{"as_of":"2026-08-19T14:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7124a7ddc3ea56d36ca51a5d812c1de1831932f9b04cb1383904f83aa74b4f4f","coverage":[{"denominator":57,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":57,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T17:56:38.919605Z","state":"measured"},{"denominator":66,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":66,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":9,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":9,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T04:19:09.835936Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-10T12:15:01.137692Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.10397","snapshot_observed_at":"2026-08-02T23:50:09.201764Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.12612","last_updated":"2026-07-09T06:11:51Z","snapshot_observed_at":"2026-08-14T07:02:21.110120Z","submitted_at":"2026-02-13T04:38:32Z","title":"Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T23:50:09.201764Z"},"links":{"cited_paper":"/paper/2509.10397","citing_paper":"/paper/2602.12612"},"observation_digest":"sha256:cc17393abefb98b651ed93d6c5082604db18022e58e28db7a0a459fe416fe953","observation_id":"d64bdfd7-71d4-49ee-9cc5-7888418ffd02","resolution":{"observed_at":"2026-08-02T23:50:09.201764Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"cited_work":{"arxiv_id":"2509.10397","doi":"10.48550/arxiv.2509.10397","metadata_source":"arxiv_reference","pith_arxiv_id":"2509.10397","snapshot_observed_at":"2026-07-28T02:22:23.314678Z","title":"Recoworld: Building simulated environments for agentic recommender systems","venue":null,"work_id":"7cccb845-4121-4179-8cf6-9a3f82033894","year":2025},"citing_paper":{"arxiv_id":"2604.10029","last_updated":"2026-04-18T04:20:33Z","snapshot_observed_at":"2026-08-16T13:44:15.209284Z","submitted_at":"2026-04-11T04:52:38Z","title":"Self-Distilled Reinforcement Learning for Co-Evolving Agentic Recommender Systems","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-10T16:24:28.048403Z"},"links":{"cited_paper":"/paper/2509.10397","citing_paper":"/paper/2604.10029"},"observation_digest":"sha256:a5d86b3110bf6468e94d955e430736d01e230587e3e45e2f4d1dc7de83bd8d33","observation_id":"9a9f5a69-edd7-4e7b-86e0-fae84021fd1f","resolution":{"observed_at":"2026-07-28T02:22:23.314678Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"cited_work":{"arxiv_id":"2509.10397","doi":"10.48550/arxiv.2509.10397","metadata_source":"arxiv_reference","pith_arxiv_id":"2509.10397","snapshot_observed_at":"2026-07-28T02:22:23.314678Z","title":"Recoworld: Building simulated environments for agentic recommender systems","venue":null,"work_id":"7cccb845-4121-4179-8cf6-9a3f82033894","year":2025},"citing_paper":{"arxiv_id":"2605.11874","last_updated":"2026-05-12T09:52:21Z","snapshot_observed_at":"2026-08-13T03:38:04.870787Z","submitted_at":"2026-05-12T09:52:21Z","title":"RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systems","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-13T05:04:08.454422Z"},"links":{"cited_paper":"/paper/2509.10397","citing_paper":"/paper/2605.11874"},"observation_digest":"sha256:5e4e3fa941bfd7964303263057e05fc7f49e3748c0feb3a5d36a291370fd6c27","observation_id":"eafc0c8d-bd0a-46af-8647-087b75d51c3c","resolution":{"observed_at":"2026-07-28T02:22:23.314678Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"cited_work":{"arxiv_id":"2509.10397","doi":"10.48550/arxiv.2509.10397","metadata_source":"arxiv_reference","pith_arxiv_id":"2509.10397","snapshot_observed_at":"2026-07-28T02:22:23.314678Z","title":"Recoworld: Building simulated environments for agentic recommender systems","venue":null,"work_id":"7cccb845-4121-4179-8cf6-9a3f82033894","year":2025},"citing_paper":{"arxiv_id":"2606.28368","last_updated":"2026-06-15T08:36:01Z","snapshot_observed_at":"2026-08-15T16:14:33.890139Z","submitted_at":"2026-06-15T08:36:01Z","title":"EvoRec: Self Evolving Agentic Recommender Systems","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-30T10:47:52.156114Z"},"links":{"cited_paper":"/paper/2509.10397","citing_paper":"/paper/2606.28368"},"observation_digest":"sha256:39a457dbd185ca60b8d1f68467b2d597de0b97077154922f664dc60ee0de26d9","observation_id":"1f428721-7b79-4685-942d-dce8e42b662c","resolution":{"observed_at":"2026-07-28T02:22:23.314678Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.10397","snapshot_observed_at":"2026-08-02T07:33:12.781312Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.09988","last_updated":"2026-07-22T17:27:17Z","snapshot_observed_at":"2026-08-16T06:58:05.670170Z","submitted_at":"2026-07-10T21:28:43Z","title":"An LLM-powered Agentic Recommendation System for Connected TV Content Discovery","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T07:33:12.781312Z"},"links":{"cited_paper":"/paper/2509.10397","citing_paper":"/paper/2607.09988"},"observation_digest":"sha256:f5a7e4b439f1a38dc8212c0ad3005ea812ea0f445f42f78746622f648c008190","observation_id":"09ef33a6-34d0-4db6-8fe0-05fdd4da5b9d","resolution":{"observed_at":"2026-08-02T07:33:12.781312Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.10397","snapshot_observed_at":"2026-08-02T05:17:58.278553Z","title":"arXiv preprint arXiv:2509.10397 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.13418","last_updated":"2026-07-16T00:42:41Z","snapshot_observed_at":"2026-08-17T00:01:39.153856Z","submitted_at":"2026-07-15T03:37:06Z","title":"Can We Steer the Black-Box? Towards Controllability-Centric Evaluation of Recommender Systems with Collaborative Agents","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-02T05:17:58.278553Z"},"links":{"cited_paper":"/paper/2509.10397","citing_paper":"/paper/2607.13418"},"observation_digest":"sha256:553ab5893b5dea08adae76996430116704aacff428a5f68f089ac6c83eb42b6e","observation_id":"36a65cd8-8fc0-4601-93c2-c3b852aa3d8b","resolution":{"observed_at":"2026-08-02T05:17:58.278553Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.10397","snapshot_observed_at":"2026-07-30T17:56:01.447706Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26893","last_updated":"2026-07-29T13:25:30Z","snapshot_observed_at":"2026-08-18T17:58:20.969028Z","submitted_at":"2026-07-29T13:25:30Z","title":"Beyond