{"as_of":"2026-08-18T14:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:616b4e0cd6b62858a1022148c2e1009817470921b6e0af9ae9445c9e1b09a51d","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":16,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":16,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":16,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":16,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T12:04:12.226516Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-09T22:16:36.509652Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.13598","last_updated":"2024-09-09T19:51:57Z","snapshot_observed_at":"2026-08-16T14:16:41.619195Z","submitted_at":"2024-02-21T08:03:27Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13598","snapshot_observed_at":"2026-08-12T21:54:44.306981Z","title":"User-llm: Efficient llm cont extualization with user embeddings,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.08181","last_updated":"2024-12-04T16:55:18Z","snapshot_observed_at":"2026-08-14T11:20:53.014041Z","submitted_at":"2024-11-12T20:57:12Z","title":"Challenges in Guardrailing Large Language Models for Science","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-12T21:54:44.306981Z"},"links":{"cited_paper":"/paper/2402.13598","citing_paper":"/paper/2411.08181"},"observation_digest":"sha256:3e9f20d3f071af237593cc62f2e5aaee08d544e29a346a6c898ea15e6f7b7f62","observation_id":"a6951630-52e7-4216-9bf8-9d2766ee1527","resolution":{"observed_at":"2026-08-12T21:54:44.306981Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13598","last_updated":"2024-09-09T19:51:57Z","snapshot_observed_at":"2026-08-16T14:16:41.619195Z","submitted_at":"2024-02-21T08:03:27Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13598","snapshot_observed_at":"2026-08-11T19:52:59.758710Z","title":"User-llm: Efficient llm contextualization with user embedding,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.06308","last_updated":"2024-12-09T08:55:48Z","snapshot_observed_at":"2026-08-13T23:38:27.652066Z","submitted_at":"2024-12-09T08:55:48Z","title":"PRECISE: Pre-training Sequential Recommenders with Collaborative and Semantic Information","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T19:52:59.758710Z"},"links":{"cited_paper":"/paper/2402.13598","citing_paper":"/paper/2412.06308"},"observation_digest":"sha256:d210a561e6e5715b8e4d4ca5fb36f9e4021120b233cb6986b4834f501fd05682","observation_id":"f5814c44-017d-408b-9b6c-b78de834dcb7","resolution":{"observed_at":"2026-08-11T19:52:59.758710Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13598","last_updated":"2024-09-09T19:51:57Z","snapshot_observed_at":"2026-08-16T14:16:41.619195Z","submitted_at":"2024-02-21T08:03:27Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13598","snapshot_observed_at":"2026-08-11T05:00:35.332531Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.18176","last_updated":"2024-12-30T09:24:34Z","snapshot_observed_at":"2026-08-18T13:49:54.448956Z","submitted_at":"2024-12-24T05:23:13Z","title":"Molar: Multimodal LLMs with Collaborative Filtering Alignment for Enhanced Sequential Recommendation","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-11T05:00:35.332531Z"},"links":{"cited_paper":"/paper/2402.13598","citing_paper":"/paper/2412.18176"},"observation_digest":"sha256:5a63015edbc93eaef46c706222048ce269bab3d179e1bf6ec775a8b3710977c2","observation_id":"f67d287e-44b9-4d66-bf44-6af97d133ad9","resolution":{"observed_at":"2026-08-11T05:00:35.332531Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13598","last_updated":"2024-09-09T19:51:57Z","snapshot_observed_at":"2026-08-16T14:16:41.619195Z","submitted_at":"2024-02-21T08:03:27Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13598","snapshot_observed_at":"2026-08-16T12:04:12.226516Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.13684","last_updated":"2025-04-18T13:35:21Z","snapshot_observed_at":"2026-08-16T12:00:09.843772Z","submitted_at":"2025-04-18T13:35:21Z","title":"Intelligent Interaction Strategies for Context-Aware Cognitive