{"as_of":"2026-08-10T11:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e1f78a6fb863a0b200faa7e077a1b803f0526b7166aac8ab11993c8e5604b202","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T13:45:13.744163Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":10,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":10,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T15:12:55.803255Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","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":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.00375","snapshot_observed_at":"2026-08-04T08:48:44.022931Z","title":"Open data synthesis for deep research, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.18939","last_updated":"2026-07-14T02:30:28Z","snapshot_observed_at":"2026-08-10T10:56:22.881573Z","submitted_at":"2025-10-21T17:58:45Z","title":"Lost in the Maze: Overcoming Context Limitations in Long-Horizon Agentic Search","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-04T08:48:44.022931Z"},"links":{"cited_paper":"/paper/2509.00375","citing_paper":"/paper/2510.18939"},"observation_digest":"sha256:9073032ea7915a018b1bae8658eeba8f7a5f9c995d57791417c20f8e6d64f6c4","observation_id":"902daa26-e857-4576-90cd-5784b9ca8960","resolution":{"observed_at":"2026-08-04T08:48:44.022931Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"cited_work":{"arxiv_id":"2509.00375","doi":"10.48550/arxiv.2509.00375","metadata_source":"arxiv_reference","pith_arxiv_id":"2509.00375","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Unlabeled/Other","venue":"ArXiv.org","work_id":"21a6b05f-3311-4cf5-881d-1dcd9ddd76aa","year":2025},"citing_paper":{"arxiv_id":"2602.13218","last_updated":"2026-04-05T16:18:56Z","snapshot_observed_at":"2026-08-02T21:44:00.625209Z","submitted_at":"2026-01-23T13:26:01Z","title":"Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-16T12:12:30.041005Z"},"links":{"cited_paper":"/paper/2509.00375","citing_paper":"/paper/2602.13218"},"observation_digest":"sha256:34b407f660ad2d63c221256267648b64ba3d556390316f595cfc955c4f20d0f9","observation_id":"2ca88b65-f366-489f-be5c-74f95098c5e1","resolution":{"observed_at":"2026-05-16T12:12:51.101340Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"cited_work":{"arxiv_id":"2509.00375","doi":"10.48550/arxiv.2509.00375","metadata_source":"arxiv_reference","pith_arxiv_id":"2509.00375","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Unlabeled/Other","venue":"ArXiv.org","work_id":"21a6b05f-3311-4cf5-881d-1dcd9ddd76aa","year":2025},"citing_paper":{"arxiv_id":"2604.04949","last_updated":"2026-03-30T17:59:02Z","snapshot_observed_at":"2026-08-07T19:35:23.113481Z","submitted_at":"2026-03-30T17:59:02Z","title":"Learning to Retrieve from Agent Trajectories","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-14T01:47:44.558384Z"},"links":{"cited_paper":"/paper/2509.00375","citing_paper":"/paper/2604.04949"},"observation_digest":"sha256:35c9becc16b6eb81f8c5b85aed2e0e044d02db755e0c2ddd8f843bc2d2871976","observation_id":"1c46dc45-be74-42f4-9ad9-bd745142935a","resolution":{"observed_at":"2026-05-14T01:48:36.098393Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"cited_work":{"arxiv_id":"2509.00375","doi":"10.48550/arxiv.2509.00375","metadata_source":"arxiv_reference","pith_arxiv_id":"2509.00375","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Unlabeled/Other","venue":"ArXiv.org","work_id":"21a6b05f-3311-4cf5-881d-1dcd9ddd76aa","year":2025},"citing_paper":{"arxiv_id":"2604.14029","last_updated":"2026-07-29T13:04:29Z","snapshot_observed_at":"2026-08-02T16:18:18.484070Z","submitted_at":"2026-04-15T16:09:37Z","title":"POINTS-Seeker: An Open Recipe for Multimodal Search Agents with Visual Memory Management","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-10T13:09:24.304696Z"},"links":{"cited_paper":"/paper/2509.00375","citing_paper":"/paper/2604.14029"},"observation_digest":"sha256:03fdc31402bce040475c378524d1c9f4e40274020f3bffd37f4e00d275272634","observation_id":"8cb3d55a-893c-4926-8b76-e8568037aabb","resolution":{"observed_at":"2026-05-10T13:10:26.476983Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.00375","snapshot_observed_at":"2026-08-02T16:18:25.106504Z","title":"arXiv