{"as_of":"2026-08-08T11:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f5f7e8e3c9c8bcd53ed4837947cace67c1b7ad71e9685e0b71f80a65a8821db2","coverage":[{"denominator":115,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:24:30.408981Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2505.21907/citation-record","integrity":"/paper/2505.21907/integrity","json":"/paper/2505.21907/citation-record.json","paper":"/paper/2505.21907"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:23.391722Z","title":"Ai-based digital assistants: Opportunities, threats, and research perspectives","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:23.391722Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:ab2e1ffb9764db8044f1ce85b1b2b90be5dbdd55c608ebf1d926240f5d4e389a","observation_id":"650e3488-6c9c-4c33-a2cf-3cf64dfed978","resolution":{"observed_at":"2026-08-07T13:24:23.391722Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.15595","last_updated":"2026-06-09T05:48:30Z","snapshot_observed_at":"2026-07-06T19:36:45.701678Z","submitted_at":"2024-10-21T02:27:24Z","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.15595","snapshot_observed_at":"2026-08-07T13:24:23.510307Z","title":"A comprehensive survey of direct preference optimization: Datasets, theories, variants, and applications","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:23.510307Z"},"links":{"cited_paper":"/paper/2410.15595","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:b30a82fbcf93bb9916ec2d54ea322b7dfc9395e9a9c1ad84a0734848a2237f5b","observation_id":"771e57d2-c34f-4158-9bea-d118b007f221","resolution":{"observed_at":"2026-08-07T13:24:23.510307Z","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":"2026-08-07T13:24:23.615165Z","title":"Survey on virtual assistant: Google assistant, siri, cortana, alexa","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:23.615165Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:f80d26704b3fb3c0ac9b4b452103aa58e12ddec2ac446a3c9c7a23fc800888ac","observation_id":"8bb595a9-92f7-4906-a4c2-69865ec12ad1","resolution":{"observed_at":"2026-08-07T13:24:23.615165Z","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":"2026-08-07T13:24:23.674271Z","title":"On the security and privacy challenges of virtual assistants","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:23.674271Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:570b4f6fbe1d6cf4e4859625e531c2ceb96094681899e0724e5940e5844d7f08","observation_id":"3ecd3377-4286-4cef-ad38-27844a591734","resolution":{"observed_at":"2026-08-07T13:24:23.674271Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.09512","last_updated":"2024-06-17T17:31:33Z","snapshot_observed_at":"2026-07-06T18:45:35.689341Z","submitted_at":"2024-06-17T17:31:33Z","title":"Design and evaluation of AI copilots -- case studies of retail copilot templates","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.09512","snapshot_observed_at":"2026-08-07T13:24:23.750477Z","title":"Design and evaluation of ai copilots–case studies of retail copilot templates","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:23.750477Z"},"links":{"cited_paper":"/paper/2407.09512","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:c529903e2f4a327f9c62a5a05df53f26472691c95a7223b261f18536ff1ca9a4","observation_id":"8c0cfe96-6706-49c2-9ae6-063206d2ae48","resolution":{"observed_at":"2026-08-07T13:24:23.750477Z","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":"2026-08-07T13:24:23.832957Z","title":"Computing, cognition and the future of knowing","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:23.832957Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:97724e6694aeb61bc4c9b47c5c7d068cbbe15a767ea85760311de412ddaa6885","observation_id":"dae83e59-2e27-41ed-8d2a-f15974d03daa","resolution":{"observed_at":"2026-08-07T13:24:23.832957Z","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":"2026-08-07T13:24:23.895109Z","title":"Foundations of augmented cognition","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:23.895109Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:6dd28546c0a5c801b276e0bc0c5eeb9d06af151d186e79fe39e0dad0bf3984ef","observation_id":"e8675f2d-3218-4e7c-bf99-d23fcda5fa41","resolution":{"observed_at":"2026-08-07T13:24:23.895109Z","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":"2026-08-07T13:24:23.994008Z","title":"Joint cognitive systems: Foundations of cognitive systems engineering","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:23.994008Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:402fc04ef288501f3b8efdc67e188d06667b4a24134ea0563f04db32e9256c22","observation_id":"d9b9f4dd-bb05-4762-8d04-52c0252835a6","resolution":{"observed_at":"2026-08-07T13:24:23.994008Z","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":"2026-08-07T13:24:24.068283Z","title":"Experi- mental evidence of effective human–ai collaboration in medical decision-making","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:24.068283Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:07dccb50319a255dd5dd58f8602269bdf984b1382bfd3cc5436527a6d4338f54","observation_id":"42c1341f-d33d-4841-9705-1aeab6ec1844","resolution":{"observed_at":"2026-08-07T13:24:24.068283Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.03354","last_updated":"2021-05-07T16:10:44Z","snapshot_observed_at":"2026-08-03T07:09:21.814269Z","submitted_at":"2021-05-07T16:10:44Z","title":"The future of human-AI collaboration: a taxonomy of design knowledge for hybrid intelligence systems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.03354","snapshot_observed_at":"2026-08-07T13:24:24.127159Z","title":"The future of human-ai collaboration: a taxonomy of design knowledge for hybrid intelligence systems","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:24.127159Z"},"links":{"cited_paper":"/paper/2105.03354","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:f6ac13cdfd1caca5c451f461d093c7f429f736fa6dac14789ecb3a0e9124d2eb","observation_id":"e1fd0ee2-1aae-4038-9601-3ebdaad2ee5c","resolution":{"observed_at":"2026-08-07T13:24:24.127159Z","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":"2026-08-07T13:24:24.200436Z","title":"Human–ai collaboration enables more empathic conversations in text-based peer-to-peer mental health support","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:24.200436Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:921b69bab5de6a70f92f7d9e17d296626e07270cbadd75d0828c45a4782c208d","observation_id":"679c3960-7e03-4080-9997-a1f86e272cf7","resolution":{"observed_at":"2026-08-07T13:24:24.200436Z","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":"2026-08-07T13:24:24.286188Z","title":"Anatomy of a digital assistant","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:24.286188Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:1da36844d76a5cfbb026c2341a1093dcfbd16d8b31b594491e3c6c7fff63e19c","observation_id":"ebf50964-0cfd-450b-9f55-21fabf95074e","resolution":{"observed_at":"2026-08-07T13:24:24.286188Z","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":"2026-08-07T13:24:24.366476Z","title":"Classifying