{"as_of":"2026-08-09T18:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f608d13eba0d3dc81b93f1409e6370d85ba80e141156fec0fd581c24e2f84ee7","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:00:31.923370Z","state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2608.06188/citation-record","integrity":"/paper/2608.06188/integrity","json":"/paper/2608.06188/citation-record.json","paper":"/paper/2608.06188"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1021/es300145v","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:00:33.314136Z","title":"Marginal Emissions Factors for the U.S. Electricity System","venue":null,"work_id":"9c9253b8-5448-45ac-b454-ee8c97cbb7c3","year":2012},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:28.925594Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:2217a63e4826b52204741f81de71f28f80873c089e38bec98bcc66159d947b9b","observation_id":"47448fd7-2e8b-49dc-a41a-a3291721df11","resolution":{"observed_at":"2026-08-07T13:00:33.426997Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:00:35.940069Z","title":"Marginal Operating Emissions Rate (MOER): methodology and validation","venue":null,"work_id":"c67d05b2-b983-4cd5-a0d1-e7f527e921ad","year":2022},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:28.979003Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:2cd2269a9d186fa576f0f487c3693329f9e4f8653f9617197393e52642bd669d","observation_id":"1455f23e-b40d-4eda-b93d-0221111d4ee0","resolution":{"observed_at":"2026-08-07T13:00:36.039428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:00:35.689276Z","title":"An Introduction to the Bootstrap","venue":null,"work_id":"eb1b1420-96a2-4880-b890-49ed5e32f30c","year":1993},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:29.080724Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:65ed343510d844b65d0079b517577aa768ae1e73ec1c35d30098dda9841ad138","observation_id":"e7bc1a16-3dda-438c-bfbb-1c271882c5e5","resolution":{"observed_at":"2026-08-07T13:00:35.789109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:00:29.193102Z","title":"Carbon-Aware Computing for Datacenters","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:29.193102Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:b47b05fad3fc7325b97387094d4ce9c6993c31b7e7e1dbb15403264b515f7db4","observation_id":"ae05443b-d64e-4ea9-a6e3-975851def28e","resolution":{"observed_at":"2026-08-07T13:00:29.193102Z","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":"2026-08-07T13:00:29.305345Z","title":"Let’ s Wait Awhile: How Temporal Workload Shifting Can Reduce Carbon Emissions in the Cloud","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:29.305345Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:ad354809f0f5d05093494ff144b4f6bc52f31c5971edbf142bf243cb29a64a35","observation_id":"fffdd508-c9fa-485a-88b1-fb33357372b7","resolution":{"observed_at":"2026-08-07T13:00:29.305345Z","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":"2026-08-07T13:00:29.468536Z","title":"Chasing Carbon: The Elusive Environmental Footprint of Computing","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:29.468536Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:3b6276e807d80c6ee0c9ea51a82bdb6d21be89457a24bd19be7d6612ed50a266","observation_id":"e82bac1f-378a-4cf8-bdb2-2985f87b497d","resolution":{"observed_at":"2026-08-07T13:00:29.468536Z","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":"2026-08-07T13:00:29.582641Z","title":"Ecovisor: A Virtual Energy System for Carbon-Efficient Applications","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:29.582641Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:2e67b44df72769b50af4ffdba9bbdf9a5609de354065aeb8c3d41f73f317874c","observation_id":"7ae5d640-01ff-46da-af9d-1ca92e4fd04e","resolution":{"observed_at":"2026-08-07T13:00:29.582641Z","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":"2026-08-07T13:00:29.681481Z","title":"CarbonScaler: Leveraging Cloud Workload Elasticity for Optimizing Carbon-Efficiency","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:29.681481Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:91bc5b686d9364a54c147a26364c2a98c32ec2606f0f1281be8693fa4a4b72ea","observation_id":"c90662ff-b400-457c-9fe5-dcf41e3a837c","resolution":{"observed_at":"2026-08-07T13:00:29.681481Z","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":"2014.23082","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:00:33.961427Z","title":"Greening Geographical Load