Action Imitation: Learning a Decision-Aware User Simulator for Online Advertising","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-30T17:56:01.447706Z"},"links":{"cited_paper":"/paper/2509.10397","citing_paper":"/paper/2607.26893"},"observation_digest":"sha256:3b79bc3186a5ee18d83db08e2be602366d285becc924993d03b7d53926881d4d","observation_id":"2c60d52a-4fa0-41d0-a551-f92f257c6821","resolution":{"observed_at":"2026-07-30T17:56:01.447706Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.10397","snapshot_observed_at":"2026-08-11T17:48:55.162617Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.09408","last_updated":"2026-08-13T13:55:36Z","snapshot_observed_at":"2026-08-16T23:12:16.266208Z","submitted_at":"2026-08-10T10:35:32Z","title":"DREAM Technical Report","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-11T17:48:55.162617Z"},"links":{"cited_paper":"/paper/2509.10397","citing_paper":"/paper/2608.09408"},"observation_digest":"sha256:d8532fe852cf2714abdaf8b8863fa6745b50585e994e39e888433920b9a8d6b2","observation_id":"0bb470be-77f2-4552-a08d-e05fd3b7bdde","resolution":{"observed_at":"2026-08-11T17:48:55.162617Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.10397","snapshot_observed_at":"2026-08-14T04:19:09.835936Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.09408","last_updated":"2026-08-13T13:55:36Z","snapshot_observed_at":"2026-08-16T23:12:16.266208Z","submitted_at":"2026-08-10T10:35:32Z","title":"DREAM Technical Report","version":3},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-14T04:19:09.835936Z"},"links":{"cited_paper":"/paper/2509.10397","citing_paper":"/paper/2608.09408"},"observation_digest":"sha256:2652064501f12d6e4b500abf3d81d5aa775f659962f4119a98e6f186074df9ba","observation_id":"71f2dfbf-7274-404a-9f7a-367a480cba92","resolution":{"observed_at":"2026-08-14T04:19:09.835936Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2509.10397/citation-record","integrity":"/paper/2509.10397/integrity","json":"/paper/2509.10397/citation-record.json","paper":"/paper/2509.10397"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T17:56:38.714395Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.714395Z"},"links":{"citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:5112e6bb10fb33a19c7bcd89d79cb7916f518ab1f423c7cac25b58843ce90867","observation_id":"41e5b18c-859f-4499-9614-c48e46ee7a4f","resolution":{"observed_at":"2026-08-04T17:56:38.714395Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.02234","last_updated":"2025-06-05T15:12:55Z","snapshot_observed_at":"2026-08-16T12:44:24.688160Z","submitted_at":"2025-04-03T03:01:26Z","title":"LLM Social Simulations Are a Promising Research Method","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.02234","snapshot_observed_at":"2026-08-04T17:56:38.720457Z","title":"Richardson, Austin C","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.720457Z"},"links":{"cited_paper":"/paper/2504.02234","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:11d9be0722ca370836eaa35456b4669f5c2c6f9bafb296e6f79047379dc20e61","observation_id":"5ce0c9d7-bab4-4be6-83ce-337050d42f36","resolution":{"observed_at":"2026-08-04T17:56:38.720457Z","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":"2026-08-04T17:56:38.724887Z","title":"System card: Claude opus 4 & claude sonnet 4","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.724887Z"},"links":{"citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:ce4c3c92f6215cfd47a4aad8e4b018fab882def7ffc666ef03751548ddb2ba5c","observation_id":"ec869160-4ff5-48c7-975a-a6d08106738d","resolution":{"observed_at":"2026-08-04T17:56:38.724887Z","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":"2026-08-04T17:56:38.728967Z","title":"Eckstein, Noémi Éltető, Thomas L","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.728967Z"},"links":{"citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:76a9d1b02444f044e86f1e1456129a3dc6452ef25d3b60036c7f0dd1abf78191","observation_id":"028c3d6f-ad9b-44bb-a4ad-d287ac62086a","resolution":{"observed_at":"2026-08-04T17:56:38.728967Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.01540","last_updated":"2016-06-05T17:54:48Z","snapshot_observed_at":"2026-08-13T12:26:05.192883Z","submitted_at":"2016-06-05T17:54:48Z","title":"OpenAI Gym","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.01540","snapshot_observed_at":"2026-08-04T17:56:38.732588Z","title":"Openai gym, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.732588Z"},"links":{"cited_paper":"/paper/1606.01540","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:d0dde2bded594963f77c02eaf24015419ca4a196596915a5aa81495fd7c974ae","observation_id":"e6216943-1f4e-465c-9dfd-db4969e94594","resolution":{"observed_at":"2026-08-04T17:56:38.732588Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21787","last_updated":"2024-12-30T19:03:24Z","snapshot_observed_at":"2026-08-14T10:00:52.343929Z","submitted_at":"2024-07-31T17:57:25Z","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21787","snapshot_observed_at":"2026-08-04T17:56:38.736352Z","title":"Le, Christopher Ré, and Azalia Mirhoseini","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.736352Z"},"links":{"cited_paper":"/paper/2407.21787","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:26fdfc74b1707f12314da2b2cb4c4f745ff427d9ebbaecdb633ea4d2dc553f66","observation_id":"18e072a6-6f41-4819-aade-cff4ad1bc3c3","resolution":{"observed_at":"2026-08-04T17:56:38.736352Z","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":"2026-08-04T17:56:38.740220Z","title":"Agentic feedback loop modeling improves recommendation and user