Augmentation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T12:04:12.226516Z"},"links":{"cited_paper":"/paper/2402.13598","citing_paper":"/paper/2504.13684"},"observation_digest":"sha256:ecd8d751440a701cee281dbb9bf926230c090a5e95dc6a2f08e4862ee16227f6","observation_id":"2271bbbb-c37e-4325-bd0b-57fdae41a9c6","resolution":{"observed_at":"2026-08-16T12:04:12.226516Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13598","last_updated":"2024-09-09T19:51:57Z","snapshot_observed_at":"2026-08-16T14:16:41.619195Z","submitted_at":"2024-02-21T08:03:27Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13598","snapshot_observed_at":"2026-08-16T11:07:58.490030Z","title":"User-llm: Efficient LLM contextualiza- tion with user embeddings,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.16420","last_updated":"2025-04-23T05:02:51Z","snapshot_observed_at":"2026-08-17T14:22:18.404244Z","submitted_at":"2025-04-23T05:02:51Z","title":"A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms","version":1},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-08-16T11:07:58.490030Z"},"links":{"cited_paper":"/paper/2402.13598","citing_paper":"/paper/2504.16420"},"observation_digest":"sha256:8d08335ceb9a074665d1f2a5ec8a0bbe31f0f3cfdf9c009f1ecc809aece2e567","observation_id":"5411a0a7-ac88-44dc-9bce-260880ed92d6","resolution":{"observed_at":"2026-08-16T11:07:58.490030Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13598","last_updated":"2024-09-09T19:51:57Z","snapshot_observed_at":"2026-08-16T14:16:41.619195Z","submitted_at":"2024-02-21T08:03:27Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13598","snapshot_observed_at":"2026-08-15T20:25:18.896345Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.13044","last_updated":"2025-05-19T12:33:52Z","snapshot_observed_at":"2026-08-18T14:33:47.507114Z","submitted_at":"2025-05-19T12:33:52Z","title":"CAIM: Development and Evaluation of a Cognitive AI Memory Framework for Long-Term Interaction with Intelligent Agents","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:18.896345Z"},"links":{"cited_paper":"/paper/2402.13598","citing_paper":"/paper/2505.13044"},"observation_digest":"sha256:5c8ace65a0577e19c1316d6583d8ef5398d4ff8aaca1efecb947f758d37787ab","observation_id":"d7f9c8ef-c0de-4132-a898-da72eedb27e3","resolution":{"observed_at":"2026-08-15T20:25:18.896345Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13598","last_updated":"2024-09-09T19:51:57Z","snapshot_observed_at":"2026-08-16T14:16:41.619195Z","submitted_at":"2024-02-21T08:03:27Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13598","snapshot_observed_at":"2026-08-15T21:02:03.181524Z","title":"User-llm: Efficient llm contextualization with user embeddings","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.17051","last_updated":"2025-05-16T13:34:25Z","snapshot_observed_at":"2026-08-17T19:13:23.858743Z","submitted_at":"2025-05-16T13:34:25Z","title":"Embedding-to-Prefix: Parameter-Efficient Personalization for Pre-Trained Large Language Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:03.181524Z"},"links":{"cited_paper":"/paper/2402.13598","citing_paper":"/paper/2505.17051"},"observation_digest":"sha256:3661330f315d7e7f35c1f59474291429533080b2f36557cb5830f6263f211c70","observation_id":"099005e2-2fab-4a20-8684-eae094dd79f1","resolution":{"observed_at":"2026-08-15T21:02:03.181524Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13598","last_updated":"2024-09-09T19:51:57Z","snapshot_observed_at":"2026-08-16T14:16:41.619195Z","submitted_at":"2024-02-21T08:03:27Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13598","snapshot_observed_at":"2026-08-07T14:39:51.958159Z","title":"User-llm: Efficient llm contextualization with user embeddings","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18071","last_updated":"2025-07-07T17:38:20Z","snapshot_observed_at":"2026-08-14T13:47:22.533486Z","submitted_at":"2025-05-23T16:16:46Z","title":"Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signals","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:51.958159Z"},"links":{"cited_paper":"/paper/2402.13598","citing_paper":"/paper/2505.18071"},"observation_digest":"sha256:0bf27b2df0e1e2fe2effda4a744ca72d33dcb914a9f12a16d8d936cce08a5a7e","observation_id":"832ce67a-7057-4741-91d5-c37ed5563240","resolution":{"observed_at":"2026-08-07T14:39:51.958159Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13598","last_updated":"2024-09-09T19:51:57Z","snapshot_observed_at":"2026-08-16T14:16:41.619195Z","submitted_at":"2024-02-21T08:03:27Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13598","snapshot_observed_at":"2026-08-06T19:37:08.021931Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.05137","last_updated":"2025-08-29T15:28:00Z","snapshot_observed_at":"2026-08-07T09:14:46.395513Z","submitted_at":"2025-07-07T15:49:23Z","title":"Interpretable