{"as_of":"2026-08-18T02:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:648e352f7f5ffa67c13aced8b8a5dd8787f5ec4d9e0424c1a7c6d78d36bef663","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":14,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":14,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":14,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T12:24:04.530447Z","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":2,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.11651","last_updated":"2024-04-16T11:41:13Z","snapshot_observed_at":"2026-08-16T19:23:14.478746Z","submitted_at":"2024-02-18T17:10:07Z","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","version":2},"cited_work":{"arxiv_id":"2402.11651","doi":"10.48550/arxiv.2402.11651","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.11651","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning from failure: Integrating negative examples when fine-tuning large language models as agents","venue":"arXiv (Cornell University)","work_id":"52cd6fe7-55b7-481f-aeb6-984d7c073995","year":2024},"citing_paper":{"arxiv_id":"2410.13181","last_updated":"2026-05-18T11:27:02Z","snapshot_observed_at":"2026-08-17T19:16:06.132846Z","submitted_at":"2024-10-17T03:07:37Z","title":"AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning","version":3},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-05-23T18:46:08.566035Z"},"links":{"cited_paper":"/paper/2402.11651","citing_paper":"/paper/2410.13181"},"observation_digest":"sha256:354961cf697134d8dbb3054cfd3d64ca32c7f2fdf2cc9c1463bbea166847f26e","observation_id":"ebce67f4-bfa5-497f-b4d9-cf4dd332b1c7","resolution":{"observed_at":"2026-05-23T18:48:20.386266Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-05-20T22:23:34.654123+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-20T22:23:34.654123+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11651","last_updated":"2024-04-16T11:41:13Z","snapshot_observed_at":"2026-08-16T19:23:14.478746Z","submitted_at":"2024-02-18T17:10:07Z","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11651","snapshot_observed_at":"2026-08-12T05:09:47.918852Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00722","last_updated":"2024-12-01T08:10:04Z","snapshot_observed_at":"2026-08-15T06:03:35.308374Z","submitted_at":"2024-12-01T08:10:04Z","title":"Towards Adaptive Mechanism Activation in Language Agent","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-12T05:09:47.918852Z"},"links":{"cited_paper":"/paper/2402.11651","citing_paper":"/paper/2412.00722"},"observation_digest":"sha256:9c3c1296c3ba5a9ffc81541e95876c2b8846b9e6b4ed6f3b1ddede98745427e0","observation_id":"1f11527f-9088-4f73-b740-6982e84933bc","resolution":{"observed_at":"2026-08-12T05:09:47.918852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11651","last_updated":"2024-04-16T11:41:13Z","snapshot_observed_at":"2026-08-16T19:23:14.478746Z","submitted_at":"2024-02-18T17:10:07Z","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11651","snapshot_observed_at":"2026-08-08T19:07:35.479808Z","title":"Learning from failure: Integrating negative examples when fine-tuning large language models as agents,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08657","last_updated":"2025-02-08T09:54:47Z","snapshot_observed_at":"2026-08-13T12:10:45.569050Z","submitted_at":"2025-02-08T09:54:47Z","title":"Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human Interventions","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-08T19:07:35.479808Z"},"links":{"cited_paper":"/paper/2402.11651","citing_paper":"/paper/2502.08657"},"observation_digest":"sha256:521d52bb788463e9e22077ba96fcc9f8af9d20419e1f0b62144036f5d9b25a6f","observation_id":"c4f2e0d2-7b2f-4c36-a474-aa7acc360373","resolution":{"observed_at":"2026-08-08T19:07:35.479808Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11651","last_updated":"2024-04-16T11:41:13Z","snapshot_observed_at":"2026-08-16T19:23:14.478746Z","submitted_at":"2024-02-18T17:10:07Z","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11651","snapshot_observed_at":"2026-08-16T12:24:04.530447Z","title":"arXiv