preprint arXiv:2509.00375 (2025) 6, 20 18 F","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.14029","last_updated":"2026-07-29T13:04:29Z","snapshot_observed_at":"2026-08-02T16:18:18.484070Z","submitted_at":"2026-04-15T16:09:37Z","title":"POINTS-Seeker: An Open Recipe for Multimodal Search Agents with Visual Memory Management","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-02T16:18:25.106504Z"},"links":{"cited_paper":"/paper/2509.00375","citing_paper":"/paper/2604.14029"},"observation_digest":"sha256:3f539a643d32fdcc17ab0089e3c5a38f1868ea4404ec638416cdae5c12909581","observation_id":"0bb23a1d-8b67-4794-8210-b72fbde161a6","resolution":{"observed_at":"2026-08-02T16:18:25.106504Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"cited_work":{"arxiv_id":"2509.00375","doi":"10.48550/arxiv.2509.00375","metadata_source":"arxiv_reference","pith_arxiv_id":"2509.00375","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Unlabeled/Other","venue":"ArXiv.org","work_id":"21a6b05f-3311-4cf5-881d-1dcd9ddd76aa","year":2025},"citing_paper":{"arxiv_id":"2605.07177","last_updated":"2026-05-11T11:21:13Z","snapshot_observed_at":"2026-08-03T10:59:43.380213Z","submitted_at":"2026-05-08T03:16:08Z","title":"HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-11T01:28:36.266167Z"},"links":{"cited_paper":"/paper/2509.00375","citing_paper":"/paper/2605.07177"},"observation_digest":"sha256:98f363e1aa5be3fbae4489b123ccbfaf22136ba919e492a013a13962f404fe8e","observation_id":"5649073c-62e3-48b1-af02-5c3a72e6ec48","resolution":{"observed_at":"2026-05-11T01:45:52.317362Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"cited_work":{"arxiv_id":"2509.00375","doi":"10.48550/arxiv.2509.00375","metadata_source":"arxiv_reference","pith_arxiv_id":"2509.00375","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Unlabeled/Other","venue":"ArXiv.org","work_id":"21a6b05f-3311-4cf5-881d-1dcd9ddd76aa","year":2025},"citing_paper":{"arxiv_id":"2605.07177","last_updated":"2026-05-11T11:21:13Z","snapshot_observed_at":"2026-08-03T10:59:43.380213Z","submitted_at":"2026-05-08T03:16:08Z","title":"HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-12T03:18:01.006274Z"},"links":{"cited_paper":"/paper/2509.00375","citing_paper":"/paper/2605.07177"},"observation_digest":"sha256:608223de7f04874e9312a74a7a4762ea2b6be8ce3e682244c244ddc718174c10","observation_id":"0880bf4e-d718-41d5-a047-668cec95db32","resolution":{"observed_at":"2026-05-12T03:21:19.026653Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"cited_work":{"arxiv_id":"2509.00375","doi":"10.48550/arxiv.2509.00375","metadata_source":"arxiv_reference","pith_arxiv_id":"2509.00375","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Unlabeled/Other","venue":"ArXiv.org","work_id":"21a6b05f-3311-4cf5-881d-1dcd9ddd76aa","year":2025},"citing_paper":{"arxiv_id":"2606.12087","last_updated":"2026-06-10T13:49:11Z","snapshot_observed_at":"2026-08-02T15:03:50.335992Z","submitted_at":"2026-06-10T13:49:11Z","title":"FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-06-27T10:01:45.332920Z"},"links":{"cited_paper":"/paper/2509.00375","citing_paper":"/paper/2606.12087"},"observation_digest":"sha256:18d4fd2cabe36e05baabcfa0f0a1eead871cd2bb60fed9ce96bf136fef27256a","observation_id":"988ed784-0343-432a-8af5-6aacf7aa0904","resolution":{"observed_at":"2026-07-03T10:27:56.444815Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"cited_work":{"arxiv_id":"2509.00375","doi":"10.48550/arxiv.2509.00375","metadata_source":"arxiv_reference","pith_arxiv_id":"2509.00375","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Unlabeled/Other","venue":"ArXiv.org","work_id":"21a6b05f-3311-4cf5-881d-1dcd9ddd76aa","year":2025},"citing_paper":{"arxiv_id":"2606.12191","last_updated":"2026-06-10T15:15:01Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-06-10T15:15:01Z","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-06-27T09:46:30.702256Z"},"links":{"cited_paper":"/paper/2509.00375","citing_paper":"/paper/2606.12191"},"observation_digest":"sha256:f2129e99dc94451b925dc09d99d4821c5862aa9cc283213a810d5942da8ccf0e","observation_id":"5ed714ef-7fed-42ce-b0d1-a26e4501faa2","resolution":{"observed_at":"2026-06-27T09:50:48.353965Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.00375","snapshot_observed_at":"2026-08-04T15:12:55.803255Z","title":"2025 , archivePrefix =","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02097","last_updated":"2026-08-03T11:58:21Z","snapshot_observed_at":"2026-08-09T08:55:51.965628Z","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":114,"source":"arxiv_source","source_observed_at":"2026-08-04T15:12:55.803255Z"},"links":{"cited_paper":"/paper/2509.00375","citing_paper":"/paper/2608.02097"},"observation_digest":"sha256:9577975350fe9bff4894120b0de97c6459c8a116c19a59c0e2b7c4e8b780016e","observation_id":"cd7621d0-a636-442c-a7f2-f090a868eeb4","resolution":{"observed_at":"2026-08-04T15:12:55.803255Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2509.00375/citation-record","integrity":"/paper/2509.00375/integrity","json":"/paper/2509.00375/citation-record.json","paper":"/paper/2509.00375"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T13:45:14.948981Z","title":"Next, we conduct the second stage of reinforcement learning","venue":null,"work_id":"518291ff-6e19-462c-8650-583cabd9fba2","year":2023},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:13.744163Z"},"links":{"citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:82f5d984c0e1fa395069f7888bdd63d2b1a11a157c0b72895437181ccc748c73","observation_id":"57e90753-9c4b-49c9-abeb-aa7ce9abdfb8","resolution":{"observed_at":"2026-08-05T13:45:15.018944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.00414","last_updated":"2026-04-22T08:14:17Z","snapshot_observed_at":"2026-08-02T16:42:25.825514Z","submitted_at":"2025-08-01T08:11:31Z","title":"Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.00414","snapshot_observed_at":"2026-08-05T13:45:11.590993Z","title":"Cognitive kernel-pro: A framework for deep research agents and agent foundation models training","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:11.590993Z"},"links":{"cited_paper":"/paper/2508.00414","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:2d916df9bf81cbbbc0a08b2e2183c353dcbc3da07322d4a66ec375526785d087","observation_id":"1c078b26-1e0b-4d38-a34b-834b59fdab0f","resolution":{"observed_at":"2026-08-05T13:45:11.590993Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.06261","last_updated":"2025-12-19T14:25:46Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-07-07T17:36:04Z","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.06261","snapshot_observed_at":"2026-08-05T13:45:11.645449Z","title":"Qwen Group","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:11.645449Z"},"links":{"cited_paper":"/paper/2507.06261","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:1f2bda6b7943385b36bb6c2c92c6611a45e5ab71bf62e976c1dac710f7c86289","observation_id":"c35809ec-5754-4179-91b0-be83303a28b7","resolution":{"observed_at":"2026-08-05T13:45:11.645449Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-05T13:45:11.698405Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:11.698405Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:be6d7206e141ffc484d56e03801294cb11daf189bca69905b983db409378c735","observation_id":"6c7efccc-5c36-44c2-99e4-801f1d441dc5","resolution":{"observed_at":"2026-08-05T13:45:11.698405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.16075","last_updated":"2025-07-21T21:23:21Z","snapshot_observed_at":"2026-08-07T12:20:24.237770Z","submitted_at":"2025-07-21T21:23:21Z","title":"Deep Researcher with Test-Time Diffusion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.16075","snapshot_observed_at":"2026-08-05T13:45:11.775915Z","title":"Deep researcher with test-time