Mnemonic Generation for Kanji Learning via Expectation-Maximization","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-06T19:37:08.021931Z"},"links":{"cited_paper":"/paper/2402.13598","citing_paper":"/paper/2507.05137"},"observation_digest":"sha256:9c331dfb64e2b1f7fa716a3fdb5161b7cc6560c3833775860c12c5d284768354","observation_id":"7cdb7862-1e4e-40e0-95f6-3c004d27de2f","resolution":{"observed_at":"2026-08-06T19:37:08.021931Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13598","last_updated":"2024-09-09T19:51:57Z","snapshot_observed_at":"2026-08-16T14:16:41.619195Z","submitted_at":"2024-02-21T08:03:27Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13598","snapshot_observed_at":"2026-08-04T10:26:11.374673Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.09905","last_updated":"2026-06-16T21:38:14Z","snapshot_observed_at":"2026-08-11T00:15:22.254397Z","submitted_at":"2025-10-10T22:39:37Z","title":"The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-04T10:26:11.374673Z"},"links":{"cited_paper":"/paper/2402.13598","citing_paper":"/paper/2510.09905"},"observation_digest":"sha256:16530446003c654ecee6b5967cbc25a89100f060801d16a2e4d4d8d2dcd9d2e4","observation_id":"896cf97a-cc07-4db8-905d-74910f18e7d1","resolution":{"observed_at":"2026-08-04T10:26:11.374673Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13598","last_updated":"2024-09-09T19:51:57Z","snapshot_observed_at":"2026-08-16T14:16:41.619195Z","submitted_at":"2024-02-21T08:03:27Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","version":2},"cited_work":{"arxiv_id":"2402.13598","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.13598","snapshot_observed_at":"2026-07-09T22:16:36.509652Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","venue":"cs.CL","work_id":"68b6a726-4600-4507-9c1e-fdc87ac2e886","year":2024},"citing_paper":{"arxiv_id":"2605.26612","last_updated":"2026-05-26T06:50:45Z","snapshot_observed_at":"2026-08-14T05:16:56.396895Z","submitted_at":"2026-05-26T06:50:45Z","title":"LATTE: Forecasting Peer Anchored Preference Trajectories for Personalized LLM Generation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-29T18:36:50.012434Z"},"links":{"cited_paper":"/paper/2402.13598","citing_paper":"/paper/2605.26612"},"observation_digest":"sha256:cd3de119972d4da00d6e44a94991dee2f6e0be0894be9ea8cdcb76d123b9bd35","observation_id":"71104885-0a07-4fbd-afe3-d2cc6d3bb2b7","resolution":{"observed_at":"2026-06-29T18:43:50.811474Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13598","last_updated":"2024-09-09T19:51:57Z","snapshot_observed_at":"2026-08-16T14:16:41.619195Z","submitted_at":"2024-02-21T08:03:27Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","version":2},"cited_work":{"arxiv_id":"2402.13598","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.13598","snapshot_observed_at":"2026-07-09T22:16:36.509652Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","venue":"cs.CL","work_id":"68b6a726-4600-4507-9c1e-fdc87ac2e886","year":2024},"citing_paper":{"arxiv_id":"2607.06993","last_updated":"2026-07-10T07:32:06Z","snapshot_observed_at":"2026-08-17T12:33:15.155025Z","submitted_at":"2026-07-08T04:31:18Z","title":"Large Behavior Model: A Promptable Digital Twin of the Retail Customer","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-09T22:13:38.928850Z"},"links":{"cited_paper":"/paper/2402.13598","citing_paper":"/paper/2607.06993"},"observation_digest":"sha256:e93238e4c044a1d55eff0a05f6acf1a170a6c6b99e6e18175802a846176e3d06","observation_id":"d1d6e22f-f4f3-40b8-a7fe-3df533e3e4a7","resolution":{"observed_at":"2026-07-09T22:16:36.513279Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13598","last_updated":"2024-09-09T19:51:57Z","snapshot_observed_at":"2026-08-16T14:16:41.619195Z","submitted_at":"2024-02-21T08:03:27Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13598","snapshot_observed_at":"2026-07-13T06:47:40.850966Z","title":"User-llm: Efficient llm contextualization with user embeddings,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.06993","last_updated":"2026-07-10T07:32:06Z","snapshot_observed_at":"2026-08-17T12:33:15.155025Z","submitted_at":"2026-07-08T04:31:18Z","title":"Large Behavior Model: A Promptable Digital Twin of the Retail Customer","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-13T06:47:40.850966Z"},"links":{"cited_paper":"/paper/2402.13598","citing_paper":"/paper/2607.06993"},"observation_digest":"sha256:f066f8c561f7ce2a64a0188c5c3a3a59bd12f6e17ee0008cf437dda70d136515","observation_id":"fb470c60-575c-4859-8ba0-260633474b5e","resolution":{"observed_at":"2026-07-13T06:47:40.850966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13598","last_updated":"2024-09-09T19:51:57Z","snapshot_observed_at":"2026-08-16T14:16:41.619195Z","submitted_at":"2024-02-21T08:03:27Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13598","snapshot_observed_at":"2026-07-14T02:23:46.480403Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.11267","last_updated":"2026-07-13T08:51:08Z","snapshot_observed_at":"2026-08-15T14:49:22.696604Z","submitted_at":"2026-07-13T08:51:08Z","title":"Enhancing LLMs through human feedback: a journey towards self-improvement","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-14T02:23:46.480403Z"},"links":{"cited_paper":"/paper/2402.13598","citing_paper":"/paper/2607.11267"},"observation_digest":"sha256:e44545d9fdd221b6ac0d451469697cfd87feee9486b2f74ddfac7ab5d466c8f0","observation_id":"7696205d-5468-472e-975b-e5e69ddc94f2","resolution":{"observed_at":"2026-07-14T02:23:46.480403Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13598","last_updated":"2024-09-09T19:51:57Z","snapshot_observed_at":"2026-08-16T14:16:41.619195Z","submitted_at":"2024-02-21T08:03:27Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13598","snapshot_observed_at":"2026-08-15T14:17:40.337708Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11354","last_updated":"2026-08-11T18:58:28Z","snapshot_observed_at":"2026-08-18T13:49:54.429270Z","submitted_at":"2026-08-11T18:58:28Z","title":"Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic Intelligent Interfaces","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T14:17:40.337708Z"},"links":{"cited_paper":"/paper/2402.13598","citing_paper":"/paper/2608.11354"},"observation_digest":"sha256:815bb8cd9e4bcc24d945118d5bcab7075652b7e35e6d631293d9facf5e915ee2","observation_id":"3c4e17f3-5518-4594-bb8a-b85d8349da90","resolution":{"observed_at":"2026-08-15T14:17:40.337708Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13598","last_updated":"2024-09-09T19:51:57Z","snapshot_observed_at":"2026-08-16T14:16:41.619195Z","submitted_at":"2024-02-21T08:03:27Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13598","snapshot_observed_at":"2026-08-14T10:42:20.397498Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.13454","last_updated":"2026-08-13T16:39:47Z","snapshot_observed_at":"2026-08-18T03:59:07.563600Z","submitted_at":"2026-08-13T16:39:47Z","title":"Before You Say It: Anticipating Verbal Behavior from Longitudinal Everyday Conversations with LLMs","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T10:42:20.397498Z"},"links":{"cited_paper":"/paper/2402.13598","citing_paper":"/paper/2608.13454"},"observation_digest":"sha256:be644db72951d10f22ad9d8a925bc5b9f093d072e4b7769fd4c0859e87f88008","observation_id":"630fe654-748a-4a1c-927a-9d0572b43238","resolution":{"observed_at":"2026-08-14T10:42:20.397498Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2402.13598/citation-record","integrity":"/paper/2402.13598/integrity","json":"/paper/2402.13598/citation-record.json","paper":"/paper/2402.13598"},"outbound":[],"paper":{"arxiv_id":"2402.13598","last_updated":"2024-09-09T19:51:57Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T14:16:41.619195Z","submitted_at":"2024-02-21T08:03:27Z","title":"User-LLM: Efficient LLM Contextualization with User Embeddings"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 16 inbound Pith citation observations for arXiv:2402.13598."}