smart personal assistants: An empirical cluster analysis","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:24.366476Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:55d518d886d56f56451d660d7c93dd17fbc09b444b6c6276c37fd6dffcc0f3a2","observation_id":"f2b52b73-af33-4f0d-af60-6d0f9d14a44d","resolution":{"observed_at":"2026-08-07T13:24:24.366476Z","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":"2026-08-07T13:24:24.434145Z","title":"what can i help you with?","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:24.434145Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:97a73141580e52dbce2d3cbe8420a23506486ccacb03ff5089ce86e330532941","observation_id":"cc67670f-285f-4ece-8e25-84d0c1e6f9d5","resolution":{"observed_at":"2026-08-07T13:24:24.434145Z","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":"2026-08-07T13:24:24.509605Z","title":"A literature survey of recent advances in chatbots","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:24.509605Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:8162472d8069e99b7165f3382ab77167ccbf4288cd9c0a966617a4a5a4c7d026","observation_id":"2f1f5cc7-f720-4f9f-bdea-bedffad2badb","resolution":{"observed_at":"2026-08-07T13:24:24.509605Z","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":"2026-08-07T13:24:24.586261Z","title":"A survey on privacy issues and solutions for voice-controlled digital assistants","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:24.586261Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:336444e49c70943a16930819ae02392d62269eb3bcb2f2e466e3fc005c321fc4","observation_id":"c1f9e320-9f0e-440d-b952-b464970cdf04","resolution":{"observed_at":"2026-08-07T13:24:24.586261Z","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":"2026-08-07T13:24:24.666037Z","title":"Manifestation of virtual assistants and robots into daily life: Vision and challenges","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:24.666037Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:6e552f080292affb422f8e71baf1d52af6a439258b7189630aa323f098fe1da8","observation_id":"9b6a6903-8546-4991-94ba-7967f0a42218","resolution":{"observed_at":"2026-08-07T13:24:24.666037Z","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":"2026-08-07T13:24:24.723648Z","title":"V oices in and of the machine: Source orientation toward mobile virtual assistants.Computers in Human Behavior, 90:343–350, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:24.723648Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:a63274aebdddfca852370d2c4c775d875c7dbb11e6eefedfa8484395ce753017","observation_id":"b0125c1f-66ab-4608-8222-6eb7c9f1a591","resolution":{"observed_at":"2026-08-07T13:24:24.723648Z","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":"2026-08-07T13:24:24.803193Z","title":"Survey on intelligent chatbots: State-of-the-art and future research directions","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:24.803193Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:68df177eae1a47424028267a1c31133f9c3402ce651cea3d5f21aec57605213a","observation_id":"ce850b77-73f1-45e8-983c-e45c4506f5c3","resolution":{"observed_at":"2026-08-07T13:24:24.803193Z","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":"2026-08-07T13:24:24.862609Z","title":"Review of state-of-the-art design techniques for chatbots","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:24.862609Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:01e6a865e0e3726247ef1d26ad8b2379f7f7f26d6e38dc83628ff3f5eca7ae70","observation_id":"3d42124d-4c5c-483e-a061-b92e9483de7e","resolution":{"observed_at":"2026-08-07T13:24:24.862609Z","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":"2026-08-07T13:24:24.932616Z","title":"A survey on conversational agents/chatbots classification and design techniques","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:24.932616Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:4a2b95457509a5e1195087afaa5cadc889ade43232b7e7e52f7cf56e91ff3730","observation_id":"5b2097f7-aaed-4443-8f2c-89c445a54112","resolution":{"observed_at":"2026-08-07T13:24:24.932616Z","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":"2026-08-07T13:24:24.996884Z","title":"Chatbots: History, technology, and applications","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:24.996884Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:1dffda30749e42cbc7e363db4d8128b348bf8c5cef5e7945360c368dbb107081","observation_id":"072d8db3-0ea3-4e4c-bb93-a5307b30c8ce","resolution":{"observed_at":"2026-08-07T13:24:24.996884Z","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":"2026-08-07T13:24:25.097788Z","title":"Improving the domain adaptation of retrieval augmented generation (rag) models for open domain question answering","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:25.097788Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:349c0c2e5ee157985642b8dcf02173244e7e96f2f0128cf1f8acf6e3a6da27f8","observation_id":"d1267a1d-5882-4731-a1d2-fc380a1af8d7","resolution":{"observed_at":"2026-08-07T13:24:25.097788Z","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":"2026-08-07T13:24:25.157026Z","title":"Medical expert systems survey","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:25.157026Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:df3b69382fb55c532b0650de1eb2d505fc0108c5162f81a28a99e8b26c5e7ef9","observation_id":"27d0ad2f-2527-40a7-912f-cbfe8ee55c61","resolution":{"observed_at":"2026-08-07T13:24:25.157026Z","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":"2026-08-07T13:24:25.224188Z","title":"Expert system methodologies and applications—a decade review from 1995 to 2004","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:25.224188Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:8c1a25a39be4d28bccffe3a527cbdbc1ec07753072587497472bf2ab5877e1ce","observation_id":"da59a662-3347-4750-b33d-4df63833c445","resolution":{"observed_at":"2026-08-07T13:24:25.224188Z","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":"2026-08-07T13:24:25.287459Z","title":"A survey on expert system in agriculture","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:25.287459Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:d3bdf4d25b321d982ed7cf6e18684697df82436cb0396cf7319d152f82cec668","observation_id":"c76b8a89-9b8e-4677-8ee1-fd8546f2749e","resolution":{"observed_at":"2026-08-07T13:24:25.287459Z","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":"2026-08-07T13:24:25.368910Z","title":"Expert systems: Principles and programming (fouth edition)","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:25.368910Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:9a314a21bf5c318858d349c4e6eebe0c0e912ef4aa7f4578738e05186ea9cd9f","observation_id":"d40b2237-3bd4-4531-b49d-370c8a76f7a0","resolution":{"observed_at":"2026-08-07T13:24:25.368910Z","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":"2026-08-07T13:24:25.452085Z","title":"A survey of