{"as_of":"2026-08-20T17:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7d890962436dfe66721c96c2259fc18f8d42095c025271f8de676f2735b216ce","coverage":[{"denominator":107,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T16:27:23.319123Z","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":"2026-08-20T06:33:59.587034+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/2507.13525/citation-record","integrity":"/paper/2507.13525/integrity","json":"/paper/2507.13525/citation-record.json","paper":"/paper/2507.13525"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:27:22.961380Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:22.961380Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:362287ed9e905cf2800c839e5fe948ecd0a9cac4b2d0f4de23d551e252e69e9d","observation_id":"d1229ee6-26f4-4891-b4fb-b87dace61d28","resolution":{"observed_at":"2026-08-06T16:27:22.961380Z","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":"2026-08-06T16:27:22.964515Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:22.964515Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:93864101f67716233ca8f0c9d9aa8be1902d43d7775418227b79c5f4f9b612cb","observation_id":"abf5e507-d85e-48df-b92b-d5959819c681","resolution":{"observed_at":"2026-08-06T16:27:22.964515Z","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":"2026-08-06T16:27:23.054316Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.054316Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:c0177b0658bf9a08e52f5ecae883dad10989863eef7401d7dbfe4673b9a4aff6","observation_id":"e3270b96-33a7-45dc-a3b9-d3e967042f07","resolution":{"observed_at":"2026-08-06T16:27:23.054316Z","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":"2026-08-06T16:27:23.056961Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.056961Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:26c33c75f7cc917967a64f8fe38411b9a4c1150c9fa86faaa2ef1bc99da48940","observation_id":"00633b33-c19b-4c87-8dd2-dc00dec7f4e6","resolution":{"observed_at":"2026-08-06T16:27:23.056961Z","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":"2026-08-06T16:27:23.059660Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.059660Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:19ceeb3a275892e361e78bb5900e45fc27e941d5802e5511bffd9461349e5dce","observation_id":"c6909d97-880d-4cd9-a1af-be8ae0a258cc","resolution":{"observed_at":"2026-08-06T16:27:23.059660Z","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":"2026-08-06T16:27:23.062548Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.062548Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:a87da864eb0b998655609db2efabb925a6c336fc9bfa1ab03eca72a4704def96","observation_id":"9d1742e4-550b-485e-8923-42c3b3ea85d1","resolution":{"observed_at":"2026-08-06T16:27:23.062548Z","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":"2026-08-06T16:27:23.065123Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.065123Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:18a21c0c4cdb27508bd28bb580f5d1626b96f6ce92ee20716c4b41b10e99da22","observation_id":"4ce6f95a-8f70-4738-a10f-3c5bec003669","resolution":{"observed_at":"2026-08-06T16:27:23.065123Z","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":"2026-08-06T16:27:23.067776Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.067776Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:a86e6d731cb982b829c51e573f4fdd05469604fd8ea6fe8f58a316672fc792c5","observation_id":"74bb6a1a-468a-4d3d-94e1-02f7201a272a","resolution":{"observed_at":"2026-08-06T16:27:23.067776Z","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":"2026-08-06T16:27:23.070722Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.070722Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:6138101ba0b22fef8f96518d5f995cfa3ca1399a68901f1bc641290920bcbe6d","observation_id":"b044ebef-146a-4cda-9c32-98b8cf792c96","resolution":{"observed_at":"2026-08-06T16:27:23.070722Z","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":"2026-08-06T16:27:23.073159Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.073159Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:c05b571f317f3c92791271b2a85f0add9a1b1d612657f7027983211a062079f3","observation_id":"b3e1f64e-5247-4c6a-9628-15f4a114515a","resolution":{"observed_at":"2026-08-06T16:27:23.073159Z","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":"2026-08-06T16:27:23.075894Z","title":"McAuley, Anton Korikov, Scott Sanner, Arnau Ramisa, René Vidal, Maheswaran Sathiamoorthy, Atoosa Kasirzadeh, and Silvia Milano","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.075894Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:4dab5253a6267bbb0242844d5fa521e15e51dab79a0261eac3c6029561ba7d1b","observation_id":"f60b2031-2bab-4420-9207-5e5a658a7e80","resolution":{"observed_at":"2026-08-06T16:27:23.075894Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.04205","last_updated":"2024-04-18T23:49:56Z","snapshot_observed_at":"2026-08-18T21:47:36.698819Z","submitted_at":"2023-11-07T18:43:34Z","title":"Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.04205","snapshot_observed_at":"2026-08-06T16:27:23.078614Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.078614Z"},"links":{"cited_paper":"/paper/2311.04205","citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:fdf5f91fecb780f35e68b91e38433caf11b9b409dc663eb3f4941a919d5b5a60","observation_id":"d1a2721c-5df4-4e42-a31c-01d126593d62","resolution":{"observed_at":"2026-08-06T16:27:23.078614Z","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":"2026-08-06T16:27:23.081504Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.081504Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:65b5946958e49767a51b7970324922ad5cbb11461dc875a8e72fa3f02f451c9e","observation_id":"b67920ee-9e80-4813-958d-a68dca5a1d91","resolution":{"observed_at":"2026-08-06T16:27:23.081504Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.02061","last_updated":"2026-07-28T04:34:05Z","snapshot_observed_at":"2026-08-19T03:08:14.388665Z","submitted_at":"2025-02-04T07:17:54Z","title":"Reason4Rec: Deliberative User Preference Alignment of Large Language Models for Recommendation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.02061","snapshot_observed_at":"2026-08-06T16:27:23.084212Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.084212Z"},"links":{"cited_paper":"/paper/2502.02061","citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:91ad694041bb6f0cb9d5ad51fd848c118df83e93408e6d1c92a98512a54b4ee3","observation_id":"1c8feb49-5bba-484e-8d35-e6db88d4a8a3","resolution":{"observed_at":"2026-08-06T16:27:23.084212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.14524","last_updated":"2023-04-04T03:51:27Z","snapshot_observed_at":"2026-08-16T15:45:22.748505Z","submitted_at":"2023-03-25T17:37:43Z","title":"Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.14524","snapshot_observed_at":"2026-08-06T16:27:23.087264Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.087264Z"},"links":{"cited_paper":"/paper/2303.14524","citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:f05f65fc0c11543fb9f99c94d3453cf931cebf066f57527ff8c9698b308965cd","observation_id":"32c3b25b-8c2d-483b-85b8-914166773ebc","resolution":{"observed_at":"2026-08-06T16:27:23.087264Z","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":"2026-08-06T16:27:23.090019Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.090019Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:16cde6daaef7f583fba6436c81b3ef449c1556f524757645432779f12e341521","observation_id":"f2de68af-52f2-4f9a-8fa3-9302e9cad2e4","resolution":{"observed_at":"2026-08-06T16:27:23.090019Z","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":"2026-08-06T16:27:23.092757Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.092757Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:f5f73a7a774582e177e5a0f5f2d0308010186dbfe7f0cadbb0289a8266846152","observation_id":"322ce2c4-c9c3-4263-a440-a3bc235c9817","resolution":{"observed_at":"2026-08-06T16:27:23.092757Z","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":"2026-08-06T16:27:23.095357Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.095357Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:867a3733f678720a4377c6875b6b6fea2a05cbe49b48dd8d928fa626a5a23ea2","observation_id":"fe31a2d5-4c16-4b3c-bcf7-55c2cb9bebd4","resolution":{"observed_at":"2026-08-06T16:27:23.095357Z","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":"2026-08-06T16:27:23.098242Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.098242Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:f632491771520709cc390d25262684a0f23401de0cae1fab876b08386ee680e4","observation_id":"4b914f7c-8323-4e3c-9d8b-b8d7d4d0c2b4","resolution":{"observed_at":"2026-08-06T16:27:23.098242Z","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":"2026-08-06T16:27:23.100676Z","title":"McAuley, and Wayne Xin Zhao","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.100676Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:42c4d56d7eee9958d93d4e78f884375894a80e909afead3b3f342c8c586f8272","observation_id":"3534ac82-7c89-4489-8065-f92e1b0c4913","resolution":{"observed_at":"2026-08-06T16:27:23.100676Z","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":"2026-08-06T16:27:23.103077Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.103077Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:de4d993da523a6b2500e152d14ad6196b19bf8a46aa1f2facafaff651b6f2ca0","observation_id":"2c06db50-9257-4912-95d9-5d010d3195d4","resolution":{"observed_at":"2026-08-06T16:27:23.103077Z","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":"2026-08-06T16:27:23.105601Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.105601Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:ea53f68eb8e1b1c41568c01f872ffde6c6948b0d4560121be118dc9e147dd3a4","observation_id":"7c101553-f878-4a61-a138-ea4a92743bf2","resolution":{"observed_at":"2026-08-06T16:27:23.105601Z","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":"2026-08-06T16:27:23.108263Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.108263Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:fc53b156de6f8936f280daf1865ff63869dbcac1f2032bca23a7cf33badb4b03","observation_id":"56ef0084-5d28-4903-b138-66b5f9f717df","resolution":{"observed_at":"2026-08-06T16:27:23.108263Z","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":"2026-08-06T16:27:23.110861Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.110861Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:96acda024624b264a8d3fa4a4031b395978b8d005a2df458dc75db8e2b61b55e","observation_id":"bc8303c1-fdb2-4d40-a6c2-d0477c3f3a38","resolution":{"observed_at":"2026-08-06T16:27:23.110861Z","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":"2026-08-06T16:27:23.113897Z","title":"Bell, and Chris Volinsky","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.113897Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:9b5ed7b4b1bb66b9b6b9cb3883a49b25ea0ea48f6ef3cfc3d6a03ecffc8ce8c2","observation_id":"d631bde4-1285-4f2d-9db3-1db74fb9e4a9","resolution":{"observed_at":"2026-08-06T16:27:23.113897Z","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":"2026-08-06T16:27:23.116634Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.116634Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:7ccb3e4dd7f8d5f47927044118204b6da8424b136c9bec6ce2f34ccd0b7748ca","observation_id":"46562782-21d3-4c63-87d9-67cb19b725cc","resolution":{"observed_at":"2026-08-06T16:27:23.116634Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.11760","last_updated":"2023-11-12T12:35:41Z","snapshot_observed_at":"2026-08-19T19:37:47.334752Z","submitted_at":"2023-07-14T00:57:12Z","title":"Large Language Models Understand and Can be Enhanced by Emotional