{"as_of":"2026-08-06T09:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:25efdd15ab00597c8da241a5bafa942dd3ec46cd3b16ed5e0442cc590ffed3cb","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":19,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":19,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+00:00","state":"measured"},{"denominator":19,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":19,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T14:22:46.685290Z","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":1,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":"2403.02502","doi":"10.48550/arxiv.2403.02502","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents","venue":"arXiv (Cornell University)","work_id":"e9f4e923-14da-4180-9f84-15011e539433","year":2024},"citing_paper":{"arxiv_id":"2501.09686","last_updated":"2025-01-23T08:44:44Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-16T17:37:58Z","title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","version":3},"reference_index":137,"source":"pdf_text","source_observed_at":"2026-05-15T21:20:59.128986Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2501.09686"},"observation_digest":"sha256:f7e18a5baf0d0a32998382e29b038356fa7756a23a41f75e52e87b5d7c341e83","observation_id":"45c31990-362d-4cfc-a117-e735ae0d5ab2","resolution":{"observed_at":"2026-05-15T21:20:59.285843Z","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":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":"2403.02502","doi":"10.48550/arxiv.2403.02502","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents","venue":"arXiv (Cornell University)","work_id":"e9f4e923-14da-4180-9f84-15011e539433","year":2024},"citing_paper":{"arxiv_id":"2506.23978","last_updated":"2026-05-16T17:29:09Z","snapshot_observed_at":"2026-08-04T08:40:19.416980Z","submitted_at":"2025-06-30T15:45:17Z","title":"LLM Agents Are the Antidote to Walled Gardens","version":3},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-05-22T00:41:19.750928Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2506.23978"},"observation_digest":"sha256:43f877d9d35c7042b40ceb3f91ccd90da6a89a7ccbcddeff305c1de65832eae4","observation_id":"b60306bd-6d8a-499b-a9cb-8c15f2fe02c3","resolution":{"observed_at":"2026-05-22T00:44:29.334526Z","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":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-08-05T14:22:46.685290Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.21456","last_updated":"2025-08-29T09:39:00Z","snapshot_observed_at":"2026-08-05T14:22:40.150859Z","submitted_at":"2025-08-29T09:39:00Z","title":"Morae: Proactively Pausing UI Agents for User Choices","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-05T14:22:46.685290Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2508.21456"},"observation_digest":"sha256:56c2ad42e4dba5e2d28faf1183185dae81ffb2c61755c53ade235d57d7221a66","observation_id":"5f4bc58d-d935-4fc3-a9bc-4aeb5ac374f0","resolution":{"observed_at":"2026-08-05T14:22:46.685290Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":"2403.02502","doi":"10.48550/arxiv.2403.02502","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents","venue":"arXiv (Cornell University)","work_id":"e9f4e923-14da-4180-9f84-15011e539433","year":2024},"citing_paper":{"arxiv_id":"2603.29908","last_updated":"2026-03-31T15:53:29Z","snapshot_observed_at":"2026-08-06T01:33:29.158513Z","submitted_at":"2026-03-31T15:53:29Z","title":"C-TRAIL: A Commonsense World Framework for Trajectory Planning in Autonomous Driving","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-13T23:27:31.054348Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2603.29908"},"observation_digest":"sha256:e79ddb61a6d50e1fa500662c6a6f074d8d8fc6c6edc49d95bb473c7e14825c7a","observation_id":"12da300c-43b1-44f2-98bc-522a405c6a9b","resolution":{"observed_at":"2026-05-13T23:28:26.147204Z","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":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":"2403.02502","doi":"10.48550/arxiv.2403.02502","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents","venue":"arXiv (Cornell