simulation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.740220Z"},"links":{"citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:101a3fd358924d9d35f4d2e3417dfe52883417c7b10d79676d689b69834e8121","observation_id":"832adcd3-2ffc-4142-aa7d-be623c3b0667","resolution":{"observed_at":"2026-08-04T17:56:38.740220Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.10568","last_updated":"2024-11-10T21:31:43Z","snapshot_observed_at":"2026-08-19T00:05:29.205468Z","submitted_at":"2024-09-14T04:17:24Z","title":"On the limits of agency in agent-based models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.10568","snapshot_observed_at":"2026-08-04T17:56:38.744028Z","title":"On the limits of agency in agent-based models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.744028Z"},"links":{"cited_paper":"/paper/2409.10568","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:ed18abe72bc545e151baa4bd6de6d40f6bb168c80c5e2c9361838cdda8f751e0","observation_id":"b0d20d46-0c5e-46b8-8ef2-1226b8b5aee9","resolution":{"observed_at":"2026-08-04T17:56:38.744028Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.01631","last_updated":"2024-08-20T13:56:21Z","snapshot_observed_at":"2026-08-16T13:47:10.602886Z","submitted_at":"2024-06-01T11:56:08Z","title":"SUBER: An RL Environment with Simulated Human Behavior for Recommender Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.01631","snapshot_observed_at":"2026-08-04T17:56:38.748325Z","title":"Lanzendörfer, Flint Xiaofeng Fan, and Roger Wattenhofer","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.748325Z"},"links":{"cited_paper":"/paper/2406.01631","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:bc32ec6139fbd34d66b3f2c974c07b4400a0a6748a9e8d701d96007c5a8f3609","observation_id":"3c21a5e4-d22b-46b2-b116-6b8cbddca4e6","resolution":{"observed_at":"2026-08-04T17:56:38.748325Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.16586","last_updated":"2024-04-08T06:40:47Z","snapshot_observed_at":"2026-08-16T14:39:45.023134Z","submitted_at":"2023-11-28T08:03:56Z","title":"SARDINE: A Simulator for Automated Recommendation in Dynamic and Interactive Environments","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.16586","snapshot_observed_at":"2026-08-04T17:56:38.752198Z","title":"Sardine: A simulator for automated recommendation in dynamic and interactive environments, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.752198Z"},"links":{"cited_paper":"/paper/2311.16586","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:0e9de5b93e888db428e84ef362e0b38b36475aba85e5f150f7efe9960efc14b3","observation_id":"85d30d4e-6fb3-4c6e-93c3-2fde31873d95","resolution":{"observed_at":"2026-08-04T17:56:38.752198Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.18965","last_updated":"2025-02-26T09:25:10Z","snapshot_observed_at":"2026-08-11T02:18:35.186995Z","submitted_at":"2025-02-26T09:25:10Z","title":"OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.18965","snapshot_observed_at":"2026-08-04T17:56:38.759620Z","title":"Onerec: Unifying retrieve and rank with generative recommender and iterative preference alignment, 2025 b","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.759620Z"},"links":{"cited_paper":"/paper/2502.18965","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:ef312378753986c2c7e100767979a1d75e4e6599747bc67e4b180da1e8463d51","observation_id":"abd22998-0c17-4001-9048-3d62071fe2a6","resolution":{"observed_at":"2026-08-04T17:56:38.759620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14387","last_updated":"2024-01-08T04:46:56Z","snapshot_observed_at":"2026-08-16T17:34:14.000776Z","submitted_at":"2023-05-22T17:55:50Z","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14387","snapshot_observed_at":"2026-08-04T17:56:38.763239Z","title":"Hashimoto","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.763239Z"},"links":{"cited_paper":"/paper/2305.14387","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:fef573e407924955fe5d13f35db5d20cecba51e3dc1980c0d83dca1031493575","observation_id":"c0e8ab4e-2af1-4680-84be-b13782bead09","resolution":{"observed_at":"2026-08-04T17:56:38.763239Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.19352","last_updated":"2025-01-01T00:03:24Z","snapshot_observed_at":"2026-08-15T20:46:10.185149Z","submitted_at":"2024-11-28T19:53:39Z","title":"OMuleT: Orchestrating Multiple Tools for Practicable Conversational Recommendation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.19352","snapshot_observed_at":"2026-08-04T17:56:38.766930Z","title":"Omulet: Orchestrating multiple tools for practicable conversational recommendation, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.766930Z"},"links":{"cited_paper":"/paper/2411.19352","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:17d418f5aec389438edfb21232e1bdb9a80b87384aab32b545aba137d5757935","observation_id":"d77549a3-c3cb-486c-80f4-6a83dadad1d3","resolution":{"observed_at":"2026-08-04T17:56:38.766930Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.23810","last_updated":"2024-10-31T10:52:42Z","snapshot_observed_at":"2026-08-18T17:20:31.674539Z","submitted_at":"2024-10-31T10:52:42Z","title":"CALE: Continuous Arcade Learning Environment","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.23810","snapshot_observed_at":"2026-08-04T17:56:38.770438Z","title":"Cale: Continuous arcade learning environment, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.770438Z"},"links":{"cited_paper":"/paper/2410.23810","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:ea7265cb186a22df4f5126566401a29ea63bf56f57ef08461d01939b3635227f","observation_id":"d9093b5e-c172-4cae-ba6a-64071c07cd36","resolution":{"observed_at":"2026-08-04T17:56:38.770438Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.14034","last_updated":"2024-05-20T04:01:08Z","snapshot_observed_at":"2026-08-16T14:16:44.366665Z","submitted_at":"2024-02-21T04:11:28Z","title":"AgentScope: A Flexible yet Robust Multi-Agent Platform","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.14034","snapshot_observed_at":"2026-08-04T17:56:38.773649Z","title":"Agentscope: A flexible yet robust multi-agent