{"as_of":"2026-08-23T08:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9220c9033dfe07204e748c307a0ec9167176e55d3a6a8f34b5d29084899c3778","coverage":[{"denominator":24,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":24,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T17:12:27.550904Z","state":"measured"},{"denominator":24,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":24,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2411.12828/citation-record","integrity":"/paper/2411.12828/integrity","json":"/paper/2411.12828/citation-record.json","paper":"/paper/2411.12828"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T17:12:27.441501Z","title":"online\" 'onlinestring :=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.441501Z"},"links":{"citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:fff446839d2848dee4e9942466cbd2c15ac8892c014fd4d310c597f0eeb0c5e4","observation_id":"75114879-3e1b-4b89-b7f7-eaa6cc6f5099","resolution":{"observed_at":"2026-08-12T17:12:27.441501Z","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":"2026-08-12T17:12:27.448492Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.448492Z"},"links":{"citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:d5b8b2173f85cc08a80757f79e40416cf8bc4f3922953722a5030bd3d408015f","observation_id":"73434c25-2d58-4c6c-a3de-de822d4a6fce","resolution":{"observed_at":"2026-08-12T17:12:27.448492Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.01547","last_updated":"2019-11-25T13:02:04Z","snapshot_observed_at":"2026-08-17T05:38:14.090895Z","submitted_at":"2019-11-05T00:31:38Z","title":"On the Measure of Intelligence","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.01547","snapshot_observed_at":"2026-08-12T17:12:27.456162Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.456162Z"},"links":{"cited_paper":"/paper/1911.01547","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:af3e7bbb1ab353ac6381b372b8e5623aae4c2d2a93ffd0c03a1ac5334cfe5272","observation_id":"620ae20c-b4ac-4889-8848-373f19591c09","resolution":{"observed_at":"2026-08-12T17:12:27.456162Z","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":"2026-08-14T05:50:17.249446Z","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":"2026-08-12T17:12:27.462350Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.462350Z"},"links":{"cited_paper":"/paper/2011.01060","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:4cd72ddc1c8ee5057b60741db38e636dd9bcb3b09198dadecd153f996349a3ca","observation_id":"b575b6ef-4675-4025-bea6-114e200c6a41","resolution":{"observed_at":"2026-08-12T17:12:27.462350Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03302","last_updated":"2024-04-14T21:02:16Z","snapshot_observed_at":"2026-08-17T14:56:37.479640Z","submitted_at":"2023-10-05T04:06:12Z","title":"MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03302","snapshot_observed_at":"2026-08-12T17:12:27.467241Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.467241Z"},"links":{"cited_paper":"/paper/2310.03302","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:fcc9b8ef43be1c0834a9a41ca36f7ac250dde4a3b6d9185dd3aee0a3f995100a","observation_id":"dd32d7fe-6786-494d-9a52-773dd83e9a5c","resolution":{"observed_at":"2026-08-12T17:12:27.467241Z","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":"2026-08-12T17:12:27.868087Z","title":null,"venue":null,"work_id":"1ca62564-d0d5-43cb-a46a-b432bce9272c","year":2024},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.475054Z"},"links":{"citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:e60016c6c589212dc64ab93e0ce0d0894a1780cdf6c98f6b9728834f3f43dead","observation_id":"bccaa92b-f338-4d66-93e9-632f02e32831","resolution":{"observed_at":"2026-08-12T17:12:27.873208Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11671","last_updated":"2024-01-04T18:46:39Z","snapshot_observed_at":"2026-08-18T17:57:47.508217Z","submitted_at":"2023-12-18T19:27:09Z","title":"Evaluating Language-Model Agents on Realistic Autonomous Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11671","snapshot_observed_at":"2026-08-12T17:12:27.480564Z","title":"Lin, Hjalmar Wijk, Joel Burget, Aaron Ho, Elizabeth Barnes, and Paul Christiano","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.480564Z"},"links":{"cited_paper":"/paper/2312.11671","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:8d27c5890776bf896b22180f82af6882f26e282eab14ae4d374ed97bee3e54e5","observation_id":"d7438d53-4b2c-46fa-870c-ac653dcaf1b3","resolution":{"observed_at":"2026-08-12T17:12:27.480564Z","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":"2026-08-12T17:12:27.485332Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.485332Z"},"links":{"citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:a893f3579ca6a29a44cc0a128e884705cd2c477bbb38a7aa352bafe6fa428cf0","observation_id":"0a56b226-388d-45cf-bcbd-59b0b9336549","resolution":{"observed_at":"2026-08-12T17:12:27.485332Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03688","last_updated":"2025-10-04T03:54:18Z","snapshot_observed_at":"2026-08-20T10:21:12.032735Z","submitted_at":"2023-08-07T16:08:11Z","title":"AgentBench: Evaluating LLMs as