belief rule-base expert system","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:25.452085Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:6db1107f16042fe97925986a8b28169d80311d5b79ab55a74b2c7aeeb9821b08","observation_id":"38d62533-dae2-4ec1-ae0f-d76965fd4d81","resolution":{"observed_at":"2026-08-07T13:24:25.452085Z","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":"2026-08-07T13:24:25.529538Z","title":"A multimodal generative ai copilot for human pathology","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:25.529538Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:49293a28e890ca1a7bff470e31b5ca6252c3d8d04cdd9a3160cabdd7f6a14d31","observation_id":"a38b1547-dc14-42d5-b5ef-67b580b2a785","resolution":{"observed_at":"2026-08-07T13:24:25.529538Z","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":"2026-08-07T13:24:25.608170Z","title":"When to show a suggestion? integrating human feedback in ai-assisted programming","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:25.608170Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:59e2316bffbfadd6e9a36786cd5b146f83ad05a77a8e85be91eaa6bb65067481","observation_id":"385ab786-03bb-4061-a636-001d230619a1","resolution":{"observed_at":"2026-08-07T13:24:25.608170Z","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":"2026-08-07T13:24:25.660988Z","title":"Human+ machine: Reimagining work in the age of AI","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:25.660988Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:fbda7806e7a92871279f28ac1b7090152d0b8d71cee72e0d3076e46bb72a3a6d","observation_id":"d31893e6-8b5d-4dbc-b34c-1bc43f2f8d07","resolution":{"observed_at":"2026-08-07T13:24:25.660988Z","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":"2026-08-07T13:24:25.743492Z","title":"The rise of the ai co-pilot: Lessons for design from aviation and beyond","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:25.743492Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:3300578e9594014b76da165aa29be202de1a0b0d3fe0eb5ca37270dd61827a71","observation_id":"a465ec60-b734-405d-b32e-7a4c1a02ab86","resolution":{"observed_at":"2026-08-07T13:24:25.743492Z","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":"2026-08-07T13:24:25.812528Z","title":"Angelopoulos, Tianle Li, Dacheng Li, Banghua Zhu, Hao Zhang, Michael I","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:25.812528Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:a2f06efe8c314c3bc5c2cfe208660e693dad8cb725bbf4ff2ab67771628015f9","observation_id":"ca7fe1fd-80ee-4763-936e-f4e242e5f838","resolution":{"observed_at":"2026-08-07T13:24:25.812528Z","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":"2026-08-07T13:24:25.905645Z","title":"Exploring the potential of generative ai for augmenting choice-based preference elicitation in recommender systems","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:25.905645Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:b95a326978ab76a7518c0931181b59c1570ae330b5ad6b98f46b3a03e302b60c","observation_id":"29b07bad-fa59-42f2-88f4-1229abb2c1d4","resolution":{"observed_at":"2026-08-07T13:24:25.905645Z","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":"2026-08-07T13:24:25.980371Z","title":"Explicit or implicit feedback? engagement or satisfaction? In Proceedings of the 12th ACM Conference on Recommender Systems (RecSys ’18), pages 24–32, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:25.980371Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:244786aaae383ca24109c66c37c1b6d7b2663db0afba88bf3c5507933b51b322","observation_id":"1549e675-7b23-40bc-b9bd-54793a1d6bdd","resolution":{"observed_at":"2026-08-07T13:24:25.980371Z","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":"2026-08-07T13:24:26.047725Z","title":"Automatic personalization based on web usage mining","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:26.047725Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:a546e0147792459fb11455d270f69bf85860e7d35ffe69bd1c984fbc65981582","observation_id":"2e793154-2a61-4fe5-84f2-3c101a2cdc0b","resolution":{"observed_at":"2026-08-07T13:24:26.047725Z","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":"2026-08-07T13:24:26.111805Z","title":"Exploring gaze-based prediction strategies for preference detection in videos","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:26.111805Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:eedeb686a19f93eb08c4769acbe1ca987267bcd20faed73e04c09e76e0602a19","observation_id":"295f517e-ebfa-4b72-a0b3-260a1252608b","resolution":{"observed_at":"2026-08-07T13:24:26.111805Z","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":"2026-08-07T13:24:26.181311Z","title":"Tucker, Kiante Brantley, Adam Cahall, and Thorsten Joachims","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:26.181311Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:92acc0393a666fbe86705f056f1a157208f3d2eb2fc35610b1323a1f6fade375","observation_id":"5e93b13a-0eb3-4743-9487-080b20d6f9f9","resolution":{"observed_at":"2026-08-07T13:24:26.181311Z","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":"2026-08-07T13:24:41.456283Z","title":"Rlhf from heterogeneous feedback via personalization and preference aggregation","venue":null,"work_id":"744872f2-4596-4e98-8fc6-f00286203585","year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:26.245575Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:fe6a076e04e6dd211c3d9b2755c18cc7595b4e95c39b116f0068fc86d88375a6","observation_id":"cfd671ff-4c66-4a6c-b9a0-41fbfb59661a","resolution":{"observed_at":"2026-08-07T13:24:41.558550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:41.275151Z","title":"What are you known for? learning user topical profiles with implicit and explicit footprints","venue":null,"work_id":"b2bc4f34-6759-44c3-b99a-314c666716b7","year":2017},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:26.315420Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:fa8edf406d16ec10d3aa14d519581c1afa1c007262808e7405ae7bd1c3bb282f","observation_id":"69cad9ad-4811-4887-9c8f-dbe93cbd388b","resolution":{"observed_at":"2026-08-07T13:24:41.371268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:41.130049Z","title":"Self-exploring language models: Active preference elicitation for online alignment","venue":null,"work_id":"b069bdd7-c170-4b2a-8fe7-f8fda1fc3b44","year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:26.346575Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:5a98b1ce7c5bebb682ef1d40c4a46a7548e6e720614abc7eff806155d0ff06d9","observation_id":"ebce5d12-d635-4566-a33a-251977548098","resolution":{"observed_at":"2026-08-07T13:24:41.176852Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:40.987102Z","title":"Bayesian optimization with llm-based acquisition functions for natural language preference