{"as_of":"2026-08-10T10:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e11e482f8ee3a7925fbbf9f97ea547e725fc4864973167cffcd6090ad29a33b8","coverage":[{"denominator":296,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T02:24:43.554361Z","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":"2026-08-10T06:31:04.303077+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/2607.14371/citation-record","integrity":"/paper/2607.14371/integrity","json":"/paper/2607.14371/citation-record.json","paper":"/paper/2607.14371"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T02:24:34.572443Z","title":"Abril and Robert Plant","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:34.572443Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:2803c6e832e76a1f64413eda3fa167563fcf16f0b83a0d593e63e1544e621e95","observation_id":"e0bc2e1c-0dea-4235-9fbf-54d8d53eaec6","resolution":{"observed_at":"2026-08-02T02:24:34.572443Z","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":"2026-08-02T02:24:34.711323Z","title":"Deciding equivalances among conjunctive aggregate queries","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:34.711323Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:18ff2be70d76a6ce797d639f8cfd5e82089f20c9f3d1730a8e868577d5cdbde8","observation_id":"ba5c68bd-23a8-4737-a8ca-edbe1868964d","resolution":{"observed_at":"2026-08-02T02:24:34.711323Z","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":"2026-08-02T02:24:34.821916Z","title":null,"venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:34.821916Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:044569f395013a193a66732822c2363df91a1bc0ba3052aa084bed1ff5ba135b","observation_id":"96bee69f-f46c-4450-8fda-d8f51f17cd82","resolution":{"observed_at":"2026-08-02T02:24:34.821916Z","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":"2026-08-02T02:24:34.942193Z","title":"Understanding Policy-Based Networking","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:34.942193Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:066d1ea4b2133a55aa8e722ee160c9058a165f29d83a6d4e7e4ade3e73b23dee","observation_id":"2a0e28e7-3aee-4403-8c74-f6db8ce78145","resolution":{"observed_at":"2026-08-02T02:24:34.942193Z","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":"2026-08-02T02:24:35.157295Z","title":null,"venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:35.157295Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:721d4a893ab069addba9c22d31aa18faab7eea7ff1c73aaa48d608b23470f37f","observation_id":"194198fa-ad58-4eb5-a4bb-c1acf65cb850","resolution":{"observed_at":"2026-08-02T02:24:35.157295Z","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":"2026-08-02T02:24:35.235469Z","title":null,"venue":null,"work_id":null,"year":1990},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:35.235469Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:df1ddeddc7f84933824a12abee0e3217486f9ad04130528fcaebbbaff3308aad","observation_id":"5a2998a1-97cc-4c19-b62b-78db375548db","resolution":{"observed_at":"2026-08-02T02:24:35.235469Z","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":"2026-08-02T02:24:35.316616Z","title":"Douglass and David Harel and Mark B","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:35.316616Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:283a77993bf7ce0b6f97d83a9fa89ecf080908b38c734fd3f3d43b3fb91b361e","observation_id":"0d4413ad-00ec-4473-93df-71afb5c9e695","resolution":{"observed_at":"2026-08-02T02:24:35.316616Z","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":"2026-08-02T02:24:35.368482Z","title":null,"venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:35.368482Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:d2c964eb2f952110d5ed864a01554686ff7d7a72ef63a31cfeda8c1330d9ccf8","observation_id":"c56397d6-2f0d-4185-b337-d3d6e69ff1b0","resolution":{"observed_at":"2026-08-02T02:24:35.368482Z","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":"2026-08-02T02:24:35.482348Z","title":null,"venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:35.482348Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:09ef477bd98c0b277ad3a65976b11540eb3d85fdd03f24533c53693206a9d765","observation_id":"c7383977-27bd-423f-99a6-92fb6f674984","resolution":{"observed_at":"2026-08-02T02:24:35.482348Z","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":"2026-08-02T02:24:35.619393Z","title":"Journal of Urban Economics , volume=","venue":null,"work_id":null,"year":1974},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:35.619393Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:01f8d4b948eb397dc93d68548316785be909c8852799ddbb32452917ae089daa","observation_id":"ad8ea5d4-8702-4c5d-ba39-a0d020763c64","resolution":{"observed_at":"2026-08-02T02:24:35.619393Z","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":"2026-08-02T02:24:35.712850Z","title":"2024 , publisher=","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:35.712850Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:e59997a748b24eddc287d50853afaff6b7aa58df43419f44cfc0a008a28eb147","observation_id":"c6bda826-1236-4285-9f97-d6f470e75103","resolution":{"observed_at":"2026-08-02T02:24:35.712850Z","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":"2026-08-02T02:24:35.861441Z","title":"Handbook of regional and urban economics , volume=","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:35.861441Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:45aabca5ac681a1fae6ce9e0e1c37c98128f256d3d13a1d4a29554d97d9686ca","observation_id":"cc9a3885-7e6a-4a0f-a2b7-2a416adc9c39","resolution":{"observed_at":"2026-08-02T02:24:35.861441Z","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":"2026-08-02T02:24:35.933363Z","title":"American Economic Review , volume=","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:35.933363Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:efdde27895f0438ee922a52712819af4ab07d6904ff2fd9cb767b139b3606bc9","observation_id":"097c509b-be22-48cd-91b5-cfaaaecdef00","resolution":{"observed_at":"2026-08-02T02:24:35.933363Z","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":"2026-08-02T02:24:35.957134Z","title":"2015 , publisher=","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:35.957134Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:392ac25caae4171ff06520973889076b93d78890b0d09cae5e993d4864158b0f","observation_id":"530fdc0a-4241-47c5-b109-664a79c69a72","resolution":{"observed_at":"2026-08-02T02:24:35.957134Z","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":"2026-08-02T02:24:35.960430Z","title":"Econometrica , volume=","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:35.960430Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:310020fbb36edf062806dcdc3ce481eccfe2fd2a0b19e80c46c86bda10b8f9b5","observation_id":"0c9e2f3e-402d-47dd-b718-29a32d736b78","resolution":{"observed_at":"2026-08-02T02:24:35.960430Z","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":"2026-08-02T02:24:35.963533Z","title":"Structured Variational Inference Procedures and their Realizations (as incol)","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:35.963533Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:fac553b4eda93bae47b549e2513039e2e9599d469ab385fcda6d2f104b68f77d","observation_id":"12ca8a9c-76fd-494f-b447-472b3bb1b014","resolution":{"observed_at":"2026-08-02T02:24:35.963533Z","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":"2026-08-02T02:24:36.060055Z","title":null,"venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:36.060055Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:1708061fc0f448ddc6e5be8fe0115ec206708261eda6f35a4da4b9c586fecc6d","observation_id":"a86e56ea-8899-4ef9-9115-639e76a1945a","resolution":{"observed_at":"2026-08-02T02:24:36.060055Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.14511","last_updated":"2024-08-28T14:13:41Z","snapshot_observed_at":"2026-08-09T19:52:27.492309Z","submitted_at":"2024-08-25T04:07:18Z","title":"Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.14511","snapshot_observed_at":"2026-08-02T02:24:36.178641Z","title":"arXiv preprint arXiv:2408.14511 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:36.178641Z"},"links":{"cited_paper":"/paper/2408.14511","citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:54075d0363f14c99c631391ceb2f4ce8e151c3a9e3e5ab58a8c9bfc2a45d5680","observation_id":"d5d415da-b896-4aa1-a52d-ff78dba5072d","resolution":{"observed_at":"2026-08-02T02:24:36.178641Z","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":"2026-08-02T02:24:36.303127Z","title":"SIAM Journal on Control and Optimization , volume=","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:36.303127Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:fa63ae6b79dafccbdf8a26bf4628bb04d4310e50e9aad1ba0e4a0e06024de8fa","observation_id":"51f8b7de-a8e5-4195-a67a-6a1651130379","resolution":{"observed_at":"2026-08-02T02:24:36.303127Z","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":"2026-08-02T02:24:36.426678Z","title":"2018 , publisher=","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:36.426678Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:a896ab742ad202c4fa779c73fe69fb6dfe8b5fa1d36c98175bf492a757d6623f","observation_id":"d695a9ce-7a73-4cb2-a9c2-4409a0512816","resolution":{"observed_at":"2026-08-02T02:24:36.426678Z","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":"2026-08-02T02:24:36.585804Z","title":"Advances in neural information processing systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:36.585804Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:0abc1aa38adb4c22a0560676af7de2b460876a3754b2fa0452c39dde0250b3bf","observation_id":"0eeea7c7-ee34-4efb-812f-b2cec6de40a1","resolution":{"observed_at":"2026-08-02T02:24:36.585804Z","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":"2026-08-02T02:24:36.705219Z","title":"arXiv preprint arXiv:2509.26030 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:36.705219Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:805344e271c34585693f08e48734026c03487972a27167a8e8eaca53442c1b8d","observation_id":"ca821c80-3d5e-433b-8aa8-9c7f09ed0aa6","resolution":{"observed_at":"2026-08-02T02:24:36.705219Z","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":"2026-08-02T02:24:36.824011Z","title":"Journal of Machine Learning Research , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:36.824011Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:22780949523f4714afd59acdb2759e58b5efae3405fe815cfe550d8de8c208f6","observation_id":"9ba70309-fc2a-4b25-8666-52e7421a0dcd","resolution":{"observed_at":"2026-08-02T02:24:36.824011Z","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":"2026-08-02T02:24:36.909953Z","title":"Catch me, if you can: Evading network signatures with web-based polymorphic worms","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:36.909953Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:125ba25d1313a8c1f476710da18005d943750b4cb7245c01bf9a340177e48289","observation_id":"de077c63-9b89-4553-8e60-ca630bd05a5a","resolution":{"observed_at":"2026-08-02T02:24:36.909953Z","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":"2026-08-02T02:24:37.035165Z","title":"Catch me, if you can: Evading network signatures with web-based polymorphic worms","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:37.035165Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:824afb53d444986cae04e12fbc8cdec0d1fe9389126bd26abdda839369e05742","observation_id":"9bc6796d-2ebb-42be-b086-2b755dbef749","resolution":{"observed_at":"2026-08-02T02:24:37.035165Z","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":"2026-08-02T02:24:37.157952Z","title":"Catch