Balancing","venue":null,"work_id":"974cbbdb-66d1-42d2-b0bf-6ea8226aac15","year":2011},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:29.766712Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:f90cccdb885479e832d589cf83110a7d3c01557de41ed3a1bc7335c2553a03ec","observation_id":"39bf7065-21dc-4ee0-97d6-e9ea9fc99b2b","resolution":{"observed_at":"2026-08-07T13:00:34.011615Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:00:29.838041Z","title":"Real-Time Carbon Accounting Method for the European Electricity Markets","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:29.838041Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:82c649bc4d4342b3c221f1f98084de33e7befcc1b8ce1e8ff5682b92c40d7080","observation_id":"2ac576d9-9d38-478a-be79-073ac1e8aa63","resolution":{"observed_at":"2026-08-07T13:00:29.838041Z","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":"2026-08-07T13:00:29.921396Z","title":"Power Hungry Processing: Watts Driving the Cost of AI Deployment?","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:29.921396Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:be196770a85b49132277d0e8e812dd048e5fa3f98cc0825237447eb25cca0113","observation_id":"63255441-7677-48d0-8005-a96fe3940d50","resolution":{"observed_at":"2026-08-07T13:00:29.921396Z","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":"2026-08-07T13:00:29.999001Z","title":"Clover: Toward Sustainable AI with Carbon-Aware Machine Learning Inference Service","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:29.999001Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:7cd3716fc6d77cedecd35a59e617d4c4708a9d32298db1b75b2b19a1df58fb29","observation_id":"e03550cb-6947-442a-8e01-021fd2261017","resolution":{"observed_at":"2026-08-07T13:00:29.999001Z","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":"10.18653/v1/2024.emnlp-main.1215","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:00:33.086577Z","title":"Sprout: Green Generative AI with Carbon-Efficient LLM Inference","venue":null,"work_id":"90e671a1-f4fc-4019-ada9-10610718e860","year":2024},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:30.112490Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:f2cef6000e3d950d6f3d0512df4a08e88169054c203833460cdb06c54aef9360","observation_id":"ba88a26e-6969-4f5f-b3e4-98aae1bed28a","resolution":{"observed_at":"2026-08-07T13:00:33.183484Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.48550/arxiv.2408.00741","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:00:32.898709Z","title":"DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency","venue":null,"work_id":"a1459290-d570-4439-bf24-271fde8a6ba3","year":2025},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:30.239349Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:333e0e249071926a2901965db61b011ca6618d47622a64ec25614d492dc6960c","observation_id":"d3fa7796-cfc8-47ce-9837-7dde5963efa4","resolution":{"observed_at":"2026-08-07T13:00:32.984354Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:00:30.318532Z","title":"Towards Environmentally Equitable AI via Geographical Load Balancing","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:30.318532Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:dd1908ffc63935abe4dbb831bb8eb0f1e4c77b41a35473adaf7355e5128e761b","observation_id":"69785945-e45f-46f1-aa25-0a6aafd38773","resolution":{"observed_at":"2026-08-07T13:00:30.318532Z","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":"2026-08-07T13:00:30.407480Z","title":"Energy and Policy Considerations for Deep Learning in NLP","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:30.407480Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:187a86995852909a6803b1bcbad57b676c007a371342c72f863c261ffc7fc603","observation_id":"1a303a26-20db-44d3-a460-9ee8d61c5bee","resolution":{"observed_at":"2026-08-07T13:00:30.407480Z","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":"2026-08-07T13:00:30.488926Z","title":"Measuring the Carbon Intensity of AI in Cloud Instances","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:30.488926Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:61adcf1361e50f0529162863e38f27f18d0858cbd8192cf64d4040acb153b060","observation_id":"732dad1d-95e2-4600-bbf0-62194ce8a950","resolution":{"observed_at":"2026-08-07T13:00:30.488926Z","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":"2026-08-07T13:00:30.590547Z","title":"Estimating Marginal CO2 Emissions Rates for National Electricity