elicitation","venue":null,"work_id":"7fd653b2-81b4-46b0-b1db-bf8dfaf47bc8","year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:26.386312Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:4efd1d83fd1ab9d33c827075459b9d66851d1406f18a6ea7ab59773ee80333de","observation_id":"bb470898-3583-4674-91ec-be8967da1333","resolution":{"observed_at":"2026-08-07T13:24:41.045495Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:40.834953Z","title":null,"venue":null,"work_id":"7afbacdc-d739-48de-ba07-a04855d49233","year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:26.431404Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:eb7fb07c86b254db7a990ed933a104e5c80f2364de57fef3df20d9a6fa4a915c","observation_id":"7f22f103-85b6-45c4-b0d0-bd2e75d60dc8","resolution":{"observed_at":"2026-08-07T13:24:40.901544Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:40.698337Z","title":"Active preference inference using language models and probabilistic reasoning","venue":null,"work_id":"88336870-a28d-489b-a0e3-29229ca1a959","year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:26.508880Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:6b760588e96788efafcda4064b32d2a5c2b19d56e72a34d4870042b21cee30fc","observation_id":"d710bcff-1e5b-4e10-a9ec-d36ab934afbb","resolution":{"observed_at":"2026-08-07T13:24:40.759586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:40.554200Z","title":"Evaluating large language models as generative user simulators for conversational recommendation","venue":null,"work_id":"d25c2744-f3fb-4ad0-b73c-8143e4800e26","year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:26.583689Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:6f3d95bb4d3e518690e9cfdf36cec36bee866d90dad2e8ea0f5e693b1cdd94ce","observation_id":"b52b63a3-837b-4c54-8754-76a53a7ffd94","resolution":{"observed_at":"2026-08-07T13:24:40.621154Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:40.391488Z","title":"Guided profile generation improves personalization with llms","venue":null,"work_id":"99753a3d-1576-4d85-b494-f72b2ed7bd04","year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:26.673283Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:047a9dd4371c587d09dc093e958f31c6657dd3d95f4d687b236f0f2c14c85de5","observation_id":"42be4766-c374-4584-bff1-9342e4eed042","resolution":{"observed_at":"2026-08-07T13:24:40.452385Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:40.263674Z","title":"Aligning language models with preferences through f-divergence minimization","venue":null,"work_id":"c93bdf30-8059-4f41-b183-e3ff6b6d54d9","year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:26.742733Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:f2a72f6c8fbfaf1452d556e3a99a9fc63721ae2fd2e69acc84e33714056cbfa9","observation_id":"48756eee-b77a-46d5-b38d-15b9fb31d05c","resolution":{"observed_at":"2026-08-07T13:24:40.314492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:40.113006Z","title":"Aligning llms with individual preferences via interaction","venue":null,"work_id":"e2ca1261-0acc-4676-ba67-a3552b89366d","year":2025},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:26.793548Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:6c440b7d6a5a0ff00c28eb9e6fb081f62a9ae7aeac45fa3959c37f9fc510eb85","observation_id":"76859dd5-d5be-412f-8716-e522ee9ba816","resolution":{"observed_at":"2026-08-07T13:24:40.186802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:39.983172Z","title":"Heimdall: A privacy-respecting implicit preference collection framework","venue":null,"work_id":"52a7b223-645a-4249-93eb-ca7b9fa6735d","year":2017},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:26.867281Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:240473720b58153492cd225ed3721aec7725abf760e506d245bf5101a6a1153e","observation_id":"23301ae8-1265-476c-9557-fdd34039c824","resolution":{"observed_at":"2026-08-07T13:24:40.034347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:39.838359Z","title":"Coached conversational preference elicitation: A case study in understanding movie preferences","venue":null,"work_id":"2876ed94-0f2f-4a62-83ea-856638fc16c3","year":2019},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:26.943533Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:6b4b3b992b8ebef8bd4dd2b65c0fad46bae9baceb5cb38fbb337ea2991594685","observation_id":"03f597ca-811f-4823-95f3-a462e52bea92","resolution":{"observed_at":"2026-08-07T13:24:39.910903Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:39.683709Z","title":"Do llms recognize your preferences? evaluating personalized preference following in llms","venue":null,"work_id":"f5864445-cecf-46b4-998f-fb3ff146e0e3","year":2025},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:26.993970Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:7925d3b9d6b6177c6345efab3bfffa5b7573be0835d30934dc1b77447f1e0625","observation_id":"9ac1c8c8-f77e-4a61-977e-2425a0731bc3","resolution":{"observed_at":"2026-08-07T13:24:39.753707Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:39.566549Z","title":"A survey of user profiling: State-of-the-art, challenges, and solutions","venue":null,"work_id":"888d2647-389c-49e0-8fec-58b3481b17b1","year":2019},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:27.066702Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:d9f53aedd6c8f051b68f7078951c20488be8e7f01c6d240e47018fe1b314e978","observation_id":"78f7e587-bd9b-468f-93cd-fda31e30e0cd","resolution":{"observed_at":"2026-08-07T13:24:39.623874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:39.366641Z","title":"User modeling and user profiling: A comprehensive survey","venue":null,"work_id":"ecae25e6-e5a9-41ce-b072-866eca2478ad","year":2022},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:27.132568Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:b8e528c7e230495efa6ebdc06245e1d8d46d639cd59c2d1616023a0798f5d090","observation_id":"25baeeac-6e32-4f28-8bbf-4a2c649e0b68","resolution":{"observed_at":"2026-08-07T13:24:39.455430Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:39.182208Z","title":"Preference learning with gaussian processes","venue":null,"work_id":"c67d8c04-b4ff-421e-be31-4906a49a9030","year":2005},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:27.199888Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:c1a907f5882ff48dae3dae3a60d6fc15256a085881d8b06cb0031cb0a3409e80","observation_id":"6aa63a57-f659-4a80-9006-425bf335e674","resolution":{"observed_at":"2026-08-07T13:24:39.251390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:38.976380Z","title":"User persona identification and new service adaptation recommendation","venue":null,"work_id":"5dc4bd2c-f901-4d94-b1b2-9e0dc5d9088f","year":2021},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:27.272076Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:e694e04d252f0c478a049837c724e1b6270abe63d065c6b7caaf92c2e913754f","observation_id":"cc81422e-aecf-4ea4-8b0b-0ad23327f4d3","resolution":{"observed_at":"2026-08-07T13:24:39.081847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:38.766615Z","title":"Collaborative filtering to capture ai user’s preferences as