Stimuli","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.11760","snapshot_observed_at":"2026-08-06T16:27:23.119561Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.119561Z"},"links":{"cited_paper":"/paper/2307.11760","citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:a2710af0b6ae9faf7a028357b6fe45f034d31bca1a32d90645e752b70c7d72c8","observation_id":"e69974c5-adbc-4ff2-8205-8e985b5e47d5","resolution":{"observed_at":"2026-08-06T16:27:23.119561Z","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":"2026-08-06T16:27:23.122396Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.122396Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:e50e066358ccc85d4e1656849a52f0099fdbabe6952f722f63c3a149db470f2f","observation_id":"9f346a38-8621-4166-94c2-0f87b6a4bd99","resolution":{"observed_at":"2026-08-06T16:27:23.122396Z","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":"2026-08-06T16:27:23.125144Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.125144Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:9955e0f5693f7f1aa4932a43dc45330712214e317352704c8969ea6b1e8ddd74","observation_id":"2eee526b-9f87-4096-abbb-189195155020","resolution":{"observed_at":"2026-08-06T16:27:23.125144Z","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":"2026-08-06T16:27:23.127649Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.127649Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:f94fef960000686a0c1ed6ef2ffb5a7f53e24bdfbd7e416a5a8e94bd534c7bf0","observation_id":"2277d50e-2fc3-4178-a8f0-b20af4f34318","resolution":{"observed_at":"2026-08-06T16:27:23.127649Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.10149","last_updated":"2023-10-27T09:11:50Z","snapshot_observed_at":"2026-08-18T13:58:48.093535Z","submitted_at":"2023-04-20T08:16:07Z","title":"Is ChatGPT a Good Recommender? A Preliminary Study","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.10149","snapshot_observed_at":"2026-08-06T16:27:23.130275Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.130275Z"},"links":{"cited_paper":"/paper/2304.10149","citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:0d812f11176df96dda4ebfdc4e7b45061a2629ea52cb5a339ddc2606763c492d","observation_id":"d170c00e-3f01-4f52-98b8-5c37d13cfa0e","resolution":{"observed_at":"2026-08-06T16:27:23.130275Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13845","last_updated":"2025-04-18T07:45:55Z","snapshot_observed_at":"2026-08-16T12:56:56.805541Z","submitted_at":"2025-02-19T16:08:17Z","title":"Improving LLM-powered Recommendations with Personalized Information","version":2},"cited_work":{"arxiv_id":"2502.13845","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.13845","snapshot_observed_at":"2026-08-06T16:27:23.400163Z","title":"Improving LLM-powered Recommendations with Personalized Information","venue":"cs.IR","work_id":"e8aea9bb-11b5-49e6-acfa-8cefa36cf60a","year":2025},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.133139Z"},"links":{"cited_paper":"/paper/2502.13845","citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:a70e5c92d37ddb2bc141d8a94f812ab7b13843e2934737c3d39f171bb8855f26","observation_id":"6383774f-7cef-4cab-8b27-b5cbcac049d0","resolution":{"observed_at":"2026-08-06T16:27:23.405514Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.987756Z","title":null,"venue":null,"work_id":"3b038bef-3b7f-4ed5-a7da-8062f82f6d70","year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.136148Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:e0cd1b36ab5ecf4b7e94a872a9984704920ad7c4b5d6ce6cd5a4d2be70ad84cc","observation_id":"8241b54c-f697-4a2f-a68e-164cc958f25d","resolution":{"observed_at":"2026-08-06T16:27:23.990780Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.978549Z","title":null,"venue":null,"work_id":"a9e0a10d-0fcc-4ce3-8334-5cf2419d5110","year":2023},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.138507Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:4981116c7a11bf47d057eaafe9b0ed5cc38ed17f60dd5ed865af974e11a37862","observation_id":"88448814-485c-4404-af8e-2ecf9dbd952b","resolution":{"observed_at":"2026-08-06T16:27:23.982109Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.970032Z","title":null,"venue":null,"work_id":"3c7802cf-c44f-46c9-9659-594585bbcecf","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.141115Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:344993a6ef64479290301b77817a613ae222d9295b873273c493fff93fbf5b85","observation_id":"6f88ce3d-67d3-4ad7-9567-afbc44954dcb","resolution":{"observed_at":"2026-08-06T16:27:23.973045Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.951355Z","title":null,"venue":null,"work_id":"8c3dc03a-6f10-41f8-b0a6-d0cafe7dd093","year":2017},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.146440Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:857625768db04fe84283bcb752420a12a5e4bb9dea3570f2dfe920350529208d","observation_id":"6dc8913a-263e-4255-8f1d-65f5ab26e5d4","resolution":{"observed_at":"2026-08-06T16:27:23.954865Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.942169Z","title":null,"venue":null,"work_id":"838b4e6b-1429-4e4f-9593-dba942cb0d5d","year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.149029Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:133ef6030b4af8cc29172479e3296fd2eddb586c03f8641cb712246a201d1ca7","observation_id":"44d0b81d-76ce-4600-b169-c3363b79c553","resolution":{"observed_at":"2026-08-06T16:27:23.945279Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.933182Z","title":null,"venue":null,"work_id":"1882a4a5-a56e-487f-bbfe-08fd94820f44","year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.151623Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:e90914f0ee623a921abfb087a4b30b58e0ab875cd47e191bca6627e006ae9dd8","observation_id":"e0185b64-4a2d-47aa-bed6-996c3a3eae29","resolution":{"observed_at":"2026-08-06T16:27:23.936219Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.924582Z","title":null,"venue":null,"work_id":"45865910-7792-4290-a67f-41d7a7851f5f","year":2019},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.154554Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:bf67fb3d185f5549b4f6414cf98340975ceb42703f8d53bc121bcde4e494a111","observation_id":"973060ef-e757-4593-b179-2a9d0088dea1","resolution":{"observed_at":"2026-08-06T16:27:23.927406Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.915787Z","title":"Petrov