{"as_of":"2026-08-22T07:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:399374e59fffc8cdecca2daf6f81ac5ff1013c56939efcfcd2d4e8f567ac1578","coverage":[{"denominator":27,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":27,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-27T22:41:03.587563Z","state":"measured"},{"denominator":27,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":27,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/2606.07685/citation-record","integrity":"/paper/2606.07685/integrity","json":"/paper/2606.07685/citation-record.json","paper":"/paper/2606.07685"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T22:41:03.587563Z","title":"Mlaas: Machine learning as a service,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:17538d5e5f7fcb962114ada03ff2e5616db9c3a964c0c9bbce614c2e1338ee4b","observation_id":"51a6c889-8fbe-46eb-af79-54c0c93f5b29","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"A hybrid contextual deep learning model to predict renewable energy generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:e2f8f9a65bd7668fa593f2e26d98f178b6f4659793990f576913af0a799002f8","observation_id":"3870f357-a888-44ed-9de5-abb9d38e9790","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"New Prediction Feature for Hypoglycemia Now Avail- able in Sugar.IQ TM Personal Diabetes Assistant App, Developed by Medtronic and IBM Watson Health,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:094f7f7dec3210fc719f164627da41dfb03e0cffd011e91d956b66a50dae560c","observation_id":"a76b3342-13a4-4f48-a7ed-c16da7bc06a2","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"On delay-sensitive healthcare data analytics at the network edge based on deep learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:4b76c98890b9f51ea30952469c1122bd1394c3f3034211669504346d998506a3","observation_id":"92bcec8a-0d02-4125-b471-8963a9511f16","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"A collaborative service composition approach considering providers’ self-interest and minimal service sharing,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:034161b703576f4e02343f1f8508de3f8ad2a352e61d5d3cbc5425acf666eee5","observation_id":"7a81c851-8ba5-499c-9d0b-ce91a0320c09","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Adaptive composition of machine learning as a service (mlaas) for iot environments,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:216045682e87ea55ae7918b761731d076abdb3ba09460958bfa5846fc07f9b28","observation_id":"c37b0cb7-389a-4caa-9daa-577252fb77ab","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Adaptive and context-aware service composition for iot-based smart cities,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:54332d1c2ae81dbd24b1906571449cd9e4d708b1f67497e4ee43add24e0ba986","observation_id":"428c6416-aee5-41b7-9a20-15c4523a5807","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Long-term iaas provider selection using short-term trial experience,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:ab6b2a274f7672e17a99fd0da005d3bded8ba1a124a413377332555a0871e18c","observation_id":"deadc530-2423-4bfa-9be3-38a4e2ae4a87","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Semantic service substitution in pervasive environments,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:b9772c17fb03d36511772a5d4956670d6e09cd952ac0eb8b503f13bbc3297efd","observation_id":"02b4a48f-b834-459a-873a-274820001e5f","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Tent: Fully test-time adaptation by entropy minimization,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:196e92cad3ce597bc3b2b195dca316c6159e7695c19cf25e76923d57881cc6ae","observation_id":"5ba90d91-f495-41af-a03e-7cdc83132421","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Ttn: A domain-shift aware batch normalization in test-time adaptation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:d47ff213c91876c6ca578bc11b4ed273e51fde76a8fdf61ce89f077d0925f4be","observation_id":"84d93abb-6598-4d50-bc7b-69892a092183","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Improving robustness against common corrup- tions by covariate shift adaptation,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:4f3a18fa92fccc5d7006abc947d0ee883fe494486625985eef327c8e998ea591","observation_id":"726424b0-742a-4930-8aff-219236d4cb27","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Dynamic selection for service composition based on temporal and qos constraints,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:23a76969775555dfcb9e13c7c487f355ad06930f9035a2ecf5fccf3a1336f519","observation_id":"8de088ce-a877-446b-ae29-c0b5f26bff53","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Federated optimization in heterogeneous networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:7d2a5d812062056d5df0752c1a48b23f3ebf3764fca155cb1708a9866a270605","observation_id":"d9b9e65a-8b5c-471b-9646-5261b6620556","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Enabling collaborative test-time adaptation in dynamic environment via federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:1e003b57c0f9f76a8b495c32e49c68d6f85333665aead8cc6eacf3335d27cf61","observation_id":"1b9b41e5-0abb-4858-a37c-a68baadecec5","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"pfedbbn: A personalized federated test-time adaptation with balanced batch normalization for class-imbalanced data,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:ba11996a3940575377258360e6464fff49610352a6d25c140a674ddd7041484e","observation_id":"e0d7925e-62c4-41ce-acd4-fc4672f9bdf7","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Skyml: A mlaas federation design for multicloud- based multimedia analytics,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:3de3696799f7fccfee89f131c271590cc5b3ac17049157775b9a2ac50debc673","observation_id":"2c65df85-0a84-499d-8ff0-8ba6d99a31ba","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Flaas: Federated learning as a service,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:a5ffb228f16ec58d65369d44ab61865f0233eb6a7c84fd1ab1ca2b69368ecaed","observation_id":"ac969b04-29c1-423c-bf7a-ebafc5391d25","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Reinforcement learning controlled adaptive pso for task offloading in iiot edge computing,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:12182c90c83e4a49557563158902f3b1fbd44d56a2f48c36a2702a2876b430af","observation_id":"4e774315-cd79-4004-98af-4d12ab8d9ead","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Semantics-based context-aware dynamic service composition,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:701ad561ae69188313b95bdb346c3ab4288a6e93a690dc2646cb0fa78ed338ff","observation_id":"b3bd6a08-6f40-4101-86d1-8d5e065e42ff","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Adaptive and dynamic service composition using q-learning,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:25bccfb46e801d904a7d1498eff501471d38c11d48e23cfdec5797001c4901e4","observation_id":"c5fb7415-b020-4829-8341-38994a2b9283","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Memo: Test time robustness via adaptation and augmentation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:521969208792d7c537009f49039bb0bc313e8f2fe99621558227111a83315ad9","observation_id":"85ddef80-67e8-4645-a3dc-8f8dce8deeca","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"A layer selection approach to test time adaptation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:d46d0834643538de6210d72dd9eb9cce964c4b5bd978a39d75db455d6c83e0d4","observation_id":"e406fc6d-1e47-4fe9-b4aa-21752279b332","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Layer-wise auto-weighting for non-stationary test- time adaptation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:e584f33ed506841e7a22087bb31c896bf86137bd58ecc39e5a39e33b6a44285c","observation_id":"9d69ca76-2b66-42e5-84fc-4b0f6fd9bd4e","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","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":"2026-06-27T22:41:03.587563Z","title":"Machine learning as a service (mlaas) dataset generator framework for iot environments,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:5628a959e3e8c3d23fd0232087938a07a86610178922db5146a40e822664c1e6","observation_id":"2f4fa3d5-fd08-44ef-bb88-70783ec05f5a","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.02337","last_updated":"2019-06-05T22:23:43Z","snapshot_observed_at":"2026-08-14T16:20:09.671705Z","submitted_at":"2019-06-05T22:23:43Z","title":"MNIST-C: A Robustness Benchmark for Computer Vision","version":1},"cited_work":{"arxiv_id":"1906.02337","doi":"10.48550/arxiv.1906.02337","metadata_source":"pith","pith_arxiv_id":"1906.02337","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"MNIST-C: A Robustness Benchmark for Computer Vision","venue":"cs.CV","work_id":"6f1e3a5b-4845-49b7-bedb-1484b0816d13","year":2019},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"cited_paper":"/paper/1906.02337","citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:634ca40d62908a185133e02247183ce7707424e57538bb8c0177b8ac6420ea6a","observation_id":"0662fad6-7827-471d-8477-9a96fb470ca2","resolution":{"observed_at":"2026-07-02T16:27:09.350911Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T22:41:03.587563Z","title":"Benchmarking neural network robustness to common corruptions and perturbations,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-27T22:41:03.587563Z"},"links":{"citing_paper":"/paper/2606.07685"},"observation_digest":"sha256:1801fc71ae99705dc5c0651bd9cf653d47a208e27b7992c9060027fc49ebc34c","observation_id":"ebd60207-960a-4996-8345-f818b4d6d3b7","resolution":{"observed_at":"2026-06-27T22:41:03.587563Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.07685","last_updated":"2026-06-05T02:52:53Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T06:50:50.650752Z","submitted_at":"2026-06-05T02:52:53Z","title":"Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments"},"reference_resolution":{"displayed":27,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":26,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":27},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2606.07685."}