{"as_of":"2026-08-08T12:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0d265a907882bd7aeea32ddd84a30c8ab3abe15cd67f95a5bfaf913f1b80d042","coverage":[{"denominator":29,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":29,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T19:46:41.592023Z","state":"measured"},{"denominator":29,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":29,"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/2509.09066/citation-record","integrity":"/paper/2509.09066/integrity","json":"/paper/2509.09066/citation-record.json","paper":"/paper/2509.09066"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.21927","last_updated":"2025-06-27T05:36:47Z","snapshot_observed_at":"2026-08-06T22:13:10.937484Z","submitted_at":"2025-06-27T05:36:47Z","title":"A Deep Learning Algorithm Based on CNN-LSTM Framework for Predicting Cancer Drug Sales Volume","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.21927","snapshot_observed_at":"2026-08-04T19:46:41.356183Z","title":"A Deep Learning Algorithm Based on CNN- LSTM Framework for Predicting Cancer Drug Sales Volume[J]","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.356183Z"},"links":{"cited_paper":"/paper/2506.21927","citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:26703dba8f59ddd6b2c8c393066fdca6018dab3318915f1024ac0d6aa4bb59d0","observation_id":"a9729609-df10-401d-8e88-8f9e48deef18","resolution":{"observed_at":"2026-08-04T19:46:41.356183Z","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":"2026-08-04T19:46:41.361690Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.361690Z"},"links":{"citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:67ad123e8c0ae8116dfe519dd8a5eba340af30be60eaf026b1495eaa3a5c9fda","observation_id":"ee82dd0b-b421-4c8f-94cc-b7279095acf2","resolution":{"observed_at":"2026-08-04T19:46:41.361690Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.17551","last_updated":"2025-06-24T02:28:50Z","snapshot_observed_at":"2026-08-06T23:28:16.170902Z","submitted_at":"2025-06-21T02:37:25Z","title":"Research on Model Parallelism and Data Parallelism Optimization Methods in Large Language Model-Based Recommendation Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.17551","snapshot_observed_at":"2026-08-04T19:46:41.367232Z","title":"Research on Model Parallelism and Data Parallelism Optimization Methods in Large Language Model-Based RecommendationSystems","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.367232Z"},"links":{"cited_paper":"/paper/2506.17551","citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:4428867ffcc7f8f92d738d81a6cfc6569334dd0d0bb034781a92f9c49add49f7","observation_id":"8b95a12c-1d3b-4306-80ea-1b484d814adc","resolution":{"observed_at":"2026-08-04T19:46:41.367232Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.04493","last_updated":"2025-07-06T18:10:00Z","snapshot_observed_at":"2026-08-06T19:44:10.974239Z","submitted_at":"2025-07-06T18:10:00Z","title":"Machine Learning-Based Prediction of Metal-Organic Framework Materials: A Comparative Analysis of Multiple Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.04493","snapshot_observed_at":"2026-08-04T19:46:41.372134Z","title":"Machine Learning-Based Prediction of Metal- Organic Framework Materials: A Comparative Analysis of Multiple Models[J].arXivpreprintarXiv:2507.04493,2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.372134Z"},"links":{"cited_paper":"/paper/2507.04493","citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:e02dbca4f21bf5f946409603fdbb6273929a22ae6b8aa05eca7957ff506323a2","observation_id":"535f3f23-2972-4dd7-a59d-56f14d7a42d3","resolution":{"observed_at":"2026-08-04T19:46:41.372134Z","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":"2026-08-04T19:46:41.377055Z","title":"Machine Learning based Enterprise Financial Audit Framework and High Risk Identification[J]","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.377055Z"},"links":{"citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:3d4f227a06773cc138d8fbf8c2bee1ffe99e3fdb3673122663a0848e3673b5e9","observation_id":"7de79aa0-7ad2-4052-8bfb-eb79596a73c8","resolution":{"observed_at":"2026-08-04T19:46:41.377055Z","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":"2026-08-04T19:46:41.384074Z","title":"(2024, August)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.384074Z"},"links":{"citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:82fdbf3eeb62a1c0d2f582ff5094a90cbf799f996f0b25aec2ca916ac7eb30f1","observation_id":"dac3513a-0530-4248-aa81-846a62790e75","resolution":{"observed_at":"2026-08-04T19:46:41.384074Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.14064","last_updated":"2025-08-11T02:39:16Z","snapshot_observed_at":"2026-08-08T04:00:53.872596Z","submitted_at":"2025-08-11T02:39:16Z","title":"An automatic patent