and Craig Macdonald","venue":null,"work_id":"6a1dcea1-94c3-4cf7-bcaa-2ed4e563f212","year":2022},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.157038Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:f93e2e1c4eed1a9a2f3dd4111e62559767c7dfa7de9e3f0193a3a1275b1a46fa","observation_id":"514342f0-a8b2-466d-8723-104e8ed13661","resolution":{"observed_at":"2026-08-06T16:27:23.918923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.906823Z","title":"Anderson","venue":null,"work_id":"d751e912-1f09-4e5b-9567-8e325b037bde","year":2020},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.159440Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:99b0558917aceb74318a9b1aa46e8df0edd5fea1dc9a489564d17ad5467f93aa","observation_id":"a6a67525-c8b1-4425-98e0-05f5dd27b7b5","resolution":{"observed_at":"2026-08-06T16:27:23.910193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07927","last_updated":"2025-03-16T06:23:34Z","snapshot_observed_at":"2026-08-16T14:09:52.485275Z","submitted_at":"2024-02-05T19:49:13Z","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.07927","snapshot_observed_at":"2026-08-06T16:27:23.161730Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.161730Z"},"links":{"cited_paper":"/paper/2402.07927","citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:d4ec691ce64df83d552abe3ab88c8adfe8ab000f9c70551151473c91783aa08d","observation_id":"2acac194-bdf4-485e-bb45-40703cfc35e0","resolution":{"observed_at":"2026-08-06T16:27:23.161730Z","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":"2026-08-06T16:27:23.894929Z","title":null,"venue":null,"work_id":"9e6028ed-9c8a-45f2-bd15-f3fa4181a6d4","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.164195Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:db52e5a64c4c0eabf7bed6fad6e46c2d1858111c2664b4c06d9bf3d1672993b0","observation_id":"80283e34-9e69-441e-b04d-4d471a9e495f","resolution":{"observed_at":"2026-08-06T16:27:23.899003Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.169887Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.169887Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:a5f28a3c86cd0e072be017a18b56c50eb62f35af2bc32d6fc80743f6cc934843","observation_id":"7d8fab55-cad8-40cf-a13e-9fedd47aee68","resolution":{"observed_at":"2026-08-06T16:27:23.169887Z","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":"2026-08-06T16:27:23.174818Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.174818Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:6f4b26fc7cdb23ff7d99f68ce553e65bf2dc01c28c14fc7a30667b5351ab3ef5","observation_id":"3962767e-2904-4b8f-9b14-3fa5ec2eef56","resolution":{"observed_at":"2026-08-06T16:27:23.174818Z","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":"2026-08-06T16:27:23.850645Z","title":null,"venue":null,"work_id":"fa31fd24-9719-4f26-bd0b-9eecb5fc76b4","year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.179715Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:9a0ba7cdfa4d8654e0374226f66a137571642a71b4ce5cca0aeb43a669ee57f1","observation_id":"416aa812-2662-43f0-baf4-53bbc86f1231","resolution":{"observed_at":"2026-08-06T16:27:23.854313Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.12994","last_updated":"2024-07-24T03:53:41Z","snapshot_observed_at":"2026-08-18T20:36:52.662035Z","submitted_at":"2024-07-17T20:23:19Z","title":"A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.12994","snapshot_observed_at":"2026-08-06T16:27:23.182275Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.182275Z"},"links":{"cited_paper":"/paper/2407.12994","citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:e0200805deb65b689f3d5692e497d60c5091732bd8bbc642838221458fcd0559","observation_id":"f57cdd04-7be8-4337-a85e-b4850550b781","resolution":{"observed_at":"2026-08-06T16:27:23.182275Z","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":"2026-08-06T16:27:23.878118Z","title":null,"venue":null,"work_id":"85ba8d29-ad51-4c38-8229-b6e1a20e2479","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.172230Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:65b2af1ea1a839a1180126cc694e5cc32024121067fb22de2f4481a6de04d729","observation_id":"3d7d962a-2c84-4833-b5d5-cc8d1bee5037","resolution":{"observed_at":"2026-08-06T16:27:23.882582Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.840534Z","title":null,"venue":null,"work_id":"4a84debf-868b-465c-b7df-4717dc322f9b","year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.187962Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:1811b5160743bd111ca781c8eccae83f8ed46cc4a70200ce5499d024e4565959","observation_id":"576f3fd9-bc2a-4326-a421-11ef194aaef2","resolution":{"observed_at":"2026-08-06T16:27:23.843874Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.830112Z","title":null,"venue":null,"work_id":"3b5a7758-3bdf-415a-b8da-e169206ab08d","year":2023},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.190737Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:794e802ad9d7141f31009b07716d149a5d049ae56f7a512e633b1399ef5d62d3","observation_id":"3f61c9b4-f6f4-454e-8f37-65db9d000a0f","resolution":{"observed_at":"2026-08-06T16:27:23.834164Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.821391Z","title":null,"venue":null,"work_id":"e11359b7-68e4-448c-96e4-b697435703be","year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.193110Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:404cdf5cdb6cdcf0ed4b92e2da409577509446acda290a0134b9d2c983f32d16","observation_id":"5aeb1dfa-1064-4372-814b-7872294e2c34","resolution":{"observed_at":"2026-08-06T16:27:23.824104Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.812327Z","title":"Le, Ed