platform, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.773649Z"},"links":{"cited_paper":"/paper/2402.14034","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:712c2e2ab75b1c757386aa23a358a2d41a50871233f0741b3afb9ab3b186b9e6","observation_id":"1f4e182a-98a9-4998-b4db-363acfd2cc40","resolution":{"observed_at":"2026-08-04T17:56:38.773649Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.19627","last_updated":"2025-01-24T20:49:16Z","snapshot_observed_at":"2026-08-18T01:30:57.895085Z","submitted_at":"2024-10-25T15:25:36Z","title":"Knowledge Graph Enhanced Language Agents for Recommendation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.19627","snapshot_observed_at":"2026-08-04T17:56:38.777051Z","title":"Knowledge graph enhanced language agents for recommendation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.777051Z"},"links":{"cited_paper":"/paper/2410.19627","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:e2e6ff03519cd1b73d5635d3da32f3c68ac9a6422f23c4b1b59ca9877d63affb","observation_id":"9ac2e555-99b9-48a4-bf7b-25c460bd37f4","resolution":{"observed_at":"2026-08-04T17:56:38.777051Z","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":"2026-08-04T17:56:38.780494Z","title":"Llm-augmented agent-based modelling for social simulations: Challenges and opportunities","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.780494Z"},"links":{"citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:68703503a7c9ffe87d4f24662e9e146886e4f82db710ab224b0334fadb40bde3","observation_id":"107b6f8a-9200-4b46-9cf0-edb2004694c9","resolution":{"observed_at":"2026-08-04T17:56:38.780494Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13581","last_updated":"2025-08-15T23:44:20Z","snapshot_observed_at":"2026-08-16T12:57:02.899353Z","submitted_at":"2025-02-19T09:45:29Z","title":"ActionPiece: Contextually Tokenizing Action Sequences for Generative Recommendation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13581","snapshot_observed_at":"2026-08-04T17:56:38.783564Z","title":"Chi, Julian McAuley, and Derek Zhiyuan Cheng","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.783564Z"},"links":{"cited_paper":"/paper/2502.13581","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:ac4cbcbb1597d6cb4261e08393b8d60734d2005f34b69676d9ed6150524db805","observation_id":"acd86507-3359-4240-8d11-f0e158779aad","resolution":{"observed_at":"2026-08-04T17:56:38.783564Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.16734","last_updated":"2025-03-20T22:37:15Z","snapshot_observed_at":"2026-08-18T14:42:56.195825Z","submitted_at":"2025-03-20T22:37:15Z","title":"Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.16734","snapshot_observed_at":"2026-08-04T17:56:38.786978Z","title":"Rossi, Branislav Kveton, Dongruo Zhou, Julian McAuley, and Lina Yao","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.786978Z"},"links":{"cited_paper":"/paper/2503.16734","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:413dc431ccd91fec0c9cb0a733aa12b9285cb622cfdfb8e5a650ccf043df03a5","observation_id":"4c82896c-10b4-47a0-918e-0b4aafa55f7a","resolution":{"observed_at":"2026-08-04T17:56:38.786978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.18878","last_updated":"2025-05-24T21:33:22Z","snapshot_observed_at":"2026-08-18T11:08:09.086702Z","submitted_at":"2025-05-24T21:33:22Z","title":"CRMArena-Pro: Holistic Assessment of LLM Agents Across Diverse Business Scenarios and Interactions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.18878","snapshot_observed_at":"2026-08-04T17:56:38.790240Z","title":"Crmarena-pro: Holistic assessment of llm agents across diverse business scenarios and interactions, 2025 b","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.790240Z"},"links":{"cited_paper":"/paper/2505.18878","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:f23a85063c466773546577bb2bdce32a4364843be7f32ca9af2a64e0863d1532","observation_id":"41590be3-4235-4ddc-b351-610025672d99","resolution":{"observed_at":"2026-08-04T17:56:38.790240Z","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":"2026-08-04T17:56:38.793787Z","title":"Agentsbench: A multi-agent llm simulation framework for legal judgment prediction","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.793787Z"},"links":{"citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:3b5cb0e512e583fd0399ca473a8a4ac77674f7ef94bee0154f2466ace106e3a0","observation_id":"09a4db6e-fb59-4a71-8189-175b796e5a9f","resolution":{"observed_at":"2026-08-04T17:56:38.793787Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.20534","last_updated":"2026-02-03T04:57:00Z","snapshot_observed_at":"2026-08-16T14:37:33.548231Z","submitted_at":"2025-07-28T05:35:43Z","title":"Kimi K2: Open Agentic Intelligence","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.20534","snapshot_observed_at":"2026-08-04T17:56:38.796921Z","title":"Kimi k2: Open agentic intelligence, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.796921Z"},"links":{"cited_paper":"/paper/2507.20534","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:2a443cea7eab90d8da5e5c3b558be5022d65e54d4f621e3935ec224c560c66c5","observation_id":"70e9e99f-fef6-402f-b3b8-1b713850d414","resolution":{"observed_at":"2026-08-04T17:56:38.796921Z","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":"2026-08-04T17:56:38.800260Z","title":"Can llm-simulated practice and feedback upskill human counselors? a randomized study with 90+ novice counselors, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.800260Z"},"links":{"citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:f471a4764e6266719a71431371ab49989ddc0f81ab762fa1edd4bee4c3529749","observation_id":"79c7ee53-4695-4235-8540-497473ac87f3","resolution":{"observed_at":"2026-08-04T17:56:38.800260Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.02097","last_updated":"2026-06-28T08:31:01Z","snapshot_observed_at":"2026-08-18T09:12:52.974169Z","submitted_at":"2025-07-02T19:25:44Z","title":"The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.02097","snapshot_observed_at":"2026-08-04T17:56:38.803451Z","title":"The future is agentic: Definitions, perspectives, and open challenges of multi-agent recommender