diffusion","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:11.775915Z"},"links":{"cited_paper":"/paper/2507.16075","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:23bb67550612c0e6aec743ac5a2ae86dacf34b7d557367b439421e375b37987d","observation_id":"ff94a419-327a-4215-91a4-d508473c1573","resolution":{"observed_at":"2026-08-05T13:45:11.775915Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.01060","last_updated":"2020-11-12T07:47:48Z","snapshot_observed_at":"2026-07-06T10:10:56.466018Z","submitted_at":"2020-11-02T15:42:40Z","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.01060","snapshot_observed_at":"2026-08-05T13:45:11.820398Z","title":"Constructing a multi-hop qa dataset for comprehensive evaluation of reasoning steps","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:11.820398Z"},"links":{"cited_paper":"/paper/2011.01060","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:f0f928c721870c903368f387d19ad52d70988f0e79d5c700be8cc592496d6494","observation_id":"df384e68-eb04-4108-971d-c394512442a0","resolution":{"observed_at":"2026-08-05T13:45:11.820398Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.09516","last_updated":"2025-08-05T19:08:38Z","snapshot_observed_at":"2026-07-06T20:51:28.022519Z","submitted_at":"2025-03-12T16:26:39Z","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.09516","snapshot_observed_at":"2026-08-05T13:45:11.976736Z","title":"Search- r1: Training llms to reason and leverage search engines with reinforcement learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:11.976736Z"},"links":{"cited_paper":"/paper/2503.09516","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:78fff541c872582fc87f80080be01c912dd66151292d41e8ebeeeb49d27e94be","observation_id":"788e5e96-a1c4-4fad-9790-04349983b374","resolution":{"observed_at":"2026-08-05T13:45:11.976736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.09516","last_updated":"2025-08-05T19:08:38Z","snapshot_observed_at":"2026-07-06T20:51:28.022519Z","submitted_at":"2025-03-12T16:26:39Z","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.09516","snapshot_observed_at":"2026-08-05T13:45:12.038009Z","title":"URL https://doi.org/10","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:12.038009Z"},"links":{"cited_paper":"/paper/2503.09516","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:05e1a3ddcedcc1f83d5131de509937a255f5c9ef53be55a3c6ffa38d7c02a2cc","observation_id":"4fb63bbe-8308-4a46-9caf-1f2d2c592017","resolution":{"observed_at":"2026-08-05T13:45:12.038009Z","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":"2026-08-05T13:45:15.361050Z","title":"14 Technical report Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al","venue":null,"work_id":"d4d8e3f5-58a5-4cf1-8197-6d834a3f2ee1","year":2025},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:12.192635Z"},"links":{"citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:08805c471e155c09c2c82ff4268da6a735fde263c9dfbdcfe3e7d7902b8b770f","observation_id":"82576d0c-c8fa-40f1-8c65-7d048df87609","resolution":{"observed_at":"2026-08-05T13:45:15.457259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.03350","last_updated":"2023-10-17T18:57:17Z","snapshot_observed_at":"2026-08-10T00:54:02.555288Z","submitted_at":"2022-10-07T06:50:23Z","title":"Measuring and Narrowing the Compositionality Gap in Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.03350","snapshot_observed_at":"2026-08-05T13:45:12.298235Z","title":"Measuring and narrowing the compositionality gap in language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:12.298235Z"},"links":{"cited_paper":"/paper/2210.03350","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:8732773d7f21fda05daf8c8e8638673168b87456064a616fdfb75f383e3b55bf","observation_id":"e0d55f66-e760-45ab-9ef5-242b6d0bcc9b","resolution":{"observed_at":"2026-08-05T13:45:12.298235Z","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":"2502.13465","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T13:45:14.444457Z","title":"Hawkbench: Investigating resilience of rag methods on stratified information-seeking