H","venue":null,"work_id":"e59bbe64-a0b7-48c4-99d1-4269ad633abc","year":2023},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.195620Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:c9bf19e35e7cf39c4662c8d8e5a0a597dca5d5935d05cceeb4ec50c4af9482b9","observation_id":"18a397a1-4619-44bf-a0ed-e410ea79eaeb","resolution":{"observed_at":"2026-08-06T16:27:23.815438Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.03153","last_updated":"2023-04-06T15:35:11Z","snapshot_observed_at":"2026-08-18T19:17:53.229417Z","submitted_at":"2023-04-06T15:35:11Z","title":"Zero-Shot Next-Item Recommendation using Large Pretrained Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.03153","snapshot_observed_at":"2026-08-06T16:27:23.184884Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.184884Z"},"links":{"cited_paper":"/paper/2304.03153","citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:875143132c3797bac4f6ae3dc517b3e51cd5d5ac1050b74f7d5705f11d773763","observation_id":"7c99722a-bdb7-4442-9d3c-c30dd148a1ac","resolution":{"observed_at":"2026-08-06T16:27:23.184884Z","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":"2026-08-06T16:27:23.799367Z","title":null,"venue":null,"work_id":"e8636687-d463-4218-aa76-cf8054c188ab","year":2021},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.200854Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:28731ad94f00adc7ba83331ae325b99eece415dbee59c916e55b00d646ba5a1b","observation_id":"6bb64728-23d3-42c5-8096-e8036239bc2b","resolution":{"observed_at":"2026-08-06T16:27:23.801939Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.792078Z","title":null,"venue":null,"work_id":"0f10d4a3-133d-4c4a-8a87-f333bf1096df","year":2020},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.203631Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:f0b138b15cc9d6d459b8a36e1330d2ee7e467674b5eb058a9f47576a19cfb821","observation_id":"87573292-7e1f-41cb-b661-cab4449c83f5","resolution":{"observed_at":"2026-08-06T16:27:23.794392Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.205913Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.205913Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:b289ffaccd9f33fef34f28fdc7fbd9f4b51d9cc45a51047d35ae8b86b4d06d1a","observation_id":"eeb9f140-06bd-40cc-88c2-4225fa68a7c6","resolution":{"observed_at":"2026-08-06T16:27:23.205913Z","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":"2026-08-06T16:27:23.771198Z","title":null,"venue":null,"work_id":"97319858-d540-407a-81e4-b56981e9d804","year":2025},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.210942Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:532fe5b1a6326bebf712d81b9b86393a22de6acb8939ca67832fbc81fe5dc469","observation_id":"137e6688-8f1a-48b5-9e3c-93e77490b165","resolution":{"observed_at":"2026-08-06T16:27:23.774067Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.198459Z","title":"Chi, Quoc V","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.198459Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:3493e0f0546cdd6c7e8a62124e1d5a3edea7cdf4fc906e5f686c4ff52228a9c6","observation_id":"239c142d-0154-4211-b923-3f0aac081107","resolution":{"observed_at":"2026-08-06T16:27:23.198459Z","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":"2026-08-06T16:27:23.755211Z","title":"Le, Denny Zhou, and Xinyun Chen","venue":null,"work_id":"acb821de-233f-44d3-aa24-9da33a0540bb","year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.216023Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:a4166cc0bacad6f008938d2d44d00ee1342bd7f2bed6661eedd7d374dad33e85","observation_id":"24ce6a44-db06-4a70-a796-fd670669d4f8","resolution":{"observed_at":"2026-08-06T16:27:23.757908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.218587Z","title":"Narasimhan, and Yuan Cao","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.218587Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:2f6b16796b4ce091f39558427f3f335feb72bf53dd4e8e77589624457aa24371","observation_id":"106e4074-0f09-48ee-ad3b-1a9e8d7f9741","resolution":{"observed_at":"2026-08-06T16:27:23.218587Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.02089","last_updated":"2023-10-25T06:23:48Z","snapshot_observed_at":"2026-08-18T12:26:07.723577Z","submitted_at":"2023-10-25T06:23:48Z","title":"LlamaRec: Two-Stage Recommendation using Large Language Models for Ranking","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.02089","snapshot_observed_at":"2026-08-06T16:27:23.221188Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.221188Z"},"links":{"cited_paper":"/paper/2311.02089","citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:838d4a33319c31d0c378a657f16f339292c9773156cad90d420e7338cb99077f","observation_id":"a9f41f87-acf8-4568-ba7f-bdf70d0ea3d4","resolution":{"observed_at":"2026-08-06T16:27:23.221188Z","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":"2026-08-06T16:27:23.223725Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.223725Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:969d7ef67b590a5dddafd68c274fc40cfaebf634afc8f5ffe20b4494142d6a16","observation_id":"b78aab8a-f3f1-47e9-a305-dee0000d9548","resolution":{"observed_at":"2026-08-06T16:27:23.223725Z","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":"2026-08-06T16:27:23.737144Z","title":"Chi, Quoc V","venue":null,"work_id":"9aa01114-fae2-4550-a8a8-99f117dc6281","year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.226128Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:1a8ca673f48bf82c1caf48e569f12c3c177369481af08078a6e86046cf3f4976","observation_id":"d1d8ffe3-564d-4306-8111-11d734f8cbd5","resolution":{"observed_at":"2026-08-06T16:27:23.739711Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.763279Z","title":null,"venue":null,"work_id":"b7fa4516-417c-491a-afe9-c3abd73f1a96","year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.213576Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:94a2180b9bda3b4361be392aa085f10593c9ecce4d5574dacf4d07c0fe1a9c60","observation_id":"10c71a1b-d780-422e-bd43-4d4d9410df3d","resolution":{"observed_at":"2026-08-06T16:27:23.765917Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.15623","last_updated":"2024-02-23T21:58:50Z","snapshot_observed_at":"2026-08-16T14:15:46.487942Z","submitted_at":"2024-02-23T21:58:50Z","title":"Language-Based