systems, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.803451Z"},"links":{"cited_paper":"/paper/2507.02097","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:ff5351cc326f5a3d51c8d70ef940a7a7ccb65840a76b65dd0e77fd1113206604","observation_id":"20228abf-98ca-42ae-8248-8f79328b2d13","resolution":{"observed_at":"2026-08-04T17:56:38.803451Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.03442","last_updated":"2023-08-06T00:21:19Z","snapshot_observed_at":"2026-08-16T03:49:04.888755Z","submitted_at":"2023-04-07T01:55:19Z","title":"Generative Agents: Interactive Simulacra of Human Behavior","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.03442","snapshot_observed_at":"2026-08-04T17:56:38.808543Z","title":"O'Brien, Carrie J","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.808543Z"},"links":{"cited_paper":"/paper/2304.03442","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:c16f3c0cafd1753677c6fef334e7b04882e9c59075ca0a8204256ca84fd1aa65","observation_id":"b39d9097-bfe0-4763-abf4-7bb40b93cd6f","resolution":{"observed_at":"2026-08-04T17:56:38.808543Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.10109","last_updated":"2026-06-28T22:37:51Z","snapshot_observed_at":"2026-08-13T12:33:17.230204Z","submitted_at":"2024-11-15T11:14:34Z","title":"LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.10109","snapshot_observed_at":"2026-08-04T17:56:38.812230Z","title":"Zou, Aaron Shaw, Benjamin Mako Hill, Carrie Cai, Meredith Ringel Morris, Robb Willer, Percy Liang, and Michael S","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.812230Z"},"links":{"cited_paper":"/paper/2411.10109","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:c5930152063cfa304b5a974875e7c9cf3d1c5e763472fd6c55f26032d11e7f77","observation_id":"bc7a3820-052f-44af-b875-a0b54554c74c","resolution":{"observed_at":"2026-08-04T17:56:38.812230Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.10050","last_updated":"2025-02-14T09:57:07Z","snapshot_observed_at":"2026-08-13T09:33:32.797621Z","submitted_at":"2025-02-14T09:57:07Z","title":"A Survey on LLM-powered Agents for Recommender Systems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.10050","snapshot_observed_at":"2026-08-04T17:56:38.815778Z","title":"A survey on llm-powered agents for recommender systems","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.815778Z"},"links":{"cited_paper":"/paper/2502.10050","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:01393a74228096e818d681cdd50f5eb3ee8120bb5fa3e823cf4cc79661ac08d9","observation_id":"765234c3-9591-4ba7-8972-a15803c00f83","resolution":{"observed_at":"2026-08-04T17:56:38.815778Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.08691","last_updated":"2026-04-10T15:11:22Z","snapshot_observed_at":"2026-08-16T11:37:43.086955Z","submitted_at":"2025-02-12T15:27:07Z","title":"AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.08691","snapshot_observed_at":"2026-08-04T17:56:38.819306Z","title":"Agentsociety: Large-scale simulation of llm-driven generative agents advances understanding of human behaviors and society, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.819306Z"},"links":{"cited_paper":"/paper/2502.08691","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:85906c0fcce81787dd876059642d634fbe51dd348c6e2260e8737516f642c8fa","observation_id":"cbf84c8d-c5c2-4260-8599-7f01cab271e6","resolution":{"observed_at":"2026-08-04T17:56:38.819306Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.07199","last_updated":"2024-08-13T20:52:13Z","snapshot_observed_at":"2026-08-14T15:46:52.927758Z","submitted_at":"2024-08-13T20:52:13Z","title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.07199","snapshot_observed_at":"2026-08-04T17:56:38.822670Z","title":"Agent q: Advanced reasoning and learning for autonomous ai agents, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.822670Z"},"links":{"cited_paper":"/paper/2408.07199","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:d0eb55b5a7994ec2b7997efe3f35f13750770bc5c053e9eab8c1fa7085d660d5","observation_id":"8fe9928b-6f33-4c1f-a128-fc62ccbc2e4e","resolution":{"observed_at":"2026-08-04T17:56:38.822670Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22034","last_updated":"2025-07-29T17:34:12Z","snapshot_observed_at":"2026-08-16T14:47:27.605319Z","submitted_at":"2025-07-29T17:34:12Z","title":"UserBench: An Interactive Gym Environment for User-Centric Agents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.22034","snapshot_observed_at":"2026-08-04T17:56:38.825906Z","title":"Userbench: An interactive gym environment for user-centric agents, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.825906Z"},"links":{"cited_paper":"/paper/2507.22034","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:73935598aa570d4ef48346de89684363cd44510dd3870553915633126047c539","observation_id":"4a16f3bc-1b29-4107-ba9f-bc553867fd04","resolution":{"observed_at":"2026-08-04T17:56:38.825906Z","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":"2026-08-04T17:56:38.829360Z","title":"Recommender systems with generative retrieval","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.829360Z"},"links":{"citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:dd928343eac654a5ebef7f0a05cb8277b15717e60767666daf7cb259fc447dac","observation_id":"40bf49d1-0e25-47d4-ab11-9ee6dfba2373","resolution":{"observed_at":"2026-08-04T17:56:38.829360Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.19623","last_updated":"2025-05-28T14:32:56Z","snapshot_observed_at":"2026-08-15T18:07:04.344086Z","submitted_at":"2025-05-26T07:45:11Z","title":"AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.19623","snapshot_observed_at":"2026-08-04T17:56:38.832953Z","title":"Agentrecbench: Benchmarking llm agent-based personalized recommender