me, if you can: Evading network signatures with web-based polymorphic worms","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:37.157952Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:27fb3719506fa3b48e484d47be35ea8ffd97229af110a54278bf203cae4f4b8d","observation_id":"61be34f3-c049-41c0-bd9e-51ace6e436a8","resolution":{"observed_at":"2026-08-02T02:24:37.157952Z","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":"2026-08-02T02:24:37.280076Z","title":"Predicate Path expressions","venue":null,"work_id":null,"year":1979},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:37.280076Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:ea8dcde503a3f2d92ee317c0a365d645e51eb84d935d939b65f89594d30ac16e","observation_id":"e78051ea-fa66-44f9-8c15-eb0ee27a3bb6","resolution":{"observed_at":"2026-08-02T02:24:37.280076Z","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":"2026-08-02T02:24:37.398053Z","title":"LOGICS of Programs: AXIOMATICS and DESCRIPTIVE POWER","venue":null,"work_id":null,"year":1978},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:37.398053Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:4bf9d03a01ade4ca249982aba78a8357b8a9be571797f278684f9d75e7054a53","observation_id":"d6d06e21-4a52-4603-b162-234312459eb4","resolution":{"observed_at":"2026-08-02T02:24:37.398053Z","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":"2026-08-02T02:24:37.487286Z","title":"Anisi , title =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:37.487286Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:3c880518b6a1206339da565561788bea2aeef768fcd6daaf7a6bd8d57b06285c","observation_id":"f31877ed-1f34-432b-ae84-b01f40dd298f","resolution":{"observed_at":"2026-08-02T02:24:37.487286Z","resolver_source":null,"status":"parse_uncertain"},"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":"2026-08-02T02:24:37.570852Z","title":"Clarkson","venue":null,"work_id":null,"year":1985},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:37.570852Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:74e848fd35cc5db5cd7979c810f10646bdc774bc5efb423f681901a53bb95762","observation_id":"db370e60-2c2e-4322-a669-289b23a3cabb","resolution":{"observed_at":"2026-08-02T02:24:37.570852Z","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":"2026-08-02T02:24:37.651931Z","title":"Introduction to Bayesian Statistics","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:37.651931Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:4fdb8b45f30c24a9e7aa53b31ecd840e6d710494b58d3138dd04c311c2e6230d","observation_id":"4f3692e4-c53b-4201-a0b0-d4c0a068e6af","resolution":{"observed_at":"2026-08-02T02:24:37.651931Z","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":"2026-08-02T02:24:37.736321Z","title":"CLIFFORD: a Maple 11 Package for Clifford Algebra Computations, version 11","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:37.736321Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:ba28b0645d37cf43ca5ff39a55533dbc6ad04da5665f4f41c85ba29a2c119dcb","observation_id":"d79aee8b-cb98-43d8-bd37-e8c00f418e30","resolution":{"observed_at":"2026-08-02T02:24:37.736321Z","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":"2026-08-02T02:24:37.775979Z","title":"Stats and Analysis","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:37.775979Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:1813595f99203426c7c3d9af46dac1f6b897403a3b918cb83d2213d2845bde3e","observation_id":"9fd6ffb8-4f04-4a18-8a8e-157ecb2587b9","resolution":{"observed_at":"2026-08-02T02:24:37.775979Z","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":"2026-08-02T02:24:37.851823Z","title":"A more perfect union","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:37.851823Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:84e93e3fe88329b9c04cef91a9c2684274527245c7ecb31950571f5ba4cdbef1","observation_id":"4f955724-c18d-470d-8546-00221cdb49ef","resolution":{"observed_at":"2026-08-02T02:24:37.851823Z","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":"2026-08-02T02:24:37.929749Z","title":"The fountain of youth","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:37.929749Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:573828c6b2443daabc9c218c0f5a5ef29436715580bb5d088d8462a8dc8aed61","observation_id":"ccb800de-99d1-4a83-92a5-fc956bf6f5ba","resolution":{"observed_at":"2026-08-02T02:24:37.929749Z","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":"2026-08-02T02:24:38.018964Z","title":"Solder man","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:38.018964Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:81d34031da7ec74f7db6c83c33a2730b49a71266efe9dd3fc6fedd5b8a141c21","observation_id":"4bedc536-c79e-4894-8c68-2e1a5e9afc38","resolution":{"observed_at":"2026-08-02T02:24:38.018964Z","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":"2026-08-02T02:24:38.108474Z","title":"Interview with Bill Kinder: January 13, 2005","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:38.108474Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:182cfd74855e8a52e56d5a0eabc3deecf4217050414544eb7aa17848cc8d2980","observation_id":"12d24164-d82d-40f8-811a-ca77ff15782c","resolution":{"observed_at":"2026-08-02T02:24:38.108474Z","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":"2026-08-02T02:24:38.186778Z","title":"The Enabling of Digital Libraries","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:38.186778Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:8486dd0298f54d787dd6b71eb963fe71dd7341485836197ef8c272e0d26da547","observation_id":"a74be3ea-261e-49ec-9bfa-0f85d70dc32b","resolution":{"observed_at":"2026-08-02T02:24:38.186778Z","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":"2026-08-02T02:24:38.414400Z","title":"(new) Finding minimum congestion spanning trees , journal =","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:38.414400Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:e94ede9f2a6f7c63046e6d592deba5af31b28ce01cf350cca7d2f2f555e090b5","observation_id":"d34d9643-04ca-4b50-b326-e6ac4cde09ae","resolution":{"observed_at":"2026-08-02T02:24:38.414400Z","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":"2026-08-02T02:24:38.627751Z","title":"and Mei, Alessandro , title =","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:38.627751Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:f06521f7bc70eebb88eb629b089418dd5d0f089442d21f670caac6e4b50e902c","observation_id":"3a58a328-76e8-47af-a631-7b1cf8bafe53","resolution":{"observed_at":"2026-08-02T02:24:38.627751Z","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":"2026-08-02T02:24:38.702035Z","title":"and Hutchful, David K","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:38.702035Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:af8eee3f3e06223416f98cc1c4a81fb964484f9ca62ea27263b19e020c7f87e6","observation_id":"0250aad9-c6dc-4f7a-ac0e-102bc5cede2d","resolution":{"observed_at":"2026-08-02T02:24:38.702035Z","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":"2026-08-02T02:24:38.780652Z","title":", title =","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:38.780652Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:456dc1448b55a812cba6e2aaaa5fa32ddad4c490803efd0e7d9096f391619a62","observation_id":"53b9b233-ae58-40c7-9e06-cc521084779f","resolution":{"observed_at":"2026-08-02T02:24:38.780652Z","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":"2026-08-02T02:24:38.867347Z","title":null,"venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:38.867347Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:b82ae2ffdfb4aad474be4dc245e490fe18a35a7bc15d3fc46f50c197692c154a","observation_id":"cc6a0b33-00c3-483b-8411-9e9ab9819f5d","resolution":{"observed_at":"2026-08-02T02:24:38.867347Z","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":"2026-08-02T02:24:38.988451Z","title":"and Rosenberg, Arnold L","venue":null,"work_id":null,"year":1987},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:38.988451Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:67de3620bd72f3e07af9f4560313f53acb69206a68e31dff7848cd5eca4b3937","observation_id":"3b8083f2-7f65-4a5c-ac95-e55fb5c27373","resolution":{"observed_at":"2026-08-02T02:24:38.988451Z","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":"2026-08-02T02:24:39.105808Z","title":"CHI '08: CHI '08 extended abstracts on Human factors in computing systems , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:39.105808Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:dd49099b9b201b9185bd639d3d0c17873ce88d07be63858e6c67b63f56fa7aa9","observation_id":"ec0cb212-f285-41a2-b646-9b56ee8237e3","resolution":{"observed_at":"2026-08-02T02:24:39.105808Z","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":"2026-08-02T02:24:39.181901Z","title":"Algorithms for Closest-Point Problems (Computational Geometry) , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:39.181901Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:62705274268959c8e2b83d9c03b7faddb0be165210f07cac857327e651a3f648","observation_id":"1a61bdbe-ef0e-4892-86cb-369e84c83311","resolution":{"observed_at":"2026-08-02T02:24:39.181901Z","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":"2026-08-02T02:24:39.313878Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:39.313878Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:b0be1c9f6687d2a3092af01994db84950550ff8863d8c8a763784d86216a460e","observation_id":"9146a563-44eb-4793-b642-390790bdc43c","resolution":{"observed_at":"2026-08-02T02:24:39.313878Z","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":"2026-08-02T02:24:39.401897Z","title":"2004 , isbn =","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:39.401897Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:8bdb916fea90ff1f3d48c49803dd219a217479ac0860194089214a5932b9cf9c","observation_id":"5909187d-bb65-45a6-b5d2-d41c29828a3f","resolution":{"observed_at":"2026-08-02T02:24:39.401897Z","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":"2026-08-02T02:24:39.488226Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:39.488226Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:f4018f3cbf01a5d9a70bb4b7127f28b938fd881a6484b5fc70694a3f0ce9f3c7","observation_id":"34c3a016-8a7c-40e9-9091-72759690ccac","resolution":{"observed_at":"2026-08-02T02:24:39.488226Z","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":"2026-08-02T02:24:39.615831Z","title":", title =","venue":null,"work_id":null,"year":1986},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:39.615831Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:9b6e3e4670ce67bdff0e50deb329db95e9492c9250b33e376ed00ae25e1e27db","observation_id":"def80af0-fcc5-47bd-8f46-5113f64a3038","resolution":{"observed_at":"2026-08-02T02:24:39.615831Z","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":"2026-08-02T02:24:39.701599Z","title":null,"venue":null,"work_id":null,"year":1981},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:39.701599Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:c6b42d5c9baab59a2447a68eda06739fdac73cb7cc0f1b05e58b7a79b938d01b","observation_id":"2cbf6020-afeb-4211-89f6-f3c5fb85a457","resolution":{"observed_at":"2026-08-02T02:24:39.701599Z","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":"2026-08-02T02:24:39.786141Z","title":"E-commerce and cultural values , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:39.786141Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:fae2cd1acafd019a1d675d5d00d3919008b736fe3819f0cce1e7bd8bb68b47de","observation_id":"63ba7e40-43ea-4612-b882-f72b7b2f7291","resolution":{"observed_at":"2026-08-02T02:24:39.786141Z","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":"2026-08-02T02:24:39.871097Z","title":"E-commerce