norms","venue":null,"work_id":"94fcfbf8-0dd4-477b-8253-ce686273ca00","year":2022},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:27.343636Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:27c6ebb3763befe97a40b6eeea054e4b57a0806bcb5b370c47d9ce5ebd02e96a","observation_id":"08f3735b-0d59-48a4-8539-ee45e1a855fe","resolution":{"observed_at":"2026-08-07T13:24:38.842810Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:38.577931Z","title":"A survey on accuracy-oriented neural recommendation: From collaborative filtering to information-rich recommendation","venue":null,"work_id":"2d09def5-f584-4e81-bebf-1cc96752917d","year":2021},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:27.416906Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:51aa8280e201e7484317e1c68fa31a708dd304650d4c1cef14ef520865cd3b76","observation_id":"3f11bc10-a138-441d-9fb2-bbf62e48b735","resolution":{"observed_at":"2026-08-07T13:24:38.670098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:38.333176Z","title":"Neural collaborative filtering for user preference discovery from biased implicit feedback","venue":null,"work_id":"f03229da-69b7-4ade-b159-1158abcf3a37","year":2017},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:27.490827Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:e00f5915f2e6d0c170a0c50b2fdac3633aba3d95ff8ef4dff719a744f257c8e3","observation_id":"80050039-83f4-4fb7-ad0f-59b80a38dd12","resolution":{"observed_at":"2026-08-07T13:24:38.439200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:38.178120Z","title":"Paed- zero-shot persona attribute extraction in dialogues","venue":null,"work_id":"b5d0a068-61c3-474c-8024-577509110cce","year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:27.547805Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:8b8f534ba457409ec65ee6a047ca7904ee5162d3941523927d69ce7ddbce2377","observation_id":"57633d0c-6673-4684-a6b7-deffd57d66f1","resolution":{"observed_at":"2026-08-07T13:24:38.238976Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:37.938418Z","title":"Enhancing emotional support conversations a framework for dynamic","venue":null,"work_id":"60d9c724-0aa1-4cfd-be57-7033291679d3","year":2025},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:27.631331Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:3442dd267481d80c9a77213f74920ca427d8c0871243dc15fac317954619652f","observation_id":"3d934f44-67af-41c3-b656-c66cb11d4cdb","resolution":{"observed_at":"2026-08-07T13:24:38.078235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:37.755739Z","title":"Towards personalized human-ai interaction: Adapting the behavior of ai agents using neural signatures of subjective interest","venue":null,"work_id":"25e06339-35ce-44c8-b467-081f2a9aa7dc","year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:27.796568Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:20ac61088b769d8e4cbba43abb18256c10a77f35d166b14a3a78204d5ecf757b","observation_id":"6b5bad74-3dca-4f20-9150-c87bb463404b","resolution":{"observed_at":"2026-08-07T13:24:37.819670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:37.578373Z","title":"Active preference learning for large language models","venue":null,"work_id":"da70e852-69c6-4194-b264-480834a25679","year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:27.867439Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:2c19e770cb2de6cee1f26a5d9c05e614d50393fd3c654b19ab9abe9bb1f79f99","observation_id":"d4cc112e-96ce-474d-b92b-c3b0ce0dabc9","resolution":{"observed_at":"2026-08-07T13:24:37.650865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:37.399254Z","title":"When to show a suggestion? integrating human feedback in ai-assisted programming","venue":null,"work_id":"daea16f4-ffce-4b01-a858-5b58f1d28eab","year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:27.967114Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:cf15c855f4b70c222a4e42ff8e96fa1f2bddbd10528c74c5766412e9157f67cb","observation_id":"6f2b79b3-38a9-47f5-aad3-6d9adb6414f8","resolution":{"observed_at":"2026-08-07T13:24:37.475371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:37.185839Z","title":"Afspp: An agent framework for shaping preference and personality with llms","venue":null,"work_id":"fafe8f17-7cb0-4e9b-be07-49023583b132","year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:28.051572Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:f3d7ec0682ee034a5b2f4f3e6022e317c06f4641ea2e1b38c1b92d5721f30a3b","observation_id":"8441b629-23a7-4aff-9126-39a51c4d9082","resolution":{"observed_at":"2026-08-07T13:24:37.288977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:37.025889Z","title":"Preferences in ai","venue":null,"work_id":"627a0a79-da83-4136-9a2f-87db29a95169","year":2020},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:28.127141Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:01b195758f4808fe0371e2124aaaf7a2fdca3c8dcc1c1dd27122d108a3362e76","observation_id":"12d7bf12-b491-4066-b97d-9b2ebab7b4e9","resolution":{"observed_at":"2026-08-07T13:24:37.104003Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.18847","last_updated":"2024-06-27T02:38:13Z","snapshot_observed_at":"2026-08-05T09:13:38.909193Z","submitted_at":"2024-06-27T02:38:13Z","title":"Learning Retrieval Augmentation for Personalized Dialogue Generation","version":1},"cited_work":{"arxiv_id":"2406.18847","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.18847","snapshot_observed_at":"2026-08-07T13:24:33.181487Z","title":"Learning Retrieval Augmentation for Personalized Dialogue Generation","venue":"cs.CL","work_id":"feec78d8-0481-43fd-9427-ee8d7a413845","year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:28.165163Z"},"links":{"cited_paper":"/paper/2406.18847","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:4c40731de854d3fb14b40f5c0ec471e21a352554e2a52f21cb9a3e728996188d","observation_id":"7bee41ed-0803-4160-b813-93ffd90a5b3b","resolution":{"observed_at":"2026-08-07T13:24:33.296148Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:28.260645Z","title":"Persobench: Benchmarking personalized response generation in large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:28.260645Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:1cee4445984dc013dbf6053c603bb7de22e6caefc89eea87aa9117963f80b0b5","observation_id":"2a35fff0-3b36-400d-baab-da659b931d4b","resolution":{"observed_at":"2026-08-07T13:24:28.260645Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17974","last_updated":"2024-05-28T09:04:13Z","snapshot_observed_at":"2026-08-05T04:24:25.545302Z","submitted_at":"2024-05-28T09:04:13Z","title":"Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17974","snapshot_observed_at":"2026-08-07T13:24:28.339748Z","title":"Recent trends in personalized dialogue generation: A review of datasets, methodologies, and evaluations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:28.339748Z"},"links":{"cited_paper":"/paper/2405.17974","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:a6bb8751925fcf3023c95ebc9ea9603da8aee9f8800ff838075621a5e7d8247a","observation_id":"88d99919-ac11-4bef-b803-fb14b9a99ff9","resolution":{"observed_at":"2026-08-07T13:24:28.339748Z","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":"2026-08-07T13:24:36.853530Z","title":"Cross-graph