tasks","venue":null,"work_id":"963aaf4a-6b28-4d8d-9b29-6a66235a9b1b","year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:12.418834Z"},"links":{"citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:6bf0a6e050fd9b338524c80536fa7e6dadf79228edbcecadda4b69f64f86db23","observation_id":"2e4b11ed-0567-4a90-ae0c-ef4857d241af","resolution":{"observed_at":"2026-08-05T13:45:14.516694Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.20286","last_updated":"2025-05-26T17:58:53Z","snapshot_observed_at":"2026-08-07T15:21:20.945396Z","submitted_at":"2025-05-26T17:58:53Z","title":"Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.20286","snapshot_observed_at":"2026-08-05T13:45:12.481722Z","title":"Alita: Generalist agent enabling scalable agentic reasoning with minimal predefinition and maximal self-evolution","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:12.481722Z"},"links":{"cited_paper":"/paper/2505.20286","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:da9e2c6e4ca53df40a3f009f3d31b4e769fe97c6d268885b448da401b03b9489","observation_id":"1941d97a-8332-4671-a5b5-fa55cc4cb781","resolution":{"observed_at":"2026-08-05T13:45:12.481722Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T13:45:12.812195Z","title":"Pangu deepdiver: Adaptive search intensity scaling via open-web reinforcement learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:12.812195Z"},"links":{"citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:3bb90430c85cc717dd30253553176d4031f4a7a3a29c5f5044720dd2e829cfdd","observation_id":"96ae09e3-40bc-4870-8ea4-cd2326ff7d70","resolution":{"observed_at":"2026-08-05T13:45:12.812195Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.04588","last_updated":"2026-05-19T11:51:42Z","snapshot_observed_at":"2026-08-04T18:36:41.979541Z","submitted_at":"2025-05-07T17:30:22Z","title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.04588","snapshot_observed_at":"2026-08-05T13:45:12.880393Z","title":"Zerosearch: Incentivize the search capability of llms without searching","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:12.880393Z"},"links":{"cited_paper":"/paper/2505.04588","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:ea8901ad0acbca9b49e794314d80f45f603700d73957a3616bba6f50ed50dbce","observation_id":"23b0208c-f8d2-48f6-aa1c-a6b1e0843da2","resolution":{"observed_at":"2026-08-05T13:45:12.880393Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10671","last_updated":"2024-09-10T13:25:53Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-07-15T12:35:42Z","title":"Qwen2 Technical Report","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.10671","snapshot_observed_at":"2026-08-05T13:45:12.966279Z","title":"Qwen2 technical report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:12.966279Z"},"links":{"cited_paper":"/paper/2407.10671","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:c4c13ac3e112e793fb0948924cd17fda19b404cca358963a2be2d5e4ad31e499","observation_id":"52723a50-cf53-423d-b5c2-90fe0b142f5a","resolution":{"observed_at":"2026-08-05T13:45:12.966279Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.10509","last_updated":"2023-06-23T00:59:13Z","snapshot_observed_at":"2026-07-06T14:33:08.041820Z","submitted_at":"2022-12-20T18:26:34Z","title":"Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.10509","snapshot_observed_at":"2026-08-05T13:45:13.050432Z","title":"Interleaving re- trieval with chain-of-thought reasoning for knowledge-intensive multi-step questions","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:13.050432Z"},"links":{"cited_paper":"/paper/2212.10509","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:d18139b8b1e7aea153f2dcdd5db28c977814f875b5495016472628c37b1cffd4","observation_id":"bbfa09ef-40af-4dd6-a06a-e8cf811499b9","resolution":{"observed_at":"2026-08-05T13:45:13.050432Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.12516","last_updated":"2025-04-16T22:27:45Z","snapshot_observed_at":"2026-08-03T00:43:33.338074Z","submitted_at":"2025-04-16T22:27:45Z","title":"BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.12516","snapshot_observed_at":"2026-08-05T13:45:13.108221Z","title":"Browsecomp: A simple yet challenging benchmark for browsing