literature retrieval system based on LLM-RAG","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.14064","snapshot_observed_at":"2026-08-04T19:46:41.388161Z","title":"An automatic patent literature retrieval system basedonLLM-RAG[J].arXivpreprintarXiv:2508.14064,2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.388161Z"},"links":{"cited_paper":"/paper/2508.14064","citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:ac0f1a3d44631177af1c43b73527b2b35432497b179f1e6a340ecd4241245653","observation_id":"4ec7402c-0a2e-4fe8-a56a-dc202a5a1357","resolution":{"observed_at":"2026-08-04T19:46:41.388161Z","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":"2026-08-04T19:46:41.391745Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.391745Z"},"links":{"citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:ad563d8003fcd69c40e08fc98acce8136ca6be9bff87a4c1c74a94d07e83b836","observation_id":"6c072d82-c022-40c4-b712-c0e6b066092a","resolution":{"observed_at":"2026-08-04T19:46:41.391745Z","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":"2026-08-04T19:46:41.395213Z","title":"Dynamic Allocation Mechanism of Cloud Computing Resources Driven by Neural Network","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.395213Z"},"links":{"citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:2233a66f368d9f2deff2c5de24c1ecddef1aefb0c01c8cd872ac8e31c5aa9bfe","observation_id":"a99aa8d8-60ae-4d74-86e4-a2cfbb3d2cd0","resolution":{"observed_at":"2026-08-04T19:46:41.395213Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.20367","last_updated":"2025-08-07T08:34:03Z","snapshot_observed_at":"2026-08-08T03:11:31.159173Z","submitted_at":"2024-12-29T06:15:41Z","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.20367","snapshot_observed_at":"2026-08-04T19:46:41.398759Z","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation[J]","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.398759Z"},"links":{"cited_paper":"/paper/2412.20367","citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:399405ad90430772993ffa777d9594363b635b9b13962df2139660c5d05a626c","observation_id":"5a2d8678-744e-481f-a02e-a3808b67795d","resolution":{"observed_at":"2026-08-04T19:46:41.398759Z","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":"2026-08-04T19:46:41.402331Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.402331Z"},"links":{"citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:52adb774008f61ad801218dc698bd073bec4b7feed6663ec3a7cf1f4a3f57cd3","observation_id":"1cbd824d-d1f8-49d9-bbf7-4ae34dc2ad54","resolution":{"observed_at":"2026-08-04T19:46:41.402331Z","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":"2026-08-04T19:46:41.406301Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.406301Z"},"links":{"citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:d177fae3713987951425f854f9f1f05206d5c3d6680782373125b0946a5a1685","observation_id":"1abcc661-bef6-401e-bf67-7861fe2fa391","resolution":{"observed_at":"2026-08-04T19:46:41.406301Z","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":"2026-08-04T19:46:41.410035Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.410035Z"},"links":{"citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:60f2d8fdc7f1d2f3ff07c6860b8784a981d62f094ba234b35d6068b470edbdd0","observation_id":"ae54c0ed-7165-4d1e-aacd-7f89a03f4910","resolution":{"observed_at":"2026-08-04T19:46:41.410035Z","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":"2026-08-04T19:46:41.413575Z","title":"& Wang, X","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.413575Z"},"links":{"citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:2cd305d81c61aecb3a44eab8020a302606ee5fd6bc27ed0d7eac05aca843ac0f","observation_id":"4f5eb39f-8bd7-45da-b643-85b184eba39a","resolution":{"observed_at":"2026-08-04T19:46:41.413575Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.14577","last_updated":"2024-09-22T19:44:46Z","snapshot_observed_at":"2026-08-05T14:11:06.518166Z","submitted_at":"2024-09-22T19:44:46Z","title":"AR Overlay: Training Image Pose Estimation on Curved Surface in a Synthetic Way","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.14577","snapshot_observed_at":"2026-08-04T19:46:41.416989Z","title":"Ar overlay: Training image pose estimation on curved surface in a synthetic way","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.416989Z"},"links":{"cited_paper":"/paper/2409.14577","citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:c73e650cef25f07f4f47f0cf9cde7b212a7ccacd1cb607fd4e0841c322d1cced","observation_id":"b7bd6588-b702-4b67-886c-2c62544b0b6d","resolution":{"observed_at":"2026-08-04T19:46:41.416989Z","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":"2026-08-04T19:46:41.421783Z","title":"Tie memories to e- souvenirs:Personalized souvenirswithaugmentedrealityforinteractive