systems, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.832953Z"},"links":{"cited_paper":"/paper/2505.19623","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:1a63d540328d4f808cb02e3f6b893637705adf3fa82377fb3f7904528ba4d7fc","observation_id":"6ef27738-b07a-4b3b-a5f3-252b7439d904","resolution":{"observed_at":"2026-08-04T17:56:38.832953Z","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":"2026-08-04T17:56:38.836788Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.836788Z"},"links":{"citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:7a9a2507c8baea47f5b6a0c16d56130763ecd8a9b038dbe8242c7f9c6abf6ed7","observation_id":"3494a903-4211-4929-b54b-accfd9230ef7","resolution":{"observed_at":"2026-08-04T17:56:38.836788Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.16363","last_updated":"2024-06-07T18:06:20Z","snapshot_observed_at":"2026-08-16T13:49:25.034729Z","submitted_at":"2024-05-25T21:57:36Z","title":"LLMs for User Interest Exploration in Large-scale Recommendation Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.16363","snapshot_observed_at":"2026-08-04T17:56:38.840146Z","title":"Llms for user interest exploration in large-scale recommendation systems, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.840146Z"},"links":{"cited_paper":"/paper/2405.16363","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:77183dde579146bb29fb73f178ec1796d1d01f96c7df1f8999e80c85c87a2411","observation_id":"929fa3ea-b86c-4f7b-9400-11cf3c4da75d","resolution":{"observed_at":"2026-08-04T17:56:38.840146Z","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":"2026-08-04T17:56:38.843739Z","title":"User behavior simulation with large language model-based agents","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.843739Z"},"links":{"citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:dc15bfcedbf677f785cd511b1c4856df6e8a650eed4261c21c9c973fe60eee30","observation_id":"bfb02ea9-ec2c-433a-bb9e-6bb27a2e3e60","resolution":{"observed_at":"2026-08-04T17:56:38.843739Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.16114","last_updated":"2026-06-01T12:57:38Z","snapshot_observed_at":"2026-08-14T21:58:21.135858Z","submitted_at":"2025-06-19T08:04:31Z","title":"GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.16114","snapshot_observed_at":"2026-08-04T17:56:38.847284Z","title":"Gflowgr: Fine-tuning generative recommendation frameworks with generative flow networks, 2025 b","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.847284Z"},"links":{"cited_paper":"/paper/2506.16114","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:12590b3947fc08a6e9338d4b0d5c406f09e174eb2a856187f2af3bba46cbedda","observation_id":"ccd35ba6-f608-4a5f-b384-c4d9cc7cbca7","resolution":{"observed_at":"2026-08-04T17:56:38.847284Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.19505","last_updated":"2025-05-26T04:32:57Z","snapshot_observed_at":"2026-08-19T01:23:40.785552Z","submitted_at":"2025-05-26T04:32:57Z","title":"Hierarchical Tree Search-based User Lifelong Behavior Modeling on Large Language Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.19505","snapshot_observed_at":"2026-08-04T17:56:38.851380Z","title":"Hierarchical tree search-based user lifelong behavior modeling on large language model, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.851380Z"},"links":{"cited_paper":"/paper/2505.19505","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:32144ccbe230a1c47a33569f43f0de90c9cd2f58c3134fe56a27e7b96aa4e6ed","observation_id":"0087880a-3b05-49fb-91d2-25e295cf41aa","resolution":{"observed_at":"2026-08-04T17:56:38.851380Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.14161","last_updated":"2025-09-10T08:35:19Z","snapshot_observed_at":"2026-08-16T19:31:08.289292Z","submitted_at":"2024-12-18T18:55:40Z","title":"TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.14161","snapshot_observed_at":"2026-08-04T17:56:38.854829Z","title":"Xu, Yufan Song, Boxuan Li, Yuxuan Tang, Kritanjali Jain, Mengxue Bao, Zora Z","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.854829Z"},"links":{"cited_paper":"/paper/2412.14161","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:aec3106a592bddb7f4b76a6bb3794c72f66578d6d68ef911cddd195a7d6d835c","observation_id":"1108fcae-4f2c-43ca-bdfd-6b1fa52d62af","resolution":{"observed_at":"2026-08-04T17:56:38.854829Z","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":"2026-08-04T17:56:38.858334Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.858334Z"},"links":{"citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:2c14fb1f24a3a66c03e68d7cfd94181beec34520a8a3207d44c344782c47454c","observation_id":"e9b6c979-c9b9-4b84-8ed6-006c694933ff","resolution":{"observed_at":"2026-08-04T17:56:38.858334Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.14662","last_updated":"2025-05-29T23:51:24Z","snapshot_observed_at":"2026-08-16T12:56:38.200544Z","submitted_at":"2025-02-20T15:58:25Z","title":"iAgent: LLM Agent as a Shield between User and Recommender Systems","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.14662","snapshot_observed_at":"2026-08-04T17:56:38.861709Z","title":"iagent: Llm agent as a shield between user and recommender systems, 2025 c","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.861709Z"},"links":{"cited_paper":"/paper/2502.14662","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:61e2435ab303faf8eda137631e2ca8b9b61e8eaa0aa20878a6e085e422eb89ab","observation_id":"7f42eb2d-bdc9-4a29-84e0-33982710a516","resolution":{"observed_at":"2026-08-04T17:56:38.861709Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.11581","last_updated":"2025-03-23T13:00:03Z","snapshot_observed_at":"2026-08-15T09:45:58.120182Z","submitted_at":"2024-11-18T13:57:35Z","title":"OASIS: Open Agent Social Interaction Simulations with One Million Agents","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.11581","snapshot_observed_at":"2026-08-04T17:56:38.865797Z","title":"Oasis: Open agent social interaction simulations with one million agents, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.865797Z"},"links":{"cited_paper":"/paper/2411.11581","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:6d3919c77e875ce24ca48661a1afafe9244deaff98d0202cb0763a4405eb75d6","observation_id":"a79e587b-1923-4470-8548-c0b15fd1c5d5","resolution":{"observed_at":"2026-08-04T17:56:38.865797Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.09738","last_updated":"2024-03-25T23:53:01Z","snapshot_observed_at":"2026-08-16T22:48:40.522509Z","submitted_at":"2024-03-13T18:16:21Z","title":"Evaluating