agents","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:13.108221Z"},"links":{"cited_paper":"/paper/2504.12516","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:612dc4b882ec13541ee9264e7bfe7927c182aed8f6d957d76bdef065d911575e","observation_id":"488771f2-8483-4d15-b829-1b80f323ac68","resolution":{"observed_at":"2026-08-05T13:45:13.108221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.07572","last_updated":"2025-08-10T05:59:20Z","snapshot_observed_at":"2026-08-09T20:43:41.220993Z","submitted_at":"2025-01-13T18:58:07Z","title":"WebWalker: Benchmarking LLMs in Web Traversal","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.07572","snapshot_observed_at":"2026-08-05T13:45:13.203875Z","title":"Webdancer: Towards autonomous information seeking agency, 2025a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:13.203875Z"},"links":{"cited_paper":"/paper/2501.07572","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:aca59aecedb27840018a66f7d85f13dcfa4adff4121611773225b281bbc155c8","observation_id":"4acf394a-80e4-4910-87b1-0967ce9e5168","resolution":{"observed_at":"2026-08-05T13:45:13.203875Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-08-05T13:45:13.288450Z","title":"Qwen3 technical report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:13.288450Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:c6ca06dbe8dbecd519e7376c10f24c0848b9c79eb549eb6280f9a044c76201ee","observation_id":"fa4559d7-d8b0-4e67-9844-968734406a40","resolution":{"observed_at":"2026-08-05T13:45:13.288450Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.09600","last_updated":"2018-09-25T17:28:20Z","snapshot_observed_at":"2026-08-09T10:11:58.541007Z","submitted_at":"2018-09-25T17:28:20Z","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.09600","snapshot_observed_at":"2026-08-05T13:45:13.378399Z","title":"Hotpotqa: A dataset for diverse, explainable multi-hop question answering","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:13.378399Z"},"links":{"cited_paper":"/paper/1809.09600","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:5b98c0e0ec58cc354a9e864d16ad09f5ebdce37327cb8858248c4013cd7cb9c9","observation_id":"edfbb634-fa44-407f-8a7c-f71cd0a7b2d2","resolution":{"observed_at":"2026-08-05T13:45:13.378399Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.09713","last_updated":"2025-02-23T03:23:46Z","snapshot_observed_at":"2026-08-05T07:48:17.311058Z","submitted_at":"2024-10-13T03:45:24Z","title":"Agentic Information Retrieval","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.09713","snapshot_observed_at":"2026-08-05T13:45:13.460438Z","title":"Agentic information retrieval","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:13.460438Z"},"links":{"cited_paper":"/paper/2410.09713","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:86c1dba0148bc7f3e077f03d75da3550833a036c967cd87f7a78e6abcb14381d","observation_id":"085b71de-e681-4f06-9644-85c554ffeaa7","resolution":{"observed_at":"2026-08-05T13:45:13.460438Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.12508","last_updated":"2026-05-28T07:38:36Z","snapshot_observed_at":"2026-08-07T00:45:11.426426Z","submitted_at":"2025-06-14T13:45:37Z","title":"AgentOrchestra: Orchestrating Multi-Agent Intelligence with the Tool-Environment-Agent(TEA) Protocol","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.12508","snapshot_observed_at":"2026-08-05T13:45:13.545426Z","title":"Agentorches- tra: A hierarchical multi-agent framework for general-purpose task solving","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:13.545426Z"},"links":{"cited_paper":"/paper/2506.12508","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:15c8da368486d6a33129ac1c7758178d459d72ba4160aad3e51b10872c196edd","observation_id":"eb491e3e-a787-4dc0-86d4-ec8d280d851b","resolution":{"observed_at":"2026-08-05T13:45:13.545426Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.14924","last_updated":"2024-09-23T11:20:20Z","snapshot_observed_at":"2026-08-10T10:50:05.915856Z","submitted_at":"2024-09-23T11:20:20Z","title":"Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.14924","snapshot_observed_at":"2026-08-05T13:45:13.613918Z","title":"Yuxiang