University)","work_id":"e9f4e923-14da-4180-9f84-15011e539433","year":2024},"citing_paper":{"arxiv_id":"2604.08178","last_updated":"2026-05-11T07:26:22Z","snapshot_observed_at":"2026-08-02T16:02:49.097271Z","submitted_at":"2026-04-09T12:35:06Z","title":"Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-10T17:12:21.813803Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2604.08178"},"observation_digest":"sha256:4dc625fb03600d4ffba582242af685dddb5d4ffd546571f939641b7f30a92157","observation_id":"b8590005-2a87-4ab2-9c57-800e77e5cf8d","resolution":{"observed_at":"2026-05-11T07:21:00.765636Z","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":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":"2403.02502","doi":"10.48550/arxiv.2403.02502","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents","venue":"arXiv (Cornell University)","work_id":"e9f4e923-14da-4180-9f84-15011e539433","year":2024},"citing_paper":{"arxiv_id":"2604.08178","last_updated":"2026-05-11T07:26:22Z","snapshot_observed_at":"2026-08-02T16:02:49.097271Z","submitted_at":"2026-04-09T12:35:06Z","title":"Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-12T02:59:19.674646Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2604.08178"},"observation_digest":"sha256:8eede15ed2850c9b0d8f0debbf6cd4663119ff066f17d0e3283c1dd39c49ea2b","observation_id":"0cfeddd9-b98e-4306-a053-a6e73a32ab6b","resolution":{"observed_at":"2026-05-12T03:01:18.099969Z","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":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":"2403.02502","doi":"10.48550/arxiv.2403.02502","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents","venue":"arXiv (Cornell University)","work_id":"e9f4e923-14da-4180-9f84-15011e539433","year":2024},"citing_paper":{"arxiv_id":"2604.23194","last_updated":"2026-04-25T07:54:23Z","snapshot_observed_at":"2026-07-06T23:09:29.537323Z","submitted_at":"2026-04-25T07:54:23Z","title":"From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM Agents","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-05-08T08:10:36.579810Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2604.23194"},"observation_digest":"sha256:2fd0b49158d153f75c5b4fc9d6b3ea05e77ea91ca1af8355f11ce79a102c2d3b","observation_id":"d3140644-00be-4e5f-8aca-39e20086c8f1","resolution":{"observed_at":"2026-05-11T20:46:10.341474Z","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":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":"2403.02502","doi":"10.48550/arxiv.2403.02502","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents","venue":"arXiv (Cornell University)","work_id":"e9f4e923-14da-4180-9f84-15011e539433","year":2024},"citing_paper":{"arxiv_id":"2605.10500","last_updated":"2026-05-11T12:58:25Z","snapshot_observed_at":"2026-08-05T13:34:21.296589Z","submitted_at":"2026-05-11T12:58:25Z","title":"SkillEvolver: Skill Learning as a Meta-Skill","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-12T04:56:14.360454Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2605.10500"},"observation_digest":"sha256:e6fb300e47612f45cfcfbff9c46825eea0a4720cc8bd027f88a959a390a8a27f","observation_id":"3c960811-bc23-4655-8161-f73b79095dc4","resolution":{"observed_at":"2026-05-12T05:46:30.933210Z","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":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":"2403.02502","doi":"10.48550/arxiv.2403.02502","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents","venue":"arXiv (Cornell University)","work_id":"e9f4e923-14da-4180-9f84-15011e539433","year":2024},"citing_paper":{"arxiv_id":"2605.24828","last_updated":"2026-05-31T15:58:08Z","snapshot_observed_at":"2026-08-03T07:25:06.734747Z","submitted_at":"2026-05-24T02:41:44Z","title":"Test-Time Deep Thinking to Explore Implicit Rules","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-30T11:52:15.163893Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2605.24828"},"observation_digest":"sha256:98deb784f4ec5237e2eb887362668ee45a495e7f315c91e969e49ff59b2b7402","observation_id":"d1c0b134-c71e-4b73-90ff-762b459da0c9","resolution":{"observed_at":"2026-06-30T11:54:38.217679Z","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":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":"2403.02502","doi":"10.48550/arxiv.2403.02502","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents","venue":"arXiv (Cornell