knowledge exchange for personalized response generation in dialogue systems","venue":null,"work_id":"b3ed6c58-9672-41c2-ad49-d9a5429571f8","year":2025},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:28.397054Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:9a3a60dcb84e95b9ff90cadbcf61e6bf17bda0aa7eb63e9d30c53a8878aa0a7b","observation_id":"641e948b-5502-478f-95ed-13d7f8a69207","resolution":{"observed_at":"2026-08-07T13:24:36.923544Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:36.626332Z","title":"Context aggregation with topic-focused summarization for personalized medical dialogue generation","venue":null,"work_id":"d5e79d63-9206-47c4-b7fe-6c57d3f74a1f","year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:28.443799Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:c60d59a321a8f2219de3432b73c7e3b20a148c61f15a950cfbfc5a28f1bc37b2","observation_id":"01582498-2d3c-41a3-87e3-8da252f3dd1b","resolution":{"observed_at":"2026-08-07T13:24:36.697544Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2004.05816","last_updated":"2020-10-06T08:20:22Z","snapshot_observed_at":"2026-08-06T09:35:40.000394Z","submitted_at":"2020-04-13T08:16:16Z","title":"Will I Sound Like Me? Improving Persona Consistency in Dialogues through Pragmatic Self-Consciousness","version":2},"cited_work":{"arxiv_id":"2004.05816","doi":null,"metadata_source":"pith","pith_arxiv_id":"2004.05816","snapshot_observed_at":"2026-08-07T13:24:32.818941Z","title":"Will I Sound Like Me? Improving Persona Consistency in Dialogues through Pragmatic Self-Consciousness","venue":"cs.CL","work_id":"8dc12fe9-1c58-4af6-983c-6b753507eb97","year":2020},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:28.515439Z"},"links":{"cited_paper":"/paper/2004.05816","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:e449d8e802278e3d2bdb1f4dcc996d92fb2802c6c2106cea385df611854dddd0","observation_id":"e82da79d-4fba-4933-ae1d-d7f0c954335d","resolution":{"observed_at":"2026-08-07T13:24:32.931496Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:36.407947Z","title":"Pk-icr: Persona-knowledge interactive multi-context retrieval for grounded dialogue","venue":null,"work_id":"38411f53-37df-4a39-9ae6-c0bc48553986","year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:28.590302Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:8a8dbbd97457b5e80f7304a699f0d1308eee11116cf66f0e3a7991126eb001f5","observation_id":"2d42b270-0cc3-4ee2-8e13-4ef95e937bcc","resolution":{"observed_at":"2026-08-07T13:24:36.519758Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.18187","last_updated":"2024-06-26T09:03:52Z","snapshot_observed_at":"2026-08-05T16:25:10.454744Z","submitted_at":"2024-06-26T09:03:52Z","title":"Selective Prompting Tuning for Personalized Conversations with LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.18187","snapshot_observed_at":"2026-08-07T13:24:28.648037Z","title":"Selective prompting tuning for personalized conversations with llms","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:28.648037Z"},"links":{"cited_paper":"/paper/2406.18187","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:10971bcf16926063142415b99cefff090ad036ecea793ec6e8b2cad7df1d957a","observation_id":"08e0c0bd-98c0-40a9-b159-83910448e981","resolution":{"observed_at":"2026-08-07T13:24:28.648037Z","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":"2026-08-07T13:24:36.237261Z","title":"Talk to your brain: Artificial personalized intelligence for emotionally adaptive ai interactions","venue":null,"work_id":"c540a832-1649-4d6c-a45f-2d9485f9a873","year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:28.733461Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:28386fee6a4192e3f44bb6f17e9d7fd8e4b3b8f6218ee1f01cd16586c35438c8","observation_id":"6bdb900e-be23-4cff-a405-77e66d5bf9e0","resolution":{"observed_at":"2026-08-07T13:24:36.317052Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:36.071657Z","title":"A cue adaptive decoder for controllable neural response generation","venue":null,"work_id":"11f70caf-ea80-4933-97a5-c733740228cf","year":2020},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:28.802073Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:f8145c0da7cbcc4dd4c5d8961f44480c4c9fdbf95558cd8271636a04a4dcc37e","observation_id":"edaf098e-b23e-470c-8faa-2b17e608d39f","resolution":{"observed_at":"2026-08-07T13:24:36.138404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.08149","last_updated":"2019-02-04T11:38:52Z","snapshot_observed_at":"2026-08-02T10:36:04.263316Z","submitted_at":"2019-01-23T22:08:01Z","title":"TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.08149","snapshot_observed_at":"2026-08-07T13:24:28.853597Z","title":"Transfertransfo: A transfer learning approach for neural network based conversational agents","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:28.853597Z"},"links":{"cited_paper":"/paper/1901.08149","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:d96bba6922a8017e466d0103b321619a5ac4747447cba4eb34ce826ee4679923","observation_id":"21a0ae83-797d-4d2e-9a9e-e3aebb7dd05b","resolution":{"observed_at":"2026-08-07T13:24:28.853597Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.09867","last_updated":"2022-04-21T03:49:54Z","snapshot_observed_at":"2026-07-06T13:02:17.457584Z","submitted_at":"2022-04-21T03:49:54Z","title":"A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation","version":1},"cited_work":{"arxiv_id":"2204.09867","doi":null,"metadata_source":"pith","pith_arxiv_id":"2204.09867","snapshot_observed_at":"2026-08-07T13:24:32.536367Z","title":"A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation","venue":"cs.CL","work_id":"19492601-5103-42b9-83e1-584e6c5a76df","year":2022},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:28.929463Z"},"links":{"cited_paper":"/paper/2204.09867","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:81a79ca72c15513c34975f5367542bd708907508614fcc7149dfe6c18a3e1152","observation_id":"b69a1478-daab-47de-a5a9-14af1886e408","resolution":{"observed_at":"2026-08-07T13:24:32.657218Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.08126","last_updated":"2023-06-13T20:47:29Z","snapshot_observed_at":"2026-07-06T15:42:18.360486Z","submitted_at":"2023-06-13T20:47:29Z","title":"PersonaPKT: Building Personalized Dialogue Agents via Parameter-efficient Knowledge Transfer","version":1},"cited_work":{"arxiv_id":"2306.08126","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.08126","snapshot_observed_at":"2026-08-07T13:24:32.355530Z","title":"PersonaPKT: Building Personalized Dialogue Agents via Parameter-efficient Knowledge Transfer","venue":"cs.CL","work_id":"aeb5dbb8-7d32-433d-9eae-52c9bb5f9319","year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.021137Z"},"links":{"cited_paper":"/paper/2306.08126","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:33f48d3574e73396acbdf41d94e70fda37dab4911107cb5db08253e551df5cf4","observation_id":"9a3e0829-3c3e-42fd-80dc-5e3229005efb","resolution":{"observed_at":"2026-08-07T13:24:32.438949Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:35.851949Z","title":"Beyond