Large Language Models as Generative User Simulators for Conversational Recommendation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.09738","snapshot_observed_at":"2026-08-04T17:56:38.869320Z","title":"Evaluating large language models as generative user simulators for conversational recommendation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.869320Z"},"links":{"cited_paper":"/paper/2403.09738","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:c32b89a4c2f1d1ab7d981da16f1740978e9c9c9ff91a0a41c58f8783e77f7eaf","observation_id":"7db04a51-54ee-4542-8586-b1491b43e33c","resolution":{"observed_at":"2026-08-04T17:56:38.869320Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.08844","last_updated":"2025-02-12T23:30:01Z","snapshot_observed_at":"2026-08-18T10:37:12.291554Z","submitted_at":"2025-02-12T23:30:01Z","title":"MuJoCo Playground","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.08844","snapshot_observed_at":"2026-08-04T17:56:38.873029Z","title":"Kahrs, Carmelo Sferrazza, Yuval Tassa, and Pieter Abbeel","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.873029Z"},"links":{"cited_paper":"/paper/2502.08844","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:04be5bfe3d5367ea4f46031e4dd16a27e0ed4d1be0d55d6bdf395bc59558343b","observation_id":"6f27ce27-967c-4cec-812d-5bf4fb298b3c","resolution":{"observed_at":"2026-08-04T17:56:38.873029Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17152","last_updated":"2024-05-06T02:05:45Z","snapshot_observed_at":"2026-08-16T20:04:50.187441Z","submitted_at":"2024-02-27T02:37:37Z","title":"Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17152","snapshot_observed_at":"2026-08-04T17:56:38.876673Z","title":"Actions speak louder than words: Trillion-parameter sequential transducers for generative recommendations, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.876673Z"},"links":{"cited_paper":"/paper/2402.17152","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:b82bec73f50c776a5e8c0969c91c5b70b94115b917b2a7f7cfcc16832aa905c2","observation_id":"b5423a38-1973-4d52-85b0-cf2ad75515fd","resolution":{"observed_at":"2026-08-04T17:56:38.876673Z","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":"2026-08-04T17:56:38.880309Z","title":"On generative agents in recommendation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.880309Z"},"links":{"citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:52f02fea2e30e5432ebc1c132c1f11eb12923ca3fb2c44742cf0069451e5e426","observation_id":"099054f9-b3a1-446d-b251-478d3f265f61","resolution":{"observed_at":"2026-08-04T17:56:38.880309Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.16789","last_updated":"2025-01-21T15:40:43Z","snapshot_observed_at":"2026-08-16T13:49:13.072319Z","submitted_at":"2024-05-27T03:24:01Z","title":"NoteLLM-2: Multimodal Large Representation Models for Recommendation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.16789","snapshot_observed_at":"2026-08-04T17:56:38.883489Z","title":"Notellm-2: Multimodal large representation models for recommendation, 2025 a","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.883489Z"},"links":{"cited_paper":"/paper/2405.16789","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:4d75fb265771a5f04f96367a1726bb1e173a0c169319584bc0f6dfb4c3cbb2d8","observation_id":"d178cd06-1b4f-47b8-ae98-056e1c839718","resolution":{"observed_at":"2026-08-04T17:56:38.883489Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.07001","last_updated":"2023-05-11T17:39:07Z","snapshot_observed_at":"2026-08-18T13:49:25.029978Z","submitted_at":"2023-05-11T17:39:07Z","title":"Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.07001","snapshot_observed_at":"2026-08-04T17:56:38.886734Z","title":"Recommendation as instruction following: A large language model empowered recommendation approach, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.886734Z"},"links":{"cited_paper":"/paper/2305.07001","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:93dfc26b775fb3b7033e00501ab769f470af6a16f16fe7aeca00b2d2162a1b90","observation_id":"59d8d5d6-696d-41c2-ab98-12bd05ce3d7c","resolution":{"observed_at":"2026-08-04T17:56:38.886734Z","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":"2026-08-04T17:56:38.889847Z","title":"Agentcf: Collaborative learning with autonomous language agents for recommender systems","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.889847Z"},"links":{"citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:6d0ea2eabdf8db5d1d90af39be4bbf4e10d7f14ee3e323fba9fa6d21a4035e81","observation_id":"a2a9ccc2-89f1-425e-9077-d79aa5dc6716","resolution":{"observed_at":"2026-08-04T17:56:38.889847Z","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":"2026-08-04T17:56:38.893248Z","title":"Llm-powered user simulator for recommender system","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.893248Z"},"links":{"citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:fe94a5fcedf6ae02704b53e16d77bb7f14d05c2ce2dd6faea61dab6e498e5994","observation_id":"03086443-ac4d-4b32-a3c7-32b2167d0109","resolution":{"observed_at":"2026-08-04T17:56:38.893248Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.12645","last_updated":"2023-10-19T07:36:03Z","snapshot_observed_at":"2026-08-16T14:58:32.924800Z","submitted_at":"2023-09-22T06:29:29Z","title":"KuaiSim: A Comprehensive Simulator for Recommender Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.12645","snapshot_observed_at":"2026-08-04T17:56:38.896525Z","title":"Kuaisim: A comprehensive simulator for recommender