University)","work_id":"e9f4e923-14da-4180-9f84-15011e539433","year":2024},"citing_paper":{"arxiv_id":"2605.27209","last_updated":"2026-05-26T16:02:00Z","snapshot_observed_at":"2026-08-03T11:00:10.339186Z","submitted_at":"2026-05-26T16:02:00Z","title":"Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-06-29T16:51:36.524194Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2605.27209"},"observation_digest":"sha256:67be6e56a506d082495cb2eedc3476cbaa688db66a7ac2a933ef52ee78270a20","observation_id":"c280ebd1-32be-4256-a36c-38317269654f","resolution":{"observed_at":"2026-06-29T16:53:40.485548Z","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":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":"2403.02502","doi":"10.48550/arxiv.2403.02502","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents","venue":"arXiv (Cornell University)","work_id":"e9f4e923-14da-4180-9f84-15011e539433","year":2024},"citing_paper":{"arxiv_id":"2605.28775","last_updated":"2026-05-27T17:37:00Z","snapshot_observed_at":"2026-07-06T23:38:19.096349Z","submitted_at":"2026-05-27T17:37:00Z","title":"Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-29T14:15:55.180284Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2605.28775"},"observation_digest":"sha256:bd278ea0d62ece6791c02ffdc990b4f4139a248c2bbd78291aa53d1a155a850d","observation_id":"465c0c7f-110c-41a7-8dd9-56c9b0b2ffa3","resolution":{"observed_at":"2026-06-29T14:23:30.930994Z","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":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":"2403.02502","doi":"10.48550/arxiv.2403.02502","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents","venue":"arXiv (Cornell University)","work_id":"e9f4e923-14da-4180-9f84-15011e539433","year":2024},"citing_paper":{"arxiv_id":"2606.01581","last_updated":"2026-06-01T02:26:39Z","snapshot_observed_at":"2026-07-06T23:42:07.508474Z","submitted_at":"2026-06-01T02:26:39Z","title":"Agent System Operations: Categorization, Challenges, and Future Directions","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-28T12:14:21.322860Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2606.01581"},"observation_digest":"sha256:3091d7236d25b4ac58057ff68de6e84a7724d5e1947183db4de31d173ee26f4d","observation_id":"0255e5ca-c9ab-478c-997a-1620b4704b82","resolution":{"observed_at":"2026-07-02T01:16:24.960638Z","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":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":"2403.02502","doi":"10.48550/arxiv.2403.02502","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents","venue":"arXiv (Cornell University)","work_id":"e9f4e923-14da-4180-9f84-15011e539433","year":2024},"citing_paper":{"arxiv_id":"2606.10507","last_updated":"2026-06-09T07:35:14Z","snapshot_observed_at":"2026-08-05T06:17:13.116592Z","submitted_at":"2026-06-09T07:35:14Z","title":"HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-27T13:04:28.758614Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2606.10507"},"observation_digest":"sha256:cec5b3c97c824d48c6cd966c5fc9a2243327a3aa028bfe0b47ca6c943d842647","observation_id":"df35d8ce-acec-4f5e-9f04-c505f631a1b5","resolution":{"observed_at":"2026-07-03T05:47:41.660750Z","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":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":"2403.02502","doi":"10.48550/arxiv.2403.02502","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents","venue":"arXiv (Cornell University)","work_id":"e9f4e923-14da-4180-9f84-15011e539433","year":2024},"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":285,"source":"pdf_text","source_observed_at":"2026-06-27T09:46:30.702256Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2606.12191"},"observation_digest":"sha256:47574b99719c56dd59e67214c099e1326f03b306a69c61e61871e5252aef6238","observation_id":"e8c4f43d-36dc-4651-a696-660148e50156","resolution":{"observed_at":"2026-06-27T09:50:48.540036Z","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":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":"2403.02502","doi":"10.48550/arxiv.2403.02502","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents","venue":"arXiv (Cornell