48550/arxiv.2508.05668","metadata_source":"pith","pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2508.05668 , year=","venue":"cs.IR","work_id":"d504829e-614b-4812-bb38-8ee43f2a863f","year":2025},"citing_paper":{"arxiv_id":"2606.11926","last_updated":"2026-06-10T10:57:05Z","snapshot_observed_at":"2026-07-06T23:50:53.469137Z","submitted_at":"2026-06-10T10:57:05Z","title":"Toward Generalist Autonomous Research via Hypothesis-Tree Refinement","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-06-27T09:34:41.800309Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2606.11926"},"observation_digest":"sha256:66164a6d8da3b4074d702b9ba11401872106dddcca9c06a82bf41ea7372bc267","observation_id":"4cfc8b1b-d6f0-408f-8f1a-c8ee0900f7f6","resolution":{"observed_at":"2026-06-27T09:40:47.128809Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":"2508.05668","doi":"10.48550/arxiv.2508.05668","metadata_source":"pith","pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2508.05668 , year=","venue":"cs.IR","work_id":"d504829e-614b-4812-bb38-8ee43f2a863f","year":2025},"citing_paper":{"arxiv_id":"2607.06374","last_updated":"2026-07-07T15:11:56Z","snapshot_observed_at":"2026-08-02T23:51:44.948258Z","submitted_at":"2026-07-07T15:11:56Z","title":"VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-08T08:00:31.873224Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2607.06374"},"observation_digest":"sha256:dbaff6fe2080af29d09d674090ad4db78f90fdd100317a2654c14d5b7b99b3d8","observation_id":"27adf1d2-70cc-4dd5-995a-a2c887028ec8","resolution":{"observed_at":"2026-07-08T08:04:47.982149Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-04T18:27:16.707483Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.01913","last_updated":"2026-08-03T08:46:48Z","snapshot_observed_at":"2026-08-06T21:27:29.925844Z","submitted_at":"2026-08-03T08:46:48Z","title":"Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agents","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T18:27:16.707483Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2608.01913"},"observation_digest":"sha256:f82e4d65ac036287b9fc649c494cfc75157bee6e65ffcabd7a9cb21512560503","observation_id":"4bc0d0a2-02c0-49a2-8efa-63e0404f1ed7","resolution":{"observed_at":"2026-08-04T18:27:16.707483Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.05668","snapshot_observed_at":"2026-08-04T15:12:56.091613Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02097","last_updated":"2026-08-03T11:58:21Z","snapshot_observed_at":"2026-08-06T21:27:56.962466Z","submitted_at":"2026-08-03T11:58:21Z","title":"Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents","version":1},"reference_index":216,"source":"arxiv_source","source_observed_at":"2026-08-04T15:12:56.091613Z"},"links":{"cited_paper":"/paper/2508.05668","citing_paper":"/paper/2608.02097"},"observation_digest":"sha256:b293a1452e16d2020f713051693c30ab66a4ffe22756d78cad77e635735641a5","observation_id":"fc91d440-2d38-4afb-a2b5-7fa12697bdef","resolution":{"observed_at":"2026-08-04T15:12:56.091613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2508.05668/citation-record","integrity":"/paper/2508.05668/integrity","json":"/paper/2508.05668/citation-record.json","paper":"/paper/2508.05668"},"outbound":[],"paper":{"arxiv_id":"2508.05668","last_updated":"2025-08-19T05:15:19Z","latest_version":3,"primary_category":"cs.IR","snapshot_observed_at":"2026-08-06T05:30:35.068556Z","submitted_at":"2025-08-03T08:02:51Z","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 22 inbound Pith citation observations for arXiv:2508.05668."}