learninginthemuseum","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.421783Z"},"links":{"citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:add1ad9380d07c80e4f15f16799508f4c3968bb62f71a6953982a96086f77728","observation_id":"a29363fa-ae0a-427b-85fa-dbbda3e95856","resolution":{"observed_at":"2026-08-04T19:46:41.421783Z","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":"2026-08-04T19:46:41.426160Z","title":"Recurrent neural network from adder’s perspective:Carry-lookaheadRNN","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.426160Z"},"links":{"citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:76074daa9b598eb16a6a3ce433e2d03254900338572e9780cc83ae30a1e48d57","observation_id":"5042fe7f-1505-4ae4-9d45-c271d0d1a542","resolution":{"observed_at":"2026-08-04T19:46:41.426160Z","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":"2026-08-04T19:46:41.431988Z","title":"Rough set improved therapy-based metaverse assisting system","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.431988Z"},"links":{"citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:e72049caed2b20affdcbb775d8aac0d7ca05d546f6528077e69bf2ab8ddd1b73","observation_id":"08a104b5-a435-46bb-8329-8907b02c64e3","resolution":{"observed_at":"2026-08-04T19:46:41.431988Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.16296","last_updated":"2024-05-17T13:14:30Z","snapshot_observed_at":"2026-07-06T18:05:16.683850Z","submitted_at":"2024-04-25T02:28:16Z","title":"Research on Splicing Image Detection Algorithms Based on Natural Image Statistical Characteristics","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.16296","snapshot_observed_at":"2026-08-04T19:46:41.439373Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.439373Z"},"links":{"cited_paper":"/paper/2404.16296","citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:f34581c2b10f852994476af43adacb479c0c7dc478f1066e30df35e1ddce0803","observation_id":"9d7ed422-8c3f-4f84-971f-a71a0286d9e4","resolution":{"observed_at":"2026-08-04T19:46:41.439373Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.06279","last_updated":"2025-03-20T21:19:15Z","snapshot_observed_at":"2026-08-07T16:47:57.834618Z","submitted_at":"2025-03-20T21:19:15Z","title":"Financial Analysis: Intelligent Financial Data Analysis System Based on LLM-RAG","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.06279","snapshot_observed_at":"2026-08-04T19:46:41.447390Z","title":"Financial analysis: Intelligent financial data analysis system based on llm-rag","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.447390Z"},"links":{"cited_paper":"/paper/2504.06279","citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:39a3598fc9e8cdf2f69735a851da898a057e01b384c1a62031983b23751f9658","observation_id":"3e271bf1-4558-4c9b-9d8f-ff7f66650e5f","resolution":{"observed_at":"2026-08-04T19:46:41.447390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.08751","last_updated":"2025-03-27T22:56:41Z","snapshot_observed_at":"2026-08-07T16:31:29.064181Z","submitted_at":"2025-03-27T22:56:41Z","title":"Research on the Design of a Short Video Recommendation System Based on Multimodal Information and Differential Privacy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.08751","snapshot_observed_at":"2026-08-04T19:46:41.456017Z","title":"Research on the Design of a Short Video Recommendation System Based on Multimodal Information and DifferentialPrivacy[J].arXivpreprintarXiv:2504.08751,2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.456017Z"},"links":{"cited_paper":"/paper/2504.08751","citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:591c7418c985d6cc72790e461bf2127a1b89adf289167b030d0b37fa925074c8","observation_id":"e828dabf-443f-484e-8ae0-982db3533cdb","resolution":{"observed_at":"2026-08-04T19:46:41.456017Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.18713","last_updated":"2024-12-25T00:23:53Z","snapshot_observed_at":"2026-07-06T20:12:59.152345Z","submitted_at":"2024-12-25T00:23:53Z","title":"Enhanced Recommendation Combining Collaborative Filtering and Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.18713","snapshot_observed_at":"2026-08-04T19:46:41.465794Z","title":"Enhanced Recommendation Combining Collaborative Filtering and Large Language Models[J]","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.465794Z"},"links":{"cited_paper":"/paper/2412.18713","citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:27546c16625a0fe183342dad56687ae5130f1abe6a17ec3d1ee2af4efdd3ee7b","observation_id":"76f265db-46e2-452c-bbd8-967fc5722143","resolution":{"observed_at":"2026-08-04T19:46:41.465794Z","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":"2026-08-04T19:46:41.474536Z","title":"Decodingstudentcognitiveabilities:acomparative study of explainable AI algorithms in educational data