systems, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.896525Z"},"links":{"cited_paper":"/paper/2309.12645","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:33adcc5fcee8432502214fb9e7321498ae2acf8e242c7dddebd9f4d2b4d51947","observation_id":"008e4e85-6235-4d54-8ccd-e72756be83f6","resolution":{"observed_at":"2026-08-04T17:56:38.896525Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.12313","last_updated":"2025-04-09T13:21:17Z","snapshot_observed_at":"2026-08-16T12:42:41.776188Z","submitted_at":"2025-04-09T13:21:17Z","title":"Exploring the Impact of Personality Traits on Conversational Recommender Systems: A Simulation with Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.12313","snapshot_observed_at":"2026-08-04T17:56:38.899610Z","title":"Exploring the impact of personality traits on conversational recommender systems: A simulation with large language models, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.899610Z"},"links":{"cited_paper":"/paper/2504.12313","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:2bddf0ad02c7c46b9320ef544dd1a2bd45c106317a2aef798358484713f18d12","observation_id":"1805f64e-c7b6-4674-834f-6eef2cbd270e","resolution":{"observed_at":"2026-08-04T17:56:38.899610Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.02137","last_updated":"2025-04-02T21:28:38Z","snapshot_observed_at":"2026-08-16T12:44:27.584603Z","submitted_at":"2025-04-02T21:28:38Z","title":"Enhancing Embedding Representation Stability in Recommendation Systems with Semantic ID","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.02137","snapshot_observed_at":"2026-08-04T17:56:38.902921Z","title":"Enhancing embedding representation stability in recommendation systems with semantic id","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.902921Z"},"links":{"cited_paper":"/paper/2504.02137","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:9410dd9f6d2d07fb41ec36f7faf8dce984cc1c672823bac2eae3bdc944fb1c10","observation_id":"79f86155-eebc-4bbc-ac2e-cf31c179a4af","resolution":{"observed_at":"2026-08-04T17:56:38.902921Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.20900","last_updated":"2025-10-28T09:32:28Z","snapshot_observed_at":"2026-08-16T16:15:56.566906Z","submitted_at":"2025-08-28T15:29:51Z","title":"OneRec-V2 Technical Report","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.20900","snapshot_observed_at":"2026-08-04T17:56:38.906062Z","title":"Onerec-v2 technical report, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.906062Z"},"links":{"cited_paper":"/paper/2508.20900","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:f1b485ab02f6a5ce11401fb08c1e88b84df16b0c0838d0cb704f8be119b96529","observation_id":"bef1c4fc-6065-48dc-81f2-b4f93d86c033","resolution":{"observed_at":"2026-08-04T17:56:38.906062Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07911","last_updated":"2023-11-14T05:13:55Z","snapshot_observed_at":"2026-07-06T16:47:08.877195Z","submitted_at":"2023-11-14T05:13:55Z","title":"Instruction-Following Evaluation for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07911","snapshot_observed_at":"2026-08-04T17:56:38.909292Z","title":"Instruction-following evaluation for large language models, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.909292Z"},"links":{"cited_paper":"/paper/2311.07911","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:72a9f8ce30c518e3e96ee6c27d83a398cf1ca60978f5df6a85d68ce02b069b86","observation_id":"81513001-0bab-491f-aa95-a2ded35727c5","resolution":{"observed_at":"2026-08-04T17:56:38.909292Z","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":"2026-08-04T17:56:38.912400Z","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":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.912400Z"},"links":{"cited_paper":"/paper/2307.13854","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:7b2893eab9d7076b0c1032f766ec6c9fe74b8541021fca7b8801bc3d8188536f","observation_id":"bb897b6c-2834-4557-93e8-d8131a859e6b","resolution":{"observed_at":"2026-08-04T17:56:38.912400Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.15817","last_updated":"2025-01-27T06:52:50Z","snapshot_observed_at":"2026-08-15T22:40:47.416704Z","submitted_at":"2025-01-27T06:52:50Z","title":"Long-Term Interest Clock: Fine-Grained Time Perception in Streaming Recommendation System","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.15817","snapshot_observed_at":"2026-08-04T17:56:38.915923Z","title":"Long-term interest clock: Fine-grained time perception in streaming recommendation system, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.915923Z"},"links":{"cited_paper":"/paper/2501.15817","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:076ff3599f0fb6b2dcc64ff9c15574f8ffe3b9d702570bec72722d612edc4d58","observation_id":"fd9ad2b0-8f20-4f81-994f-f40c1ced21dd","resolution":{"observed_at":"2026-08-04T17:56:38.915923Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21439","last_updated":"2025-05-27T17:14:37Z","snapshot_observed_at":"2026-08-13T06:20:52.491989Z","submitted_at":"2025-05-27T17:14:37Z","title":"Towards Better Instruction Following Retrieval Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.21439","snapshot_observed_at":"2026-08-04T17:56:38.919605Z","title":"Towards better instruction following retrieval models, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","version":3},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-04T17:56:38.919605Z"},"links":{"cited_paper":"/paper/2505.21439","citing_paper":"/paper/2509.10397"},"observation_digest":"sha256:8cf637d2e5b57c5475512c74444938e3454016e0dde3f7adf81055a6cc77c2fa","observation_id":"b158857f-e5e2-4877-a85e-d9ff66377f7f","resolution":{"observed_at":"2026-08-04T17:56:38.919605Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.10397","last_updated":"2026-07-25T20:09:07Z","latest_version":3,"primary_category":"cs.IR","snapshot_observed_at":"2026-08-19T04:49:00.708675Z","submitted_at":"2025-09-12T16:44:34Z","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems"},"reference_resolution":{"displayed":57,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":57,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":57},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 9 inbound Pith citation observations for arXiv:2509.10397."}