Systems","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:30.590547Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:4d976408c92cef6d5f47b18593f849d229c7c2b20f07cb1cecac879817fa0247","observation_id":"a9b505ca-63f0-44c3-bb9f-ebe2f343ea95","resolution":{"observed_at":"2026-08-07T13:00:30.590547Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.10350","last_updated":"2021-04-23T14:26:29Z","snapshot_observed_at":"2026-07-06T11:02:18.405330Z","submitted_at":"2021-04-21T04:44:25Z","title":"Carbon Emissions and Large Neural Network Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.10350","snapshot_observed_at":"2026-08-07T13:00:30.630891Z","title":"Carbon Emissions and Large Neural Network Training","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:30.630891Z"},"links":{"cited_paper":"/paper/2104.10350","citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:d5374caf8fae7fd0ffc7887229c72b989b57055bb2048f84c48ba15388b5fd0c","observation_id":"11e2b943-2064-4579-8160-5e08f3ad9e45","resolution":{"observed_at":"2026-08-07T13:00:30.630891Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:00:35.438647Z","title":"TowardstheSystematic Reporting of the Energy and Carbon Footprints of Machine Learning","venue":null,"work_id":"c8ee0b0e-ecbf-4400-8452-c8b26d0c2b2c","year":2020},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:30.788875Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:7db995520b7cfab73e4d7ca193d521c77021f06f92979cc0007ecfa65d90ae80","observation_id":"5646786f-c0a6-4687-a2ff-6597f600aa71","resolution":{"observed_at":"2026-08-07T13:00:35.580513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.48550/arxiv.2606.15050","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:00:32.622887Z","title":"Solyx AI Grid: Hardware-Telemetry-Aware Routing Across Geographically Distributed GPU Clusters","venue":null,"work_id":"2ac3c24e-23f9-4e38-b3cc-166f1a628681","year":2026},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:30.866693Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:df08db180ded9825a6beb8b3af46b72eadcc5b0b1830f7e6da32a6c72e413845","observation_id":"43a98908-a110-409e-81be-d3c40d812166","resolution":{"observed_at":"2026-08-07T13:00:32.686524Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.05043","last_updated":"2025-03-15T19:26:40Z","snapshot_observed_at":"2026-08-09T07:19:40.287753Z","submitted_at":"2025-02-07T16:09:17Z","title":"EcoServe: Designing Carbon-Aware AI Inference Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.05043","snapshot_observed_at":"2026-08-07T13:00:30.958563Z","title":"EcoServe: Designing Carbon-Aware AI Inference Systems","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:30.958563Z"},"links":{"cited_paper":"/paper/2502.05043","citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:0d84d5d6763685b53aad3ae693272708d33d714beb3eb1177d555a5115b6d1b6","observation_id":"c58e9d3b-f534-4daf-afa9-1372a189abb5","resolution":{"observed_at":"2026-08-07T13:00:30.958563Z","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":"10.48550/arxiv.2502.14617","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:00:32.359038Z","title":"Serving Models, Fast and Slow: Optimizing Heterogeneous LLM Inferencing Workloads at Scale (SAGESERVE)","venue":null,"work_id":"4836e457-a890-4574-8564-c8f228aa74b4","year":2025},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:31.199614Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:0191c879711b84aab9a07fa7d924c7992c32a06435ae908ab84d60faca2dd62e","observation_id":"13b15205-ebc9-44fe-a7c7-7cfa0a8827bf","resolution":{"observed_at":"2026-08-07T13:00:32.454291Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2605.11603","last_updated":"2026-05-12T06:32:31Z","snapshot_observed_at":"2026-07-31T18:10:13.620375Z","submitted_at":"2026-05-12T06:32:31Z","title":"GAR: Carbon-Aware Routing for LLM Inference via Constrained Optimization","version":1},"cited_work":{"arxiv_id":"2605.11603","doi":"10.48550/arxiv.2605.11603","metadata_source":"pith","pith_arxiv_id":"2605.11603","snapshot_observed_at":"2026-08-07T18:16:16.850658Z","title":"GAR: Carbon-Aware Routing for LLM Inference via Constrained Optimization","venue":"cs.AI","work_id":"cdc69565-c59a-4a84-a722-f0fb3df159a6","year":2026},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:31.324204Z"},"links":{"cited_paper":"/paper/2605.11603","citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:4a3d57fbfced2156bf07da0d580d169f0c437d21786b66cfec2c92fe73ea9083","observation_id":"f3e6692b-2605-4406-9297-f2d904efb5c2","resolution":{"observed_at":"2026-08-07T13:00:32.162092Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:00:35.218644Z","title":"v3 