and cultural values , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:39.871097Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:e0a1d1830208b3b87c78b4c1cc14ec64b4fc9d66787f9c771e367aa139df8590","observation_id":"50bb429f-3eb8-487e-991f-b87062714f73","resolution":{"observed_at":"2026-08-02T02:24:39.871097Z","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":"2026-08-02T02:24:39.960659Z","title":"Chapter 9 , booktitle =","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:39.960659Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:712decf5402ebf99ed258c6217fbf26abda309c30b610ed82ceabc7205fcbbb3","observation_id":"da597a44-c567-421a-9533-8e9a31415d1c","resolution":{"observed_at":"2026-08-02T02:24:39.960659Z","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":"2026-08-02T02:24:40.051629Z","title":"E-commerce and cultural values , editor =","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:40.051629Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:38f7475749e6be3b347b30b5bb7f355d8641b2463e7edae6f7e05cf0ae5774b9","observation_id":"a748ea9a-c6aa-40a8-92c6-90add1b6f79a","resolution":{"observed_at":"2026-08-02T02:24:40.051629Z","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":"2026-08-02T02:24:40.103540Z","title":"E-commerce and cultural values - (InBook-num-in-chap) , chapter =","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:40.103540Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:ad0c4e3be0a41059e2330f74b006f08bb69d7f5fdc8103350cb715e51566bced","observation_id":"8dad001f-be06-4ee7-b6be-50f817a9e9c5","resolution":{"observed_at":"2026-08-02T02:24:40.103540Z","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":"2026-08-02T02:24:40.183363Z","title":"E-commerce and cultural values (Inbook-text-in-chap) , chapter =","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:40.183363Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:dc2a2efb68b35a40a90a0504b122b4f5ee81eb628ba6b35dd611cbe711d377dd","observation_id":"6b19ea1a-0350-40e7-8add-607bb2208a65","resolution":{"observed_at":"2026-08-02T02:24:40.183363Z","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":"2026-08-02T02:24:40.246612Z","title":"E-commerce and cultural values (Inbook-num chap) , chapter =","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:40.246612Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:f9df56b883f1ff845688421e2982a6231e4711720b37ef1a09cd58bc92d7e7b8","observation_id":"2d6709ed-3619-4407-a841-729953fd492a","resolution":{"observed_at":"2026-08-02T02:24:40.246612Z","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":"2026-08-02T02:24:40.352984Z","title":"Microelectron","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:40.352984Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:af62463479d66e491f1d8e46a15739571a20e0906c593f34c6e6746ddac12e47","observation_id":"08f9716f-3e0b-40c2-bace-12a8e6d1e8ef","resolution":{"observed_at":"2026-08-02T02:24:40.352984Z","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":"2026-08-02T02:24:40.415583Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:40.415583Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:eacc98bb29a8cc8d3d00e15c4c78110fb24e4b4a29981ca6500cd2bb97006d4e","observation_id":"f1d987a3-4e1f-42be-8a0b-a13e04af362d","resolution":{"observed_at":"2026-08-02T02:24:40.415583Z","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":"2026-08-02T02:24:40.418125Z","title":null,"venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:40.418125Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:83a1da7e37cc9368ec362198ce9e01e3988f65ca4d199194727c645bcd58d054","observation_id":"5421377f-3971-4376-af26-7ba5fc7ddfe5","resolution":{"observed_at":"2026-08-02T02:24:40.418125Z","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":"2026-08-02T02:24:40.483323Z","title":null,"venue":null,"work_id":null,"year":1972},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:40.483323Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:9fb33cbf36b1a56a8ae40a68037bb15d61bdef015bc28774f2f90cf48a2dd736","observation_id":"1c9b7974-c136-43cb-94c1-208c86f8e308","resolution":{"observed_at":"2026-08-02T02:24:40.483323Z","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":"2026-08-02T02:24:40.580528Z","title":"History of programming languages I (incoll) , editor =","venue":null,"work_id":null,"year":1981},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:40.580528Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:5a8cb0460231c00ca1deb6a4ab61dcba5eae9063c39e67d3d74efe9ccb8b7887","observation_id":"184bc4f6-7bec-4831-a679-83a1490fbb3d","resolution":{"observed_at":"2026-08-02T02:24:40.580528Z","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":"2026-08-02T02:24:40.640199Z","title":", title =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:40.640199Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:4cfd9d26f01b1c20aaaf010a8abaea47144fc78411247bdb4b2226475329dc4f","observation_id":"09281022-844a-4493-98c5-981214b5ed85","resolution":{"observed_at":"2026-08-02T02:24:40.640199Z","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":"2026-08-02T02:24:40.759311Z","title":", title =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:40.759311Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:c8d775251112e7d2792590205632e8a9eb083198c60ac3ace17cca33c46b97b7","observation_id":"730bec6b-602d-465e-9f13-828a99f97314","resolution":{"observed_at":"2026-08-02T02:24:40.759311Z","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":"2026-08-02T02:24:40.811006Z","title":", title =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:40.811006Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:02b10f9f939467290f1451a36f2767fe220dc6d63532c99f33676b897182dac9","observation_id":"b836279c-e17b-4a38-bce9-334881570c35","resolution":{"observed_at":"2026-08-02T02:24:40.811006Z","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":"2026-08-02T02:24:40.922221Z","title":"and Golden, Donald G","venue":null,"work_id":null,"year":1990},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:40.922221Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:78b328d3ecc0ac70baca5a6b15cc973dfe87ad4f58d9cac70986d37e376a5a40","observation_id":"1e748ef4-80da-462a-adf7-2100010fe3b2","resolution":{"observed_at":"2026-08-02T02:24:40.922221Z","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":"2026-08-02T02:24:41.042763Z","title":"The analysis of linear partial differential operators","venue":null,"work_id":null,"year":1985},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:41.042763Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:6bbb49a6834dc1d0654177e5c12cc9330912ca3ee47680c39af2f41dc3f8c1a6","observation_id":"5b5a504c-ec2a-446d-b0c7-7b4b111b285e","resolution":{"observed_at":"2026-08-02T02:24:41.042763Z","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":"2026-08-02T02:24:41.125081Z","title":"IEEE\", address =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:41.125081Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:e40fd2161c4fd016d304b2c5cfbe417620e372292124075512f3fb8635da0563","observation_id":"1018afaa-63fb-447f-a6b8-a4fab8ba627f","resolution":{"observed_at":"2026-08-02T02:24:41.125081Z","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":"2026-08-02T02:24:41.228551Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:41.228551Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:0852c39861261206bc6c308b1d8270ae3ffebe76c3d23d1eb328c71b1eea0c24","observation_id":"415cc161-24c3-468a-b812-bf7dd0dc6a24","resolution":{"observed_at":"2026-08-02T02:24:41.228551Z","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":"2026-08-02T02:24:41.314843Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:41.314843Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:9188d331dda3c72f256d9cc2768fb4b0ba6ddb4a039b6d32043abb6b05f79da4","observation_id":"d9ab1c76-1ee2-45ad-930c-b5e31c02225b","resolution":{"observed_at":"2026-08-02T02:24:41.314843Z","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":"2026-08-02T02:24:41.430065Z","title":"ACM\", address =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:41.430065Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:51b2ac9d2d422a406b2cd7320c0836b58e4ba9a26eada2c4f6542b5ae69fb23b","observation_id":"a33869db-b0a6-48cd-8e82-39e981cd41d5","resolution":{"observed_at":"2026-08-02T02:24:41.430065Z","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":"2026-08-02T02:24:41.517644Z","title":"8 (Special Issue on Sensor Networks)","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:41.517644Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:ca1108ed50ac36a6c319a084960bea1cd37c94188f291a737e354f8a3a953a0a","observation_id":"281ed220-8b0e-4545-ac1b-56b009f8b9ab","resolution":{"observed_at":"2026-08-02T02:24:41.517644Z","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":"2026-08-02T02:24:41.607158Z","title":"Natarajan and M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:41.607158Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:beb369eac7b0e1e16081a9c4908829c28bf61fca034f1c088bba2c42d360d9ef","observation_id":"d5f8052c-8165-4301-aa2d-c2d114c96c3e","resolution":{"observed_at":"2026-08-02T02:24:41.607158Z","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":"2026-08-02T02:24:41.717063Z","title":"Tzamaloukas and J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:41.717063Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:5cf0256c9bbe2095b4bd04307d7138c212248074d953943b0e76542a7601eaf2","observation_id":"ba74cfe2-cc03-47f1-8834-cf427c1f9569","resolution":{"observed_at":"2026-08-02T02:24:41.717063Z","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":"2026-08-02T02:24:41.776120Z","title":"Zhou and J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:41.776120Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:a3702b13d20f79cd3274141ce3e8180a1769940325939564262b6961abca8023","observation_id":"03570c5d-17ec-4264-9763-2e6ab859bfa0","resolution":{"observed_at":"2026-08-02T02:24:41.776120Z","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":"2026-08-02T02:24:41.885071Z","title":"Mapping Powerlists onto Hypercubes","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:41.885071Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:c659972dbc20cd693bf1aae2e5307da99cea73529af893b4a9f927cd05666c94","observation_id":"4a754bf0-d705-4ac9-83bd-870903bd53cd","resolution":{"observed_at":"2026-08-02T02:24:41.885071Z","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":"2026-08-02T02:24:41.971288Z","title":"Automatic Parallelization for Distributed-Memory Multiprocessing Systems","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:41.971288Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:571d7bfc1865c857ad0373144d855cce282a5b43e7e701d2a818121994790617","observation_id":"85dd61e1-acb0-4d8c-82c6-d8318bba0d4e","resolution":{"observed_at":"2026-08-02T02:24:41.971288Z","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":"2026-08-02T02:24:42.099032Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:42.099032Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:22de3524e18766cba8182eaddeb24c1cea5d42df1e2ecee017d78b43658e0757","observation_id":"925dfb30-456d-4061-9260-102f987c1e79","resolution":{"observed_at":"2026-08-02T02:24:42.099032Z","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":"2026-08-02T02:24:42.199499Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:42.199499Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:7230bdaf521f8be4bff4b96369683bb994e8077eb74131421bebf0b46130a269","observation_id":"785b053f-6963-4c52-9217-26b456b7d43a","resolution":{"observed_at":"2026-08-02T02:24:42.199499Z","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":"2026-08-02T02:24:42.248788Z","title":"Heering