Agents","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03688","snapshot_observed_at":"2026-08-12T17:12:27.489930Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.489930Z"},"links":{"cited_paper":"/paper/2308.03688","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:0b82a7238b9f9d845d18a4afa7ab21659a7d6c68b21a64609b2ce1db3614cbce","observation_id":"9ba4cb79-1ea7-476d-9609-3b74bdbacfc0","resolution":{"observed_at":"2026-08-12T17:12:27.489930Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.12983","last_updated":"2023-11-21T20:34:47Z","snapshot_observed_at":"2026-08-13T10:06:26.439949Z","submitted_at":"2023-11-21T20:34:47Z","title":"GAIA: a benchmark for General AI Assistants","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.12983","snapshot_observed_at":"2026-08-12T17:12:27.495003Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.495003Z"},"links":{"cited_paper":"/paper/2311.12983","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:daaba51e849b59a9c6f138aada5b12f702b623c066785636929965475ef415b3","observation_id":"6b8ee843-340a-48f2-bb6f-cae1120dd06a","resolution":{"observed_at":"2026-08-12T17:12:27.495003Z","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":"2026-08-12T17:12:27.500025Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.500025Z"},"links":{"citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:e7908947a882cbde060a671fa38f1f1b194bcd1dbf63a6365a35098f96ce5e61","observation_id":"b73335bd-bd8d-49b6-b04a-8cc03d6a1e25","resolution":{"observed_at":"2026-08-12T17:12:27.500025Z","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":"2026-08-12T17:12:27.842341Z","title":null,"venue":null,"work_id":"a453db68-8ea5-400c-be89-2c904b9babe2","year":2023},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.504414Z"},"links":{"citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:a6efc066444e3d7315238a05d71651ac6f9212ab48038bcfa196736cc16da50a","observation_id":"3aa019c1-0eec-4857-b712-115005caf43a","resolution":{"observed_at":"2026-08-12T17:12:27.847999Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.19450","last_updated":"2024-02-29T18:48:18Z","snapshot_observed_at":"2026-08-22T00:15:31.436093Z","submitted_at":"2024-02-29T18:48:18Z","title":"Functional Benchmarks for Robust Evaluation of Reasoning Performance, and the Reasoning Gap","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.19450","snapshot_observed_at":"2026-08-12T17:12:27.508094Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.508094Z"},"links":{"cited_paper":"/paper/2402.19450","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:b24e21c0f70fb177a3501ece9c1dd690e4dd6ee659b874c7563f43e65e69e777","observation_id":"a27ad8a0-b62a-4074-bb5f-577f43b96f2f","resolution":{"observed_at":"2026-08-12T17:12:27.508094Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.12766","last_updated":"2025-04-23T12:52:18Z","snapshot_observed_at":"2026-08-18T08:27:14.551488Z","submitted_at":"2024-03-18T17:32:32Z","title":"NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.12766","snapshot_observed_at":"2026-08-12T17:12:27.512222Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.512222Z"},"links":{"cited_paper":"/paper/2403.12766","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:c87c6b308691b6b1d49256d57aa0627653ba06d3ac4235d91ce1795b7d33104f","observation_id":"935984f7-7696-4ea4-9199-afc23baa82aa","resolution":{"observed_at":"2026-08-12T17:12:27.512222Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.16291","last_updated":"2023-10-19T16:27:03Z","snapshot_observed_at":"2026-08-13T16:55:46.498156Z","submitted_at":"2023-05-25T17:46:38Z","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.16291","snapshot_observed_at":"2026-08-12T17:12:27.516108Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.516108Z"},"links":{"cited_paper":"/paper/2305.16291","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:ba36cc702ff1e51820be537f3b9e10b07bed8b63baa60b91a13186a17a804e2f","observation_id":"cc3a9381-3c80-4aa0-8251-de8aec5cf89f","resolution":{"observed_at":"2026-08-12T17:12:27.516108Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.08184","last_updated":"2024-06-12T13:14:50Z","snapshot_observed_at":"2026-08-16T13:43:45.903326Z","submitted_at":"2024-06-12T13:14:50Z","title":"MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.08184","snapshot_observed_at":"2026-08-12T17:12:27.519744Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.519744Z"},"links":{"cited_paper":"/paper/2406.08184","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:a15916956e0dfa441bdf601259974bf02c7fca3f1c50e7c2880bc346fe54dbd9","observation_id":"28e004a6-1049-4d22-86c9-00aa6c1e1683","resolution":{"observed_at":"2026-08-12T17:12:27.519744Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.07540","last_updated":"2022-11-14T17:52:27Z","snapshot_observed_at":"2026-08-22T04:51:34.197483Z","submitted_at":"2022-03-14T22:52:34Z","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.07540","snapshot_observed_at":"2026-08-12T17:12:27.523178Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.523178Z"},"links":{"cited_paper":"/paper/2203.07540","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:5dd85fa9f986ebc56a068f78e03eda25c5727f43839aff03801b43f502d9df01","observation_id":"1369f742-cd63-4b19-bc59-5ad9cf5bbf7c","resolution":{"observed_at":"2026-08-12T17:12:27.523178Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.11903","last_updated":"2023-01-10T23:07:57Z","snapshot_observed_at":"2026-08-13T07:04:41.220509Z","submitted_at":"2022-01-28T02:33:07Z","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.11903","snapshot_observed_at":"2026-08-12T17:12:27.527467Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.527467Z"},"links":{"cited_paper":"/paper/2201.11903","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:b59be3e6d99438fab682d50fd3805318fa1f69dadec838595583a83e26d4c223","observation_id":"85c4f3d1-6e8e-4392-8c47-c897e499d6fd","resolution":{"observed_at":"2026-08-12T17:12:27.527467Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01557","last_updated":"2024-03-17T23:23:31Z","snapshot_observed_at":"2026-08-20T13:34:08.656200Z","submitted_at":"2023-10-02T18:52:11Z","title":"SmartPlay: A Benchmark for LLMs as Intelligent Agents","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01557","snapshot_observed_at":"2026-08-12T17:12:27.531912Z","title":"Mitchell, and Yuanzhi Li","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.531912Z"},"links":{"cited_paper":"/paper/2310.01557","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:fa0bd30695bb588829a27ae36c870bbd0242e27097170280266cc5b07b95e7fb","observation_id":"9a1212a9-3faa-4bcb-bde0-a3a9a6fc2689","resolution":{"observed_at":"2026-08-12T17:12:27.531912Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.07864","last_updated":"2023-09-19T08:29:18Z","snapshot_observed_at":"2026-08-17T06:15:32.510873Z","submitted_at":"2023-09-14T17:12:03Z","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.07864","snapshot_observed_at":"2026-08-12T17:12:27.535964Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.535964Z"},"links":{"cited_paper":"/paper/2309.07864","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:19dac44fbd485a4fe4581791e1651b117fd238c2b38d44cdf203dc1214daa3cb","observation_id":"fd349079-c987-4354-ae06-32ed7d96a2a8","resolution":{"observed_at":"2026-08-12T17:12:27.535964Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16837","last_updated":"2025-05-31T11:20:49Z","snapshot_observed_at":"2026-08-17T19:25:01.286150Z","submitted_at":"2024-02-26T18:57:54Z","title":"Do Large Language Models Latently Perform Multi-Hop Reasoning?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16837","snapshot_observed_at":"2026-08-12T17:12:27.539468Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.539468Z"},"links":{"cited_paper":"/paper/2402.16837","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:d702cc3923f3a87cbee6041db8d90970f5c2a4c1f0cd1fe3bbb8ae50e7c64bb5","observation_id":"d22546ac-ecce-4062-ad32-11d7e5ab53b4","resolution":{"observed_at":"2026-08-12T17:12:27.539468Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.01206","last_updated":"2023-02-08T01:39:30Z","snapshot_observed_at":"2026-08-20T13:31:10.504015Z","submitted_at":"2022-07-04T05:30:22Z","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.01206","snapshot_observed_at":"2026-08-12T17:12:27.543427Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.543427Z"},"links":{"cited_paper":"/paper/2207.01206","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:c04955f01cd90ec5d8adbee5330f397567badff2646ddd648fca1a802c42c35d","observation_id":"94a06b83-d13f-4796-8956-11ec95cceb99","resolution":{"observed_at":"2026-08-12T17:12:27.543427Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.16054","last_updated":"2024-08-02T13:49:32Z","snapshot_observed_at":"2026-08-20T15:20:12.685260Z","submitted_at":"2024-04-12T15:39:09Z","title":"LlamaTouch: A Faithful and Scalable Testbed for Mobile UI Task Automation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.16054","snapshot_observed_at":"2026-08-12T17:12:27.547029Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.547029Z"},"links":{"cited_paper":"/paper/2404.16054","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:2c193b33a3de36a3ff96e76af17521143e7b3d38d0c35662ec2d6c1a169b44b5","observation_id":"e4165a0e-adfd-4a3e-8e87-4dd78ab8d0f2","resolution":{"observed_at":"2026-08-12T17:12:27.547029Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13854","last_updated":"2024-04-16T15:13:18Z","snapshot_observed_at":"2026-08-14T11:14:55.351653Z","submitted_at":"2023-07-25T22:59:32Z","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13854","snapshot_observed_at":"2026-08-12T17:12:27.550904Z","title":"Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, and Graham Neubig","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-12T17:12:27.550904Z"},"links":{"cited_paper":"/paper/2307.13854","citing_paper":"/paper/2411.12828"},"observation_digest":"sha256:5e78a5745fa35105f6e4b0a559f62e9f3eb5dded6bcd2ba7093aae65db5779b8","observation_id":"ec4f73e1-eef1-4e10-81a8-04a1d6061082","resolution":{"observed_at":"2026-08-12T17:12:27.550904Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.12828","last_updated":"2024-11-19T19:33:16Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-20T03:02:07.394136Z","submitted_at":"2024-11-19T19:33:16Z","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction"},"reference_resolution":{"displayed":24,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":24},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2411.12828."}