User Profiles for Recommendation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.15623","snapshot_observed_at":"2026-08-06T16:27:23.231134Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.231134Z"},"links":{"cited_paper":"/paper/2402.15623","citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:aa8a64aea0f4aef07f660413006530a9b8af5d87c276afcaf832e4042098d820","observation_id":"3fb38358-7fcf-4bda-bb76-33bae8f6a4ca","resolution":{"observed_at":"2026-08-06T16:27:23.231134Z","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":"2026-08-06T16:27:23.722617Z","title":null,"venue":null,"work_id":"eca84d6c-136f-4d17-93a3-5785ed1b9fbd","year":2023},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.233552Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:2a9e9f442efb57200380d5deaecfc9e185ea2483a3c68646aeb8291d18c53201","observation_id":"9a519760-a726-4315-ab3e-e4b9b9033488","resolution":{"observed_at":"2026-08-06T16:27:23.725025Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.715110Z","title":"(omitted)","venue":null,"work_id":"683e2340-a718-4b3d-9dd5-cc3a963eddf9","year":2020},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.236015Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:d64b7025d930adac61eafe6b212c83ef7e5f57ce282f3fb43e3ebf895af2d112","observation_id":"f28ca736-411e-4afb-b251-e756e7629a61","resolution":{"observed_at":"2026-08-06T16:27:23.717811Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.729765Z","title":null,"venue":null,"work_id":"1119f43d-b941-4652-9d6d-0f94262f91e6","year":2024},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.228637Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:3a5444e0d67a384d3156a36c9b48b3be797d4a35b8e51264e73cfbdf89a37dfb","observation_id":"d98a62ba-3cae-4c27-8843-78559e0c92a5","resolution":{"observed_at":"2026-08-06T16:27:23.732260Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.708072Z","title":null,"venue":null,"work_id":"fd9e7f6d-0066-467a-af1b-a90fef42dd15","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.238860Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:324d7dde07afc6b1c579d0931c330f4a80de9611fe7213141899c4108be9116a","observation_id":"d8dd70a8-1fc9-46ef-b7bb-e55e4945c018","resolution":{"observed_at":"2026-08-06T16:27:23.710439Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.699050Z","title":null,"venue":null,"work_id":"644ae415-c5f4-4ea5-bb32-3027083fc5c7","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.241586Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:73169ebd416e175fda10e38cae2af1cada0f6490968cf5652c7d5c383da50385","observation_id":"bd4dfca6-fbe2-418c-9332-38cfa79115bb","resolution":{"observed_at":"2026-08-06T16:27:23.703348Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.691517Z","title":"After analyzing the candidate products, I will provide a ranked list indicating the order of preference for the user","venue":null,"work_id":"22c7cc71-a7fa-4ec6-b894-635de0889741","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.244124Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:deed5d0294eac8a4532a4712f06d1599339fefcd60cb3d24e955bb76b1ac09e5","observation_id":"f78cdd7e-0a7f-4739-aae5-611524517e65","resolution":{"observed_at":"2026-08-06T16:27:23.694160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.684246Z","title":null,"venue":null,"work_id":"8e0f1bd2-9dec-4129-b9d7-e2e598e83189","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.246722Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:b98c9f8aa0d2a88c850695434f43eb8266b283380d9e5d162387c7e187add5b7","observation_id":"80a2f84b-077f-42bb-ad3f-2b27420d0e42","resolution":{"observed_at":"2026-08-06T16:27:23.686775Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.676639Z","title":"Now, let 's rank the products","venue":null,"work_id":"e38ff196-0477-4925-b719-0be5a97666d5","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.249266Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:ef14b1f7d5656915ac893c8c7dd3abbe77325a3546d226a09483bdb874b4b93a","observation_id":"dece6d1a-7882-4980-b4c0-75698b836091","resolution":{"observed_at":"2026-08-06T16:27:23.679027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.668735Z","title":"(omitted)","venue":null,"work_id":"9c21b98f-11db-4c0a-85f5-948cf9b7fa65","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.251863Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:967365d595cab04839dbcf9a2a78b31f941be1be3b5ca79774320cbe915fa3a2","observation_id":"32112b5b-8f69-40e3-be1c-e5a374cccdff","resolution":{"observed_at":"2026-08-06T16:27:23.671730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.660627Z","title":"Tyler Perry 's A Madea Christmas","venue":null,"work_id":"836456e2-33c6-4a69-80ef-2dd5089f5571","year":2018},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.254278Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:6fade6389cb925f43a6b557161608b00b6ee8ea912f1f88b3adeefc3b3856875","observation_id":"a5a5cf8f-e08d-4f31-a7b8-5668e2354c5a","resolution":{"observed_at":"2026-08-06T16:27:23.663869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.652888Z","title":"(omitted)","venue":null,"work_id":"d75ba18b-d660-4fee-b0e3-29911bb3f646","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.256930Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:e3171a1a898f99c90f5de2e10423edc22d3fb4111b5566d01aebf8fb6fd8c2d2","observation_id":"816498d5-f505-4829-86d1-35e1b1cbd919","resolution":{"observed_at":"2026-08-06T16:27:23.655503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.645132Z","title":"The Bourne