mining","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.474536Z"},"links":{"citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:008d43852a7c28f712ea4d109aac633e32a23ba950f77f8a24abec468f1ba39e","observation_id":"b9413481-bd59-446f-a781-649faab666ad","resolution":{"observed_at":"2026-08-04T19:46:41.474536Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.16672","last_updated":"2025-07-22T15:07:23Z","snapshot_observed_at":"2026-08-06T15:02:14.025584Z","submitted_at":"2025-07-22T15:07:23Z","title":"Meta-Learning for Cold-Start Personalization in Prompt-Tuned LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.16672","snapshot_observed_at":"2026-08-04T19:46:41.481942Z","title":"Meta-Learning for Cold-Start Personalization in Prompt-Tuned LLMs","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.481942Z"},"links":{"cited_paper":"/paper/2507.16672","citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:5cd17b542e31d238145570cc5da0d07b59324ec340a0b8fe3d5f0205ad8a30bb","observation_id":"7e5bd490-1dd3-420c-930c-d6751186cfe5","resolution":{"observed_at":"2026-08-04T19:46:41.481942Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.05289","last_updated":"2025-08-07T11:36:55Z","snapshot_observed_at":"2026-08-05T23:28:35.537565Z","submitted_at":"2025-08-07T11:36:55Z","title":"RLHF Fine-Tuning of LLMs for Alignment with Implicit User Feedback in Conversational Recommenders","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.05289","snapshot_observed_at":"2026-08-04T19:46:41.489691Z","title":"RLHF Fine-Tuning of LLMs for Alignment with Implicit User Feedback in Conversational Recommenders","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.489691Z"},"links":{"cited_paper":"/paper/2508.05289","citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:2abd397a03693a076b6a52962015eae4e004f7771efd6f2a0579eda0d437bf40","observation_id":"cbf72c0f-fa0d-4ca6-8744-9506b34e04fd","resolution":{"observed_at":"2026-08-04T19:46:41.489691Z","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":"2026-08-04T19:46:41.499048Z","title":"Bideeplab: An improved lightweight multi-scale feature fusion deeplab algorithm for facial recognition on mobile devices[J]","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.499048Z"},"links":{"citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:0c525bf02acb26b9f8fce81ff9e9aff1ea67c695f09d73aabdc5200745f440e1","observation_id":"bdedbeaa-aff2-4d7d-87bf-4ba829f5e718","resolution":{"observed_at":"2026-08-04T19:46:41.499048Z","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":"2026-08-04T19:46:41.516684Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.516684Z"},"links":{"citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:4117f56a29e49ed20ca6857af260a3b4ad0d55f78aa7d9a8a7157b542b458c1b","observation_id":"446364f2-7054-4f70-ac5e-6dafff26dd05","resolution":{"observed_at":"2026-08-04T19:46:41.516684Z","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":"2026-08-04T19:46:41.533961Z","title":"Self-Supervised User Embedding Alignment for Cross-Domain Recommendations via Multi-LLM Co-Training","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.533961Z"},"links":{"citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:a9ee7c00d5f9f3d59453087350252ef0480d3a0e220205d91ee8bb83c2377759","observation_id":"64438a9c-22b4-42ee-82f8-c709804ea80f","resolution":{"observed_at":"2026-08-04T19:46:41.533961Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.11421","last_updated":"2025-08-13T15:18:09Z","snapshot_observed_at":"2026-08-07T04:07:23.347386Z","submitted_at":"2025-06-13T02:39:21Z","title":"Deep Learning Model Acceleration and Optimization Strategies for Real-Time Recommendation Systems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.11421","snapshot_observed_at":"2026-08-04T19:46:41.592023Z","title":"DeepLearningModelAccelerationandOptimization Strategies for Real-Time Recommendation Systems","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:41.592023Z"},"links":{"cited_paper":"/paper/2506.11421","citing_paper":"/paper/2509.09066"},"observation_digest":"sha256:157d7eb01a621c2565e88fed2b196d12caa505c982c7881e15fc14e7320bbe00","observation_id":"304e5980-4df1-4b05-8c38-56065e002e23","resolution":{"observed_at":"2026-08-04T19:46:41.592023Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.09066","last_updated":"2025-09-11T00:13:17Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-04T19:46:40.464000Z","submitted_at":"2025-09-11T00:13:17Z","title":"Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users"},"reference_resolution":{"displayed":29,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":29,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":29},"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 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2509.09066."}