preprint arXiv:2402.11651 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13032","last_updated":"2025-04-17T15:41:39Z","snapshot_observed_at":"2026-08-16T12:14:08.787671Z","submitted_at":"2025-04-17T15:41:39Z","title":"InstructRAG: Leveraging Retrieval-Augmented Generation on Instruction Graphs for LLM-Based Task Planning","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-16T12:24:04.530447Z"},"links":{"cited_paper":"/paper/2402.11651","citing_paper":"/paper/2504.13032"},"observation_digest":"sha256:90ee8a34170aec2d2c23ada2df96328c61b129314de1f3e386169df6e727e06e","observation_id":"c5b0055d-7329-42b5-89b6-d4517c227117","resolution":{"observed_at":"2026-08-16T12:24:04.530447Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11651","last_updated":"2024-04-16T11:41:13Z","snapshot_observed_at":"2026-08-16T19:23:14.478746Z","submitted_at":"2024-02-18T17:10:07Z","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11651","snapshot_observed_at":"2026-08-07T14:10:08.942221Z","title":"Learning from failure: Integrating negative examples when fine-tuning large language models as agents","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.19761","last_updated":"2025-05-26T09:43:40Z","snapshot_observed_at":"2026-08-17T22:58:10.438994Z","submitted_at":"2025-05-26T09:43:40Z","title":"Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-07T14:10:08.942221Z"},"links":{"cited_paper":"/paper/2402.11651","citing_paper":"/paper/2505.19761"},"observation_digest":"sha256:7516aa8dcf01d8db3f9259b509a2f03243eed8732d7dc245eb50a29377b6e43e","observation_id":"748cf0a8-fb8c-4516-882a-c84645db6add","resolution":{"observed_at":"2026-08-07T14:10:08.942221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11651","last_updated":"2024-04-16T11:41:13Z","snapshot_observed_at":"2026-08-16T19:23:14.478746Z","submitted_at":"2024-02-18T17:10:07Z","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11651","snapshot_observed_at":"2026-08-07T14:06:56.596041Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20023","last_updated":"2025-05-26T14:11:12Z","snapshot_observed_at":"2026-08-16T13:28:40.997677Z","submitted_at":"2025-05-26T14:11:12Z","title":"Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T14:06:56.596041Z"},"links":{"cited_paper":"/paper/2402.11651","citing_paper":"/paper/2505.20023"},"observation_digest":"sha256:4054fc9bd03638ac683f7f1e6a1aa9e81113b749774d0f89acb8eb1a158addbf","observation_id":"6019eb82-e0fa-4fa5-b0a3-d7dce12e2c28","resolution":{"observed_at":"2026-08-07T14:06:56.596041Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11651","last_updated":"2024-04-16T11:41:13Z","snapshot_observed_at":"2026-08-16T19:23:14.478746Z","submitted_at":"2024-02-18T17:10:07Z","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11651","snapshot_observed_at":"2026-08-07T11:47:50.812929Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.01475","last_updated":"2025-06-02T09:35:07Z","snapshot_observed_at":"2026-08-17T06:56:04.079884Z","submitted_at":"2025-06-02T09:35:07Z","title":"PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T11:47:50.812929Z"},"links":{"cited_paper":"/paper/2402.11651","citing_paper":"/paper/2506.01475"},"observation_digest":"sha256:8ac5681fff387d6fba2f6219d3fd02a0cd9395c9dd602662106e5c9de5870c6b","observation_id":"c4321bbf-c7f3-42b4-90a5-8aca749254dc","resolution":{"observed_at":"2026-08-07T11:47:50.812929Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11651","last_updated":"2024-04-16T11:41:13Z","snapshot_observed_at":"2026-08-16T19:23:14.478746Z","submitted_at":"2024-02-18T17:10:07Z","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11651","snapshot_observed_at":"2026-08-06T21:55:04.444807Z","title":"Learning from failure: Integrating negative examples when fine-tuning large language models as