candidates: adaptive dialogue agent utilizing persona and knowledge","venue":null,"work_id":"4b2f5a36-eda6-45d0-8bf5-ac40154ab7db","year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.159371Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:8abcb3801a16dce73abac32fa13140f13d331f248d24f141213984c772256cef","observation_id":"c8ffa51a-c336-4206-99e3-6e47b21566f1","resolution":{"observed_at":"2026-08-07T13:24:35.983903Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07931","last_updated":"2020-04-30T16:06:37Z","snapshot_observed_at":"2026-07-06T08:30:18.977426Z","submitted_at":"2019-10-17T14:09:42Z","title":"PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.07931","snapshot_observed_at":"2026-08-07T13:24:29.267513Z","title":"Plato: Pre-trained dialogue generation model with discrete latent variable","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.267513Z"},"links":{"cited_paper":"/paper/1910.07931","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:3eaabb5ad0d3ed719287b7e61fed9cb51ecd64bc1eca4105b9c6a42a2834dccb","observation_id":"a0252f89-dd57-46da-b8cd-de8f61143cce","resolution":{"observed_at":"2026-08-07T13:24:29.267513Z","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":"2026-08-07T13:24:35.664986Z","title":"Personalized response generation via generative split memory network","venue":null,"work_id":"14a266ae-7e4d-4f19-83e1-543e24bf4aa9","year":2021},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.393956Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:729625c4bae08e255c51d6435a13b52229a368af85d9075a1fe616b480093b47","observation_id":"a93738a4-c3ba-4163-b8e6-de55cd591c64","resolution":{"observed_at":"2026-08-07T13:24:35.767300Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2004.12316","last_updated":"2020-11-19T11:00:23Z","snapshot_observed_at":"2026-07-06T09:15:15.738005Z","submitted_at":"2020-04-26T08:51:01Z","title":"Towards Persona-Based Empathetic Conversational Models","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.12316","snapshot_observed_at":"2026-08-07T13:24:29.497969Z","title":"Towards persona-based empathetic conversational models","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.497969Z"},"links":{"cited_paper":"/paper/2004.12316","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:be368a633437dfdf4cd72dcc4e4ab9d53913eb8a073251f1ae235b1f463acb46","observation_id":"8fab62ec-7545-427f-9d00-c2b165716d86","resolution":{"observed_at":"2026-08-07T13:24:29.497969Z","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":"2026-08-07T13:24:35.407454Z","title":"Learning to improve persona consistency in multi-party dialogue generation via text knowledge enhancement","venue":null,"work_id":"58b733a8-992e-42af-8982-a94176eba503","year":2022},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.551399Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:f1b63314803b969debff11d2cd724b80364d8340e754c662597d701a382929e3","observation_id":"cd781854-3cdb-40fd-a9bc-577a77f26058","resolution":{"observed_at":"2026-08-07T13:24:35.522931Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:35.201804Z","title":"Personalized dialogue generation with persona-adaptive attention","venue":null,"work_id":"9730c4a3-c4cf-4b3e-8c3e-372823acdb71","year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.636081Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:3794d88f5933099850b38d51ae8d69f78fa588262b5832549f2814fe77f01f87","observation_id":"33964d5a-ff70-4e1f-b5c2-c8d38dde34a1","resolution":{"observed_at":"2026-08-07T13:24:35.274147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:34.994698Z","title":"Persona-aware multi-party conversation response generation","venue":null,"work_id":"8137a11a-5866-455e-873d-a88d0b1aeca1","year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.698848Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:7cb3b4c4cfc04ee74eda8c21f632b8b6425a45946d031bc21e6a8de5940de36e","observation_id":"bd2b6b6e-f58d-4bde-86b2-e03a18bfb890","resolution":{"observed_at":"2026-08-07T13:24:35.092125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10471","last_updated":"2024-10-28T00:43:22Z","snapshot_observed_at":"2026-07-06T18:31:21.929350Z","submitted_at":"2024-06-15T02:26:18Z","title":"Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10471","snapshot_observed_at":"2026-08-07T13:24:29.738328Z","title":"Personalized pieces: Efficient personalized large language models through collaborative efforts","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.738328Z"},"links":{"cited_paper":"/paper/2406.10471","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:0e03c4225218facb0316c0d6453ac4c84b9a025a7b69f226d62385a4f1bd8814","observation_id":"6dc1ce23-e30d-4b35-8c77-833a5ecce85a","resolution":{"observed_at":"2026-08-07T13:24:29.738328Z","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":"2026-08-07T13:24:29.743517Z","title":"Training language models to follow instructions with human feedback","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.743517Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:2d3fc3eafaa5cec04330f89f7a71579a9241d6a3faf28899d1304d27e9423155","observation_id":"9d6c4ac6-b464-461b-9cf3-8bfb55266fa9","resolution":{"observed_at":"2026-08-07T13:24:29.743517Z","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":"2026-08-07T13:24:29.747785Z","title":"Direct preference optimization: Your language model is secretly a reward model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.747785Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:57131aaafba919b64b2ca4a66d09f01f7a11a7ca6ee771af3fa8756faf6ff026","observation_id":"365cac23-fd65-4f7b-92ac-7e913f471b9c","resolution":{"observed_at":"2026-08-07T13:24:29.747785Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.08593","last_updated":"2020-01-08T23:02:36Z","snapshot_observed_at":"2026-08-08T07:44:49.921146Z","submitted_at":"2019-09-18T17:33:39Z","title":"Fine-Tuning Language Models from Human Preferences","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.08593","snapshot_observed_at":"2026-08-07T13:24:29.752590Z","title":"Fine-tuning language models from human preferences","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.752590Z"},"links":{"cited_paper":"/paper/1909.08593","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:2e3ad3fcb9d3bbb4a84f062c5171547717f5ebbdaf06bb6a2c2bfe4312cc6135","observation_id":"2b48c89d-06c4-4169-a26a-2204eab6db34","resolution":{"observed_at":"2026-08-07T13:24:29.752590Z","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":"2026-08-07T13:24:29.761435Z","title":"Learning to summarize with human