API documentation","venue":null,"work_id":"1736bff9-e8d6-407d-90a9-9c376986ed2d","year":2024},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:31.475248Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:41b73726328152ad0db38f48414316a46fa8a12f581ce4f307cf4c160f60b540","observation_id":"ca612e8b-fdd6-422c-8092-ca6911bde83d","resolution":{"observed_at":"2026-08-07T13:00:35.324632Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:00:35.008470Z","title":"North-America MOER model version 2026-03-01 release notes (expanded renewable- curtailment detection; zero-MOER values during modeled curtailment)","venue":null,"work_id":"8dc8845d-cfcf-4d23-861b-786d7dff7d60","year":2026},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:31.624372Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:47c0efbec13c873ff0bce5c135a6bd5760197063487905d8f727f22207478f7a","observation_id":"06e93b2c-f960-4d59-baa6-e2e09638481c","resolution":{"observed_at":"2026-08-07T13:00:35.113190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:00:34.822457Z","title":"The GHG Protocol for Project Accounting","venue":null,"work_id":"80bcdac2-85ec-4edd-b79a-3de36dadf60e","year":2005},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:31.734682Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:0ce0b4bdf083cd9f02959224491daa73d80c255f3084401b87c39f5fd809e6b9","observation_id":"3384a559-c0ff-4e10-8389-edf7e8ecd3ea","resolution":{"observed_at":"2026-08-07T13:00:34.922297Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:00:34.626284Z","title":"Guidelines for Quantifying GHG Reductions from Grid-Connected Electricity Projects","venue":null,"work_id":"d1e5a920-4af0-4cf1-8dee-18eaa1ecde36","year":null},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:31.827948Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:86d076a8d87b57cb4777cf536a92a2f62eb8f13dcfbe9ff0c789bd9ba660e96a","observation_id":"b291e807-2dd8-4536-9923-94fc48250d60","resolution":{"observed_at":"2026-08-07T13:00:34.716609Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:00:34.419994Z","title":null,"venue":null,"work_id":"707f34a2-65e5-4feb-b436-865d877d6ac9","year":2026},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":2007,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:31.923370Z"},"links":{"citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:55850a8df565ba2af3a74554a666afc84e1400b848072ec62f9a3ab7688a31f6","observation_id":"60a57892-9a93-4d95-967d-9c5d5f564666","resolution":{"observed_at":"2026-08-07T13:00:34.514625Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.10350","last_updated":"2021-04-23T14:26:29Z","snapshot_observed_at":"2026-07-06T11:02:18.405330Z","submitted_at":"2021-04-21T04:44:25Z","title":"Carbon Emissions and Large Neural Network Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.10350","snapshot_observed_at":"2026-08-07T13:00:30.717634Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:30.717634Z"},"links":{"cited_paper":"/paper/2104.10350","citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:1db12dd3151b3aed5821657424cb9be5d71883a2b3544aaf6ae3dd36a9ed2182","observation_id":"2c19ea45-c4fc-442c-a38d-19d9aca21f10","resolution":{"observed_at":"2026-08-07T13:00:30.717634Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.05043","last_updated":"2025-03-15T19:26:40Z","snapshot_observed_at":"2026-08-09T07:19:40.287753Z","submitted_at":"2025-02-07T16:09:17Z","title":"EcoServe: Designing Carbon-Aware AI Inference Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.05043","snapshot_observed_at":"2026-08-07T13:00:31.049555Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-07T13:00:31.049555Z"},"links":{"cited_paper":"/paper/2502.05043","citing_paper":"/paper/2608.06188"},"observation_digest":"sha256:f3425feb7fdcb03abde91bfffe8f78df155416e232e41675ca38417d19290012","observation_id":"bb7ba158-1ba9-450c-8a7b-44929659aa1d","resolution":{"observed_at":"2026-08-07T13:00:31.049555Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.06188","last_updated":"2026-08-06T15:46:18Z","latest_version":1,"primary_category":"cs.DC","snapshot_observed_at":"2026-08-09T17:12:54.282908Z","submitted_at":"2026-08-06T15:46:18Z","title":"Routing LLM Inference to the Cleanest Grid in Real Time"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":17,"verified_exact":6,"verified_fuzzy":7},"total_outbound_references":31},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2608.06188."}