and P","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:42.248788Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:1d8b7143b81377815e5762876dd12377fba3d6db60ee17787118b6613c9fff9d","observation_id":"e735db71-9ab1-42f4-bf15-2b9dd9d41a5e","resolution":{"observed_at":"2026-08-02T02:24:42.248788Z","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":"2026-08-02T02:24:42.344989Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":86,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:42.344989Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:42671907e2e1004c354e584c05458734ae3ea7de1370a73cb19c8b578bd812f2","observation_id":"1a915f52-25dd-409f-bcdd-6f1e0b3c2747","resolution":{"observed_at":"2026-08-02T02:24:42.344989Z","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":"2026-08-02T02:24:42.399649Z","title":"Korach and D","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:42.399649Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:e9fec75264c1fde93defa612ae87721fefbd8245611aaa05dfee6c316f39e5c0","observation_id":"f6969ee4-1e29-43b1-801f-563df0cb1726","resolution":{"observed_at":"2026-08-02T02:24:42.399649Z","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":"2026-08-02T02:24:42.510157Z","title":": A Document Preparation System","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":88,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:42.510157Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:dbab9d2666250a3ddc740812080160b389497e2491b0faf03bd6e9ff8be8be6f","observation_id":"5d3a4b47-9abb-45f2-b7f2-e7019d526b72","resolution":{"observed_at":"2026-08-02T02:24:42.510157Z","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":"2026-08-02T02:24:42.586937Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":89,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:42.586937Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:09ec6796ee44c370ac124a230d2e4355823fa3411dafed59f40c3fe45dc1ae9e","observation_id":"8acc6fd5-8b22-471c-a4dd-a72216cd23e9","resolution":{"observed_at":"2026-08-02T02:24:42.586937Z","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":"2026-08-02T02:24:42.655251Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:42.655251Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:2521a445e4ac182d984a07c28f43c90c56c810bc6ea415d05a389e1fd67262a4","observation_id":"12b7cf3e-dbfa-42af-aa57-1d22602fb48c","resolution":{"observed_at":"2026-08-02T02:24:42.655251Z","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":"2026-08-02T02:24:42.708714Z","title":"and Abdelzaher, Tarek F","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:42.708714Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:907c01c9fc3f8f19b2626971b882d11b045826e7478a44ca7d30d20375318508","observation_id":"3fb30cc5-f213-4103-8c5f-29efa6c42551","resolution":{"observed_at":"2026-08-02T02:24:42.708714Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.02716","last_updated":"2024-02-05T04:25:24Z","snapshot_observed_at":"2026-08-09T14:47:51.558187Z","submitted_at":"2024-02-05T04:25:24Z","title":"Understanding the planning of LLM agents: A survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.02716","snapshot_observed_at":"2026-08-02T02:24:42.797794Z","title":"arXiv preprint arXiv:2402.02716 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":92,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:42.797794Z"},"links":{"cited_paper":"/paper/2402.02716","citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:846537755ebadef4436302eaaff82c0d9de4e6b8403fa2e4f3fd648d20fcf0ad","observation_id":"14f6beed-2f5b-4a9d-8e36-248afbba188b","resolution":{"observed_at":"2026-08-02T02:24:42.797794Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10490","last_updated":"2025-06-29T05:43:22Z","snapshot_observed_at":"2026-08-01T14:47:14.023229Z","submitted_at":"2024-07-15T07:30:28Z","title":"Learning Dynamics of LLM Finetuning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.10490","snapshot_observed_at":"2026-08-02T02:24:42.877960Z","title":"arXiv preprint arXiv:2407.10490 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":93,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:42.877960Z"},"links":{"cited_paper":"/paper/2407.10490","citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:2d437248db09eea6b1f8ac3d5c48c38eaae26352289194ac0308aa52045d8fa1","observation_id":"bf00b194-6eb2-423c-b23f-bb76c5b8a4bf","resolution":{"observed_at":"2026-08-02T02:24:42.877960Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.16852","last_updated":"2025-02-24T05:24:52Z","snapshot_observed_at":"2026-08-07T17:54:16.806953Z","submitted_at":"2025-02-24T05:24:52Z","title":"Improving LLM General Preference Alignment via Optimistic Online Mirror Descent","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.16852","snapshot_observed_at":"2026-08-02T02:24:42.953753Z","title":"arXiv preprint arXiv:2502.16852 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":94,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:42.953753Z"},"links":{"cited_paper":"/paper/2502.16852","citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:06339163e665e4cf4fba910d46b83ccc7317531d8c300826c0190fb167f7e338","observation_id":"c42f0dc0-1a24-4b14-b95b-906cda524044","resolution":{"observed_at":"2026-08-02T02:24:42.953753Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.02080","last_updated":"2022-07-21T07:44:13Z","snapshot_observed_at":"2026-07-30T03:45:35.558793Z","submitted_at":"2021-11-03T09:12:33Z","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.02080","snapshot_observed_at":"2026-08-02T02:24:43.029666Z","title":"arXiv