Identity,","venue":null,"work_id":"040b357d-76c9-45e6-ac12-0af260ea8490","year":2018},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.259521Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:5a14acc65025c8acd44ab0699b13d1b76742304d70298feda2897cc448017d76","observation_id":"1a5de39b-b8b9-4b70-8301-cf07d69b7c0d","resolution":{"observed_at":"2026-08-06T16:27:23.647884Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.629846Z","title":null,"venue":null,"work_id":"1ece7f08-c5a8-4da9-83ee-7be3757d88ae","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.264608Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:d454c4ffff2e792a62aa1b7f20752f679de6258135e021523526a65d6c82302a","observation_id":"f2f78459-5f2e-4c1d-b023-32b974f79aa8","resolution":{"observed_at":"2026-08-06T16:27:23.632212Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.622782Z","title":null,"venue":null,"work_id":"e836e8bc-71c1-4ab2-9252-b19731c24f71","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.267138Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:f5368ae5172a405d794e69140d0c495b5ec8f5bb23f44ecf9e134d4379827777","observation_id":"8410056c-30b8-484c-ba62-e4af8bc1fb5e","resolution":{"observed_at":"2026-08-06T16:27:23.625313Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.615284Z","title":"Now, let 's analyze the candidate products:","venue":null,"work_id":"03f13090-6221-45dc-ae84-921f77576224","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.269397Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:a4e0a09c287fb79861584a59a82d165f5a9c2e7d0c819d90eda187d1a61cdec9","observation_id":"c0f61bb4-5ce0-412e-baad-220827b0c8d8","resolution":{"observed_at":"2026-08-06T16:27:23.618118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.607678Z","title":"(omitted)","venue":null,"work_id":"ee741fac-b213-470d-b429-870defe4b904","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.271907Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:876a4662b4e0d6300e3c1e6a01dfe3d07b5161a20ec4d020e88a55db6158b7c2","observation_id":"2a3a0483-9e4d-4885-b98f-2727da1a0d16","resolution":{"observed_at":"2026-08-06T16:27:23.610194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.600608Z","title":null,"venue":null,"work_id":"eefdb497-17c4-4004-b232-e88a2b09e7b2","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.274283Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:6c61a0aac4b71c15dfd87dc7b0927f3b221b440c7213cdf9b5f060218fe9b4bb","observation_id":"2d5af0c3-15ca-449f-92d9-42560903aaa1","resolution":{"observed_at":"2026-08-06T16:27:23.603053Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.593130Z","title":null,"venue":null,"work_id":"17e8a7e3-7586-4006-94a1-0173ee9f4601","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.277017Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:ed5a1ede50639cf7edb4451a5ebbb6697baf56bb65dfc7a51d84140dbe8502fc","observation_id":"263a526a-4606-41b3-b76b-7046ba0cdbb2","resolution":{"observed_at":"2026-08-06T16:27:23.595783Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.586015Z","title":null,"venue":null,"work_id":"3c8c0b36-ddf4-45f1-a041-49eba2a8cee3","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.279636Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:ac3cfd9174610c6eaba01239fde9b5d0c1da28e259f202151e1ea5a2ed3a50a3","observation_id":"7dd2c4bc-9055-4b0c-885a-e51cb73b862b","resolution":{"observed_at":"2026-08-06T16:27:23.588418Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.578316Z","title":"Now, let 's analyze the candidate products:","venue":null,"work_id":"b0507cd3-0b60-4296-8f85-32a62de5eba9","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.282013Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:28042bcddc9b02c5a3c1ac1aca07d29d934ac2e7792e08bb249e182bc3b40546","observation_id":"30c46051-ca4f-4a59-9280-a3fc945ad566","resolution":{"observed_at":"2026-08-06T16:27:23.580736Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.570617Z","title":"It has a compelling description and fits the action/thriller genre","venue":null,"work_id":"83f0b557-fecd-4792-91b0-12918ced7ea0","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.284345Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:ee6113a9edd3c5d639e2d9e0473f02f0c9f56dc2658bcd4df3a5aad931f78e04","observation_id":"7928a3be-70ae-406a-8c48-74f5fdc18644","resolution":{"observed_at":"2026-08-06T16:27:23.573193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.563548Z","title":"Bourne Ultimatum","venue":null,"work_id":"92a5b236-19a8-49b0-afb3-1fb8f663a2ba","year":2018},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.286744Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:c6b2cf5ea007da9d6db371d4240bafba5e0267176621d1dcd2eef3d645d337bf","observation_id":"2c33f0c8-223c-401f-9427-4dc5ea38f339","resolution":{"observed_at":"2026-08-06T16:27:23.565859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.555987Z","title":"(omitted)","venue":null,"work_id":"90f26e5a-89d4-40ea-be9e-8508b52ed23b","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.289497Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:bee716ee53f67978e02d3a6a838186b43f1af2706cd6dd8abd20a6d695dcc4fa","observation_id":"ad27620e-1ae9-4f1a-b27b-b63bcb935c3b","resolution":{"observed_at":"2026-08-06T16:27:23.558835Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.547893Z","title":"# Candidate Products: You will evaluate the following 10 candidate products to determine which ones best align with the user 's preferences for high-rated action and comedy