feedback","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.761435Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:67a97f89ac101509e7e2ffa63b86e8e14d04bb8c1021e3f0a5f81486ccb14052","observation_id":"660c9214-e1e5-4f5c-a64d-cf2c19dd1383","resolution":{"observed_at":"2026-08-07T13:24:29.761435Z","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":"2026-08-07T13:24:34.813025Z","title":"Fine-grained human feedback gives better rewards for language model training","venue":null,"work_id":"77ccea94-76e5-46e2-870d-eb4c2086d980","year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.810340Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:749e67ac803fa4707c10a048ba8c8171fc1d923ed7f54a4b79dd167b5ceb4e1c","observation_id":"1cc8a3b3-bfc9-4bce-b9ad-56cadf354ff5","resolution":{"observed_at":"2026-08-07T13:24:34.867143Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.19279","last_updated":"2024-03-28T10:02:10Z","snapshot_observed_at":"2026-07-06T17:52:26.380307Z","submitted_at":"2024-03-28T10:02:10Z","title":"Fine-Tuning Language Models with Reward Learning on Policy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.19279","snapshot_observed_at":"2026-08-07T13:24:29.885002Z","title":"Fine-tuning language models with reward learning on policy","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.885002Z"},"links":{"cited_paper":"/paper/2403.19279","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:00eec8f374ec884d5f591248ee02bfc55b60706a695199e6810b465fa6b081c0","observation_id":"f0950b69-1412-4337-8094-aad210ce9b44","resolution":{"observed_at":"2026-08-07T13:24:29.885002Z","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":"2026-08-07T13:24:29.933042Z","title":"Pretraining language models with human preferences","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.933042Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:393a079952e8a2932f87bd061b0470be1cd041d4e48b89bcd130b841ff44cb4e","observation_id":"7edda160-2dfc-4367-a029-edd0badfddbd","resolution":{"observed_at":"2026-08-07T13:24:29.933042Z","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":"2026-08-07T13:24:34.696583Z","title":"trlx: A framework for large scale reinforcement learning from human feedback","venue":null,"work_id":"bf19503e-f05c-41e8-8835-e2cc7b0dfd80","year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:29.993291Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:0bac6d5ca40ee290f5f89cbc772baa6e8dbf9a9a253ba85b80ecac835cf11b72","observation_id":"a2769944-a99f-44ea-93e0-1557a5aae3ed","resolution":{"observed_at":"2026-08-07T13:24:34.740613Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:24:30.066231Z","title":"Deep reinforcement learning from human preferences","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:30.066231Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:830d11a675a1023386513382f606494d2fa383666fdc0fbb4dcc45de38f6cbd6","observation_id":"0f396de3-948b-4652-8ee5-55ff1588566f","resolution":{"observed_at":"2026-08-07T13:24:30.066231Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.16635","last_updated":"2024-10-22T06:19:20Z","snapshot_observed_at":"2026-07-06T17:22:11.359057Z","submitted_at":"2024-01-30T00:17:37Z","title":"Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.16635","snapshot_observed_at":"2026-08-07T13:24:30.152840Z","title":"Improving reinforcement learning from human feedback with efficient reward model ensemble","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:30.152840Z"},"links":{"cited_paper":"/paper/2401.16635","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:88ae223209991add1a0c82cce9c74f50d8c8afc32bafa294f91303ef77537af9","observation_id":"bb59dc01-c5f7-4551-b9de-a78f7d70b003","resolution":{"observed_at":"2026-08-07T13:24:30.152840Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00782","last_updated":"2024-02-01T17:10:35Z","snapshot_observed_at":"2026-07-06T17:23:51.547578Z","submitted_at":"2024-02-01T17:10:35Z","title":"Dense Reward for Free in Reinforcement Learning from Human Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00782","snapshot_observed_at":"2026-08-07T13:24:30.201304Z","title":"Dense reward for free in reinforcement learning from human feedback","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:30.201304Z"},"links":{"cited_paper":"/paper/2402.00782","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:2b8e622d6e53e417b71c889dda5ee389b562400aae07e6d75a92e017d44e4abc","observation_id":"04b3437d-e8a2-4c38-90df-e92982a2163d","resolution":{"observed_at":"2026-08-07T13:24:30.201304Z","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":"2026-08-07T13:24:34.562310Z","title":"Adaptive preference scaling for reinforcement learning with human feedback","venue":null,"work_id":"5b89ed23-6c4b-4888-b0e9-08009dea8b49","year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:30.274736Z"},"links":{"citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:369c09c69d07b01f98f95386a944ce0f270ac89681f2e9bdecd03d843a065fec","observation_id":"377015c3-fe7f-40db-849b-341f6af6eb34","resolution":{"observed_at":"2026-08-07T13:24:34.606304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04373","last_updated":"2023-10-10T15:01:11Z","snapshot_observed_at":"2026-08-03T12:56:26.490744Z","submitted_at":"2023-10-06T16:59:17Z","title":"Confronting Reward Model Overoptimization with Constrained RLHF","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04373","snapshot_observed_at":"2026-08-07T13:24:30.335635Z","title":"Confronting reward model overoptimization with constrained rlhf","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:30.335635Z"},"links":{"cited_paper":"/paper/2310.04373","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:bb4c8dda14caaa3e84b92653eab74d976356cee4e92ed8dbe4695e64baeda1fe","observation_id":"b6b24e2f-2f2f-40e5-8d64-81a0dae43c40","resolution":{"observed_at":"2026-08-07T13:24:30.335635Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.19446","last_updated":"2024-02-29T18:45:56Z","snapshot_observed_at":"2026-08-07T22:12:46.006835Z","submitted_at":"2024-02-29T18:45:56Z","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.19446","snapshot_observed_at":"2026-08-07T13:24:30.408981Z","title":"Archer: Training language model agents via hierarchical multi-turn rl","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","version":2},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-08-07T13:24:30.408981Z"},"links":{"cited_paper":"/paper/2402.19446","citing_paper":"/paper/2505.21907"},"observation_digest":"sha256:d87d35bc041fd0a0833d069319c357a70fc2c792c69012a6383887027f9dc645","observation_id":"ac711189-9f6d-43d7-9184-727b8818fe3f","resolution":{"observed_at":"2026-08-07T13:24:30.408981Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.21907","last_updated":"2025-05-31T04:48:02Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-07T13:17:19.145607Z","submitted_at":"2025-05-28T02:52:39Z","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":57,"verified_exact":4,"verified_fuzzy":39},"total_outbound_references":115},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 100 of 115 outbound references and 0 inbound Pith citation observations for arXiv:2505.21907."}