preprint arXiv:2111.02080 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":95,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:43.029666Z"},"links":{"cited_paper":"/paper/2111.02080","citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:7f16b964bb05dabfaf8672b2ef3e0edf00ba2632496b792f52683c0e7995cea4","observation_id":"de5e4062-061b-4f76-b3b8-40908c4f6a8e","resolution":{"observed_at":"2026-08-02T02:24:43.029666Z","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":"2026-08-02T02:24:43.110116Z","title":"Advances in neural information processing systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":96,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:43.110116Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:436a1c7d1c82e025354d90cb9809ba78d3540548e8dab73b1e7dbee7698c1117","observation_id":"81182c35-9455-444f-89c0-ae0089c595fd","resolution":{"observed_at":"2026-08-02T02:24:43.110116Z","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":"2026-08-02T02:24:43.183793Z","title":"IEEE Transactions on Audio, Speech and Language Processing , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":97,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:43.183793Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:74164f941ad2103dfebe32d807a96339e8f88a3fe629275a07373a51367a30fa","observation_id":"617cbeab-3d55-4b7a-b1a3-904f3992e0e9","resolution":{"observed_at":"2026-08-02T02:24:43.183793Z","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":"2026-08-02T02:24:43.205483Z","title":"The Eleventh International Conference on Learning Representations , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":98,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:43.205483Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:d6ecc58185f3a76a83457c2bedee2e9d957a53892d80a56d700f904068537531","observation_id":"871d7ac4-8137-45f4-b626-718b8de09615","resolution":{"observed_at":"2026-08-02T02:24:43.205483Z","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":"2026-08-02T02:24:43.227726Z","title":"2025 , institution=","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":99,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:43.227726Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:96ed93adb9be04ab9cae0c05ec54d7f7f27f5a0cf9921615497f4c7b2ffe94cc","observation_id":"598b85fe-7ea5-4ff1-bb26-30f4eb15b202","resolution":{"observed_at":"2026-08-02T02:24:43.227726Z","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":"2026-08-02T02:24:43.254326Z","title":"SIAM Journal on Control and Optimization , volume=","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":100,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:43.254326Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:75e44b846f45c8c3754d84328e13e2a2775db43624960abd5b9d7237b35a5826","observation_id":"135244c6-93db-4b57-b373-d561b2936a81","resolution":{"observed_at":"2026-08-02T02:24:43.254326Z","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":"2026-08-02T02:24:43.299535Z","title":"Proceedings of the National Academy of Sciences , volume=","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":101,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:43.299535Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:e4f2766f1fefe67facc1521b4aed405383a97bb1de4b7df23b8ae179410a21d6","observation_id":"de8f1d36-3b57-479a-aeec-a1462f733602","resolution":{"observed_at":"2026-08-02T02:24:43.299535Z","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":"2026-08-02T02:24:43.378652Z","title":"arXiv preprint arXiv:2511.00674 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":102,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:43.378652Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:21dd6408061bc49f63b40f0c5c984a4a1e48a450d920fa1bab462df64762ad31","observation_id":"39c7a193-0891-40b8-a0ac-2a88248cf4be","resolution":{"observed_at":"2026-08-02T02:24:43.378652Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.00522","last_updated":"2024-07-17T08:55:59Z","snapshot_observed_at":"2026-08-08T22:56:38.752447Z","submitted_at":"2024-03-31T01:41:57Z","title":"Minimum-Norm Interpolation Under Covariate Shift","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.00522","snapshot_observed_at":"2026-08-02T02:24:43.479028Z","title":"arXiv preprint arXiv:2404.00522 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":103,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:43.479028Z"},"links":{"cited_paper":"/paper/2404.00522","citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:01687104155f616126179ad9338b6ad1aad20b5410ac7641ef0481c43a88046a","observation_id":"5a0be415-1c4c-4fb3-88dc-dd93db2b96fb","resolution":{"observed_at":"2026-08-02T02:24:43.479028Z","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":"2026-08-02T02:24:43.554361Z","title":"International conference on machine learning , pages=","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","version":1},"reference_index":104,"source":"arxiv_source","source_observed_at":"2026-08-02T02:24:43.554361Z"},"links":{"citing_paper":"/paper/2607.14371"},"observation_digest":"sha256:20f3e8c92f5d7c84d42958e4d5c3ee48e6ef72e1ee2b933733777aca18a40b67","observation_id":"738ed4b7-8a8e-45b4-9fe2-c746da96312d","resolution":{"observed_at":"2026-08-02T02:24:43.554361Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.14371","last_updated":"2026-07-15T21:17:42Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T13:04:16.701334Z","submitted_at":"2026-07-15T21:17:42Z","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":99,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":296},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 100 of 296 outbound references and 0 inbound Pith citation observations for arXiv:2607.14371."}