films:","venue":null,"work_id":"0d4af0d0-655a-459c-aec4-cd3a01efea4e","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.291909Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:ec7e575977aed3dddc471239bb67d1c7d24f22088f08eca271513dc8d999002b","observation_id":"99fcad61-3f72-40c9-86e0-c0d633ec184f","resolution":{"observed_at":"2026-08-06T16:27:23.551053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.540252Z","title":"(omitted)","venue":null,"work_id":"7e0da715-cf60-4f76-88d3-c77c1fd57a4e","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.294285Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:0fad397d719ed06db52f04b23b9f09ccba7dc796805cf0112dbbd397d20bccad","observation_id":"0358dd23-456a-4586-80e1-c0a527f0d264","resolution":{"observed_at":"2026-08-06T16:27:23.542755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.532374Z","title":null,"venue":null,"work_id":"eb016790-2208-46bd-801d-8474106ed291","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.296702Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:d9f3c464da2a0084c22975dcabc4ac912793be8e78ad4d7b7de8785b5c7cd793","observation_id":"e6cfa9b2-4946-4c5c-9fc0-9fd43ccb2631","resolution":{"observed_at":"2026-08-06T16:27:23.535312Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.524804Z","title":"(omitted)","venue":null,"work_id":"cf1b36c0-d4bc-42fd-85b9-356802b1b4ff","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.299564Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:4ff5060d91f99fe8fdeb9cbc0f96cbe552455e21718a0ff0f798617a301b2db1","observation_id":"952555f0-ec6f-4428-a3f0-5aee48c25320","resolution":{"observed_at":"2026-08-06T16:27:23.527459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.516896Z","title":"### Answer: Based on the evaluations, the ranked list of candidate products is: **[4, 9, 8, 3, 2]**","venue":null,"work_id":"f50890fd-fc72-4349-bdfc-24f1ead12bd0","year":2018},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.302044Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:a5bba0fe4653f1fb03e57317e344aae9e09a39da06f5472c75ceaa38f0837467","observation_id":"e742053a-1757-4758-b3b2-262b65f6c02b","resolution":{"observed_at":"2026-08-06T16:27:23.519716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.637258Z","title":null,"venue":null,"work_id":"7c198a53-e4a2-426e-967f-8ea1c6b28f7b","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.304575Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:356418a27b359a039cbd9482199934e12be2c8f03331d1aee7a8b073b67b295e","observation_id":"7647914f-c8c0-4c24-b7bb-21229a612c3c","resolution":{"observed_at":"2026-08-06T16:27:23.640003Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.508758Z","title":null,"venue":null,"work_id":"14eb5faa-eded-41df-b903-8972f2f2d183","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.307051Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:5aa2887cfa51688d021464c2568fbdfcde9d5e6572788ba96d9e0a9a403cbcf9","observation_id":"9760541b-febd-48a6-b16e-ccf3a8e9ae27","resolution":{"observed_at":"2026-08-06T16:27:23.511637Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.500888Z","title":"Given these criteria, let 's analyze the candidate products:","venue":null,"work_id":"90afeaa7-5aea-4f07-b29f-11dc5ef69ff5","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":102,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.309529Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:7c4ac26294bc6a1962fa2b69ef333995a01614ba082241ed8648ce82465426a2","observation_id":"6a3df143-fa73-4e56-b404-eadab6d0c96b","resolution":{"observed_at":"2026-08-06T16:27:23.503715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.492842Z","title":"It has a similar action and espionage theme","venue":null,"work_id":"dd72d248-3d3c-4f18-8a87-11b3b1f0177b","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":103,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.311969Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:ee9c14b85f3659b854f929c848b3db2c28503ba7b65a1f4e2965cb33ad3fd005","observation_id":"9b9bc7d8-6d64-44f4-b55c-e53f9cccc4b7","resolution":{"observed_at":"2026-08-06T16:27:23.495582Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.484603Z","title":null,"venue":null,"work_id":"40b9a226-f8cb-4112-8ffd-127ff14a56b6","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":104,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.314390Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:441ff715bd580064575169feb2ae0dfb9eb0625a4e22b541469d2cfd7806c693","observation_id":"37c057d7-1176-4dfd-836d-93151c636d86","resolution":{"observed_at":"2026-08-06T16:27:23.487141Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.476676Z","title":"For instance, if the user enjoys a mix of genres, including comedy or drama, those products could be ranked higher","venue":null,"work_id":"e0f761ab-a10b-4032-979b-d90ba138ca34","year":null},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":105,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.316617Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:df94d192fb0a4f8768a65c1c0269c9f8e506f8ba89c726766861f884a9c7cb6a","observation_id":"491187fe-3d3a-4594-ba13-d88b8e6bf976","resolution":{"observed_at":"2026-08-06T16:27:23.479462Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T16:27:23.468310Z","title":"This would allow for continuous learning and improvement based on user responses","venue":null,"work_id":"4a16a4c6-b27f-405f-9cc9-d49029a11173","year":2018},"citing_paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation","version":1},"reference_index":106,"source":"pdf_text","source_observed_at":"2026-08-06T16:27:23.319123Z"},"links":{"citing_paper":"/paper/2507.13525"},"observation_digest":"sha256:87b28a7cf190be0e9ee23d2bb94e2ff3f0362709086f9e5b886ebd4564cfa305","observation_id":"031360b6-8956-4424-a720-64df9b25dad3","resolution":{"observed_at":"2026-08-06T16:27:23.471220Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.13525","last_updated":"2025-07-17T20:26:00Z","latest_version":1,"primary_category":"cs.IR","snapshot_observed_at":"2026-08-15T09:32:57.512638Z","submitted_at":"2025-07-17T20:26:00Z","title":"Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":73,"verified_exact":1,"verified_fuzzy":25},"total_outbound_references":107},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 100 of 107 outbound references and 0 inbound Pith citation observations for arXiv:2507.13525."}