University)","work_id":"e9f4e923-14da-4180-9f84-15011e539433","year":2024},"citing_paper":{"arxiv_id":"2606.17628","last_updated":"2026-06-16T07:33:53Z","snapshot_observed_at":"2026-08-05T17:08:33.405254Z","submitted_at":"2026-06-16T07:33:53Z","title":"OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation","version":1},"reference_index":115,"source":"arxiv_source","source_observed_at":"2026-06-27T01:07:49.603969Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2606.17628"},"observation_digest":"sha256:e27f90fc1a580416930b63d9e860b69497cd28f7c2d4836f8a1e6711454ff840","observation_id":"4b8f4369-4b4a-45bf-a075-4a9fb3033cb8","resolution":{"observed_at":"2026-07-03T20:48:56.469629Z","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":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":"2403.02502","doi":"10.48550/arxiv.2403.02502","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents","venue":"arXiv (Cornell University)","work_id":"e9f4e923-14da-4180-9f84-15011e539433","year":2024},"citing_paper":{"arxiv_id":"2606.21740","last_updated":"2026-06-19T20:53:10Z","snapshot_observed_at":"2026-08-01T23:24:43.869329Z","submitted_at":"2026-06-19T20:53:10Z","title":"Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-06-26T13:56:51.914966Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2606.21740"},"observation_digest":"sha256:69b7b842d5cd48a7cbafbab09239146b4cd47b2e2cfa11bee64cc6f0d15b32d9","observation_id":"a7b3a7f0-21cc-44b3-bd62-fe69125b1956","resolution":{"observed_at":"2026-07-04T06:59:38.168063Z","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":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":"2403.02502","doi":"10.48550/arxiv.2403.02502","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents","venue":"arXiv (Cornell University)","work_id":"e9f4e923-14da-4180-9f84-15011e539433","year":2024},"citing_paper":{"arxiv_id":"2606.22385","last_updated":"2026-06-21T08:22:23Z","snapshot_observed_at":"2026-08-01T18:23:09.613202Z","submitted_at":"2026-06-21T08:22:23Z","title":"MetaPS: Adaptive Programmatic Strategy Selection for Market Agents","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-06-26T11:06:28.690956Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2606.22385"},"observation_digest":"sha256:07a2fa1596d74fae84ee8b405846a5bade8cc40351195a5c4bd8967e072c4926","observation_id":"b3c80fb3-719f-4334-8921-b1545b440c14","resolution":{"observed_at":"2026-07-04T08:39:42.730106Z","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":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-07-14T10:33:54.851493Z","title":"Trial and error: Exploration-based trajectory optimization for LLM agents.arXiv preprint arXiv:2403.02502, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.10601","last_updated":"2026-07-12T06:38:55Z","snapshot_observed_at":"2026-07-16T23:18:52.250852Z","submitted_at":"2026-07-12T06:38:55Z","title":"Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-14T10:33:54.851493Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2607.10601"},"observation_digest":"sha256:390e38913109e045516d0937dfbc002faf069f153b007a426eeaca89a2e32e64","observation_id":"9e11918f-c40e-4fcf-9e2c-4f56c9e8a377","resolution":{"observed_at":"2026-07-14T10:33:54.851493Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02502","last_updated":"2024-07-10T17:36:25Z","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02502","snapshot_observed_at":"2026-07-31T00:46:11.219569Z","title":"Trial and error: Exploration-based trajectory optimization for llm agents.arXiv preprint arXiv:2403.02502, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.27443","last_updated":"2026-07-29T20:14:43Z","snapshot_observed_at":"2026-08-06T07:25:46.863771Z","submitted_at":"2026-07-29T20:14:43Z","title":"Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-31T00:46:11.219569Z"},"links":{"cited_paper":"/paper/2403.02502","citing_paper":"/paper/2607.27443"},"observation_digest":"sha256:3990286d84094e2a697b1c514d7ff2eb7b08386177156958cb495161c98b26c3","observation_id":"e4d25527-dbe6-4bf0-8e64-2cf2c4db6b9d","resolution":{"observed_at":"2026-07-31T00:46:11.219569Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2403.02502/citation-record","integrity":"/paper/2403.02502/integrity","json":"/paper/2403.02502/citation-record.json","paper":"/paper/2403.02502"},"outbound":[],"paper":{"arxiv_id":"2403.02502","last_updated":"2024-07-10T17:36:25Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T17:39:32.800594Z","submitted_at":"2024-03-04T21:50:29Z","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents"},"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 19 inbound Pith citation observations for arXiv:2403.02502."}