Zheng, Dayuan Fu, Xiangkun Hu, Xiaojie Cai, Lyumanshan Ye, Pengrui Lu, and Pengfei Liu","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:13.613918Z"},"links":{"cited_paper":"/paper/2409.14924","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:c6e073e0b6ddea850d92b8adca6c765ce8a542ef621f95e5ed5ef4d3516f958b","observation_id":"d51a29c2-c421-448f-8281-6e5b4431d019","resolution":{"observed_at":"2026-08-05T13:45:13.613918Z","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":"2026-08-05T13:45:15.133044Z","title":"shortcut","venue":null,"work_id":"5c02c2b7-e1b4-4793-b05b-94f9acf3e469","year":2025},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:13.674162Z"},"links":{"citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:0d3afc2f80fce47396ea0b5b6d6658e237e2a0c7a0f718f74a559364a18a54ad","observation_id":"bc5b8a63-854e-459d-9723-736403b9df16","resolution":{"observed_at":"2026-08-05T13:45:15.200744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.00610","last_updated":"2024-03-31T08:58:54Z","snapshot_observed_at":"2026-08-09T13:15:07.647793Z","submitted_at":"2024-03-31T08:58:54Z","title":"RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.00610","snapshot_observed_at":"2026-08-05T13:45:11.359396Z","title":"RQ- RAG: learning to refine queries for retrieval augmented generation.CoRR, abs/2404.00610,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":1976,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:11.359396Z"},"links":{"cited_paper":"/paper/2404.00610","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:fa0767a774ce099b3aa3609f2142f6c595f7fb1e5f6f298a8cda6035d8f74499","observation_id":"d1ca22b1-0123-4818-9a96-498baefa963c","resolution":{"observed_at":"2026-08-05T13:45:11.359396Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1506.02438","last_updated":"2018-10-20T18:55:07Z","snapshot_observed_at":"2026-08-09T23:04:15.431743Z","submitted_at":"2015-06-08T11:12:48Z","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.02438","snapshot_observed_at":"2026-08-05T13:45:12.553416Z","title":"High- dimensional continuous control using generalized advantage estimation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:12.553416Z"},"links":{"cited_paper":"/paper/1506.02438","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:0adac4ffbc75a16a9379d56f47203073d97be5e2255a059d17c998806ccfc670","observation_id":"bb9447a8-5dab-4752-bc39-7f055dbbf040","resolution":{"observed_at":"2026-08-05T13:45:12.553416Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-08-05T13:45:12.651316Z","title":"Proximal policy optimization algorithms","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:12.651316Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:37c8ad5a6acfa11dbed71dc56ae3eaea78a3413cce1d5f0a4b1dadb539616d47","observation_id":"51020e55-4f25-442b-abf3-11595a9198b5","resolution":{"observed_at":"2026-08-05T13:45:12.651316Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03300","last_updated":"2024-04-27T15:25:53Z","snapshot_observed_at":"2026-08-06T14:58:42.911363Z","submitted_at":"2024-02-05T18:55:32Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-08-05T13:45:12.737814Z","title":"Deepseekmath: Pushing the limits of mathemati- cal reasoning in open language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:12.737814Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:297638710cc4ce211388778da672e47a4555bf49fa854846edd994ff57318a27","observation_id":"990c622e-a4c8-44a6-9332-c6a3a8e7b6a9","resolution":{"observed_at":"2026-08-05T13:45:12.737814Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.02592","last_updated":"2025-07-03T12:59:07Z","snapshot_observed_at":"2026-08-09T01:03:55.193390Z","submitted_at":"2025-07-03T12:59:07Z","title":"WebSailor: Navigating Super-human Reasoning for Web Agent","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.02592","snapshot_observed_at":"2026-08-05T13:45:12.135736Z","title":"Websailor: Navigating super-human reasoning for web