agents","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.23127","last_updated":"2025-06-29T07:31:24Z","snapshot_observed_at":"2026-08-14T15:01:44.047747Z","submitted_at":"2025-06-29T07:31:24Z","title":"Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-06T21:55:04.444807Z"},"links":{"cited_paper":"/paper/2402.11651","citing_paper":"/paper/2506.23127"},"observation_digest":"sha256:1ee63a18dc9d0d1df77e0e53de9fc6e8cfdb2d409d269336d19b7b97305ad463","observation_id":"73074153-2e5e-44f9-81ac-73f5cfc3c85f","resolution":{"observed_at":"2026-08-06T21:55:04.444807Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11651","last_updated":"2024-04-16T11:41:13Z","snapshot_observed_at":"2026-08-16T19:23:14.478746Z","submitted_at":"2024-02-18T17:10:07Z","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11651","snapshot_observed_at":"2026-08-04T09:41:00.977441Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.14331","last_updated":"2026-07-02T12:40:23Z","snapshot_observed_at":"2026-08-14T19:13:06.738966Z","submitted_at":"2025-10-16T06:10:11Z","title":"LLM Priors for ERM over Programs","version":3},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-04T09:41:00.977441Z"},"links":{"cited_paper":"/paper/2402.11651","citing_paper":"/paper/2510.14331"},"observation_digest":"sha256:f3266748a337a7e8e71fe214bf958ad85a1340adbb6cbcff91c95872044c462f","observation_id":"69ab1f96-ecc9-437c-a1b1-9e2e3e7828ed","resolution":{"observed_at":"2026-08-04T09:41:00.977441Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11651","last_updated":"2024-04-16T11:41:13Z","snapshot_observed_at":"2026-08-16T19:23:14.478746Z","submitted_at":"2024-02-18T17:10:07Z","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","version":2},"cited_work":{"arxiv_id":"2402.11651","doi":"10.48550/arxiv.2402.11651","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.11651","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning from failure: Integrating negative examples when fine-tuning large language models as agents","venue":"arXiv (Cornell University)","work_id":"52cd6fe7-55b7-481f-aeb6-984d7c073995","year":2024},"citing_paper":{"arxiv_id":"2604.19710","last_updated":"2026-04-21T17:34:19Z","snapshot_observed_at":"2026-07-06T23:06:16.972438Z","submitted_at":"2026-04-21T17:34:19Z","title":"SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-05-10T02:34:29.624029Z"},"links":{"cited_paper":"/paper/2402.11651","citing_paper":"/paper/2604.19710"},"observation_digest":"sha256:d16a160050858138f55d33936e4dda14bd8a724ee9169dc97b106463c8abfba7","observation_id":"a149a689-1aa9-4f62-9159-2f6e36b7fadf","resolution":{"observed_at":"2026-05-11T12:56:11.106795Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-05-20T22:23:34.654123+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-20T22:23:34.654123+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11651","last_updated":"2024-04-16T11:41:13Z","snapshot_observed_at":"2026-08-16T19:23:14.478746Z","submitted_at":"2024-02-18T17:10:07Z","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","version":2},"cited_work":{"arxiv_id":"2402.11651","doi":"10.48550/arxiv.2402.11651","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.11651","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning from failure: Integrating negative examples when fine-tuning large language models as agents","venue":"arXiv (Cornell University)","work_id":"52cd6fe7-55b7-481f-aeb6-984d7c073995","year":2024},"citing_paper":{"arxiv_id":"2605.11882","last_updated":"2026-05-12T09:56:28Z","snapshot_observed_at":"2026-08-11T20:30:03.018548Z","submitted_at":"2026-05-12T09:56:28Z","title":"On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-13T06:29:32.776647Z"},"links":{"cited_paper":"/paper/2402.11651","citing_paper":"/paper/2605.11882"},"observation_digest":"sha256:cdb78110d4963fe822a2c43dd6e05a08bc861dade6c651c25c2f81184bb9abe2","observation_id":"93fa921f-3737-4600-845a-fcaa19275709","resolution":{"observed_at":"2026-05-13T06:32:24.485251Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-05-20T22:23:34.654123+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-20T22:23:34.654123+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11651","last_updated":"2024-04-16T11:41:13Z","snapshot_observed_at":"2026-08-16T19:23:14.478746Z","submitted_at":"2024-02-18T17:10:07Z","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","version":2},"cited_work":{"arxiv_id":"2402.11651","doi":"10.48550/arxiv.2402.11651","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.11651","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning from failure: Integrating negative examples when fine-tuning large language models as agents","venue":"arXiv (Cornell University)","work_id":"52cd6fe7-55b7-481f-aeb6-984d7c073995","year":2024},"citing_paper":{"arxiv_id":"2605.18684","last_updated":"2026-05-18T17:23:13Z","snapshot_observed_at":"2026-08-15T01:55:30.634730Z","submitted_at":"2026-05-18T17:23:13Z","title":"Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-20T08:58:32.951138Z"},"links":{"cited_paper":"/paper/2402.11651","citing_paper":"/paper/2605.18684"},"observation_digest":"sha256:873bff3d34de2220caf147cec616dfd2077091a87b30aca5542cab25984ac4b5","observation_id":"d957ded0-c6bd-472f-92bc-7d1e7d3f61e1","resolution":{"observed_at":"2026-05-20T09:03:09.726877Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-05-20T22:23:34.654123+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-20T22:23:34.654123+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11651","last_updated":"2024-04-16T11:41:13Z","snapshot_observed_at":"2026-08-16T19:23:14.478746Z","submitted_at":"2024-02-18T17:10:07Z","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","version":2},"cited_work":{"arxiv_id":"2402.11651","doi":"10.48550/arxiv.2402.11651","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.11651","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning from failure: Integrating negative examples when fine-tuning large language models as agents","venue":"arXiv (Cornell University)","work_id":"52cd6fe7-55b7-481f-aeb6-984d7c073995","year":2024},"citing_paper":{"arxiv_id":"2606.25605","last_updated":"2026-06-24T09:14:18Z","snapshot_observed_at":"2026-08-15T11:57:29.856660Z","submitted_at":"2026-06-24T09:14:18Z","title":"Constraint Tax in Open-Weight LLMs: An Empirical Study of Tool Calling Suppression Under Structured Output Constraints","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-25T20:58:26.602409Z"},"links":{"cited_paper":"/paper/2402.11651","citing_paper":"/paper/2606.25605"},"observation_digest":"sha256:32bcb3a825f281e491d239387cc80cd2af47862c536dff9433f22a5d9af1998f","observation_id":"64847219-317c-41b7-be34-15ef0b0cf9db","resolution":{"observed_at":"2026-07-04T19:50:11.241838Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-05-20T22:23:34.654123+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-20T22:23:34.654123+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11651","last_updated":"2024-04-16T11:41:13Z","snapshot_observed_at":"2026-08-16T19:23:14.478746Z","submitted_at":"2024-02-18T17:10:07Z","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11651","snapshot_observed_at":"2026-08-16T00:33:33.490521Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11772","last_updated":"2026-08-12T08:14:45Z","snapshot_observed_at":"2026-08-17T13:29:36.867985Z","submitted_at":"2026-08-12T08:14:45Z","title":"Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-16T00:33:33.490521Z"},"links":{"cited_paper":"/paper/2402.11651","citing_paper":"/paper/2608.11772"},"observation_digest":"sha256:c2a161466baf955feae6ada42eaa3dda4ea490a316dbf547b989e624cd880d30","observation_id":"896cc7b9-c227-48b8-b059-40c9543f532e","resolution":{"observed_at":"2026-08-16T00:33:33.490521Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2402.11651/citation-record","integrity":"/paper/2402.11651/integrity","json":"/paper/2402.11651/citation-record.json","paper":"/paper/2402.11651"},"outbound":[],"paper":{"arxiv_id":"2402.11651","last_updated":"2024-04-16T11:41:13Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T19:23:14.478746Z","submitted_at":"2024-02-18T17:10:07Z","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as 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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 14 inbound Pith citation observations for arXiv:2402.11651."}