agent","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:12.135736Z"},"links":{"cited_paper":"/paper/2507.02592","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:c740b809f4a651545ada361f33d91916a2649208954d1755c245784feca3aa24","observation_id":"b55c6770-84ad-4a04-b6ed-81b4a1a5c535","resolution":{"observed_at":"2026-08-05T13:45:12.135736Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.16720","last_updated":"2026-04-30T02:46:40Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-21T18:04:31Z","title":"OpenAI o1 System Card","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.16720","snapshot_observed_at":"2026-08-05T13:45:11.868980Z","title":"Openai o1 system card","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:11.868980Z"},"links":{"cited_paper":"/paper/2412.16720","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:da9e4ddac2b8fd064e26426f8e8050a3ac0bc40e3d6b1609d2053ca419ca49e0","observation_id":"46c89d5a-ce45-45ba-b26a-afcbd3e4536c","resolution":{"observed_at":"2026-08-05T13:45:11.868980Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T13:45:12.341801Z","title":"Scent of knowledge: Optimizing search-enhanced reasoning with information foraging","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:12.341801Z"},"links":{"citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:247b708e7da2a2938b9795368a10d6442f7885f39afa3fbdbfc1a2abc5e80806","observation_id":"60c71515-6770-4f91-bc24-87c5935698f1","resolution":{"observed_at":"2026-08-05T13:45:12.341801Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.19470","last_updated":"2025-09-23T03:45:42Z","snapshot_observed_at":"2026-08-10T03:47:52.773511Z","submitted_at":"2025-03-25T09:00:58Z","title":"ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.19470","snapshot_observed_at":"2026-08-05T13:45:11.469664Z","title":"Learning to reason with search for llms via reinforce- ment learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:11.469664Z"},"links":{"cited_paper":"/paper/2503.19470","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:c4908e68e460fcd4abe3cd2fe6d200b15cf638b2661ed65fb52b65496e72998a","observation_id":"e851582e-a11c-4268-8ab1-04791c355845","resolution":{"observed_at":"2026-08-05T13:45:11.469664Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.00610","last_updated":"2024-03-31T08:58:54Z","snapshot_observed_at":"2026-08-09T13:15:07.647793Z","submitted_at":"2024-03-31T08:58:54Z","title":"RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.00610","snapshot_observed_at":"2026-08-05T13:45:11.399188Z","title":"URL https://doi.org/10.48550/arXiv.2404","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:11.399188Z"},"links":{"cited_paper":"/paper/2404.00610","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:9c4935300e46d270f6873f1606d368e8c493bf0123946778ad9c65c13b202a93","observation_id":"cbd2aa57-6f18-4acc-b836-73395ee09a68","resolution":{"observed_at":"2026-08-05T13:45:11.399188Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.11511","last_updated":"2023-10-17T18:18:32Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-17T18:18:32Z","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.11511","snapshot_observed_at":"2026-08-05T13:45:11.313077Z","title":"Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:11.313077Z"},"links":{"cited_paper":"/paper/2310.11511","citing_paper":"/paper/2509.00375"},"observation_digest":"sha256:bc9ff1b12071ddf03e4f686cdffd6092656e6fb7fcb12375efdcae0471e94c8f","observation_id":"010e1081-4ccf-42b1-8b51-87b92f2e4ab1","resolution":{"observed_at":"2026-08-05T13:45:11.313077Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.00375","last_updated":"2025-08-30T06:02:56Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-09T10:52:17.524309Z","submitted_at":"2025-08-30T06:02:56Z","title":"Open Data Synthesis For Deep Research"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":29,"verified_exact":1,"verified_fuzzy":3},"total_outbound_references":34},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 10 inbound Pith citation observations for arXiv:2509.00375."}