{"as_of":"2026-08-09T19:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2a9aed0754eb4275991b4d2490cb7df6b96349fe0078f8485e1d026ceac5d9f2","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":5,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":5,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":5,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":5,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T18:41:32.417291Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-23T21:15:49.390225Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2109.05472","last_updated":"2023-03-29T11:34:30Z","snapshot_observed_at":"2026-07-06T11:46:43.815468Z","submitted_at":"2021-09-12T09:40:18Z","title":"Compute and Energy Consumption Trends in Deep Learning Inference","version":2},"cited_work":{"arxiv_id":"2109.05472","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2109.05472","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv:2109.05472 (2021)","venue":null,"work_id":"9695231b-98c5-43d6-812d-1b2a4247ac85","year":2021},"citing_paper":{"arxiv_id":"2409.07609","last_updated":"2026-07-21T12:24:53Z","snapshot_observed_at":"2026-08-04T02:09:32.375092Z","submitted_at":"2024-09-11T20:43:59Z","title":"Survival of the Cheapest: Cost-Aware Hardware Adaptation for Adversarial Robustness","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-23T21:14:38.949892Z"},"links":{"cited_paper":"/paper/2109.05472","citing_paper":"/paper/2409.07609"},"observation_digest":"sha256:3e54f442413d2061eaa489b876a98ba3938309b94bd1c390ac57bf166a403bd1","observation_id":"a3a60006-d9f1-4b4d-a26b-c8024ce1c7cf","resolution":{"observed_at":"2026-05-23T21:15:49.393891Z","resolver_source":"arxiv_id","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":"2109.05472","last_updated":"2023-03-29T11:34:30Z","snapshot_observed_at":"2026-07-06T11:46:43.815468Z","submitted_at":"2021-09-12T09:40:18Z","title":"Compute and Energy Consumption Trends in Deep Learning Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.05472","snapshot_observed_at":"2026-08-08T18:41:32.417291Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.05610","last_updated":"2025-03-15T09:28:13Z","snapshot_observed_at":"2026-08-09T03:40:49.859971Z","submitted_at":"2025-02-08T15:34:52Z","title":"Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-08T18:41:32.417291Z"},"links":{"cited_paper":"/paper/2109.05472","citing_paper":"/paper/2502.05610"},"observation_digest":"sha256:56998d99b27954613a7ffef9611be85aae8d2d56b8433de00fdffcfd95fc281d","observation_id":"cb14421e-76cf-4633-aca0-cbe6b3990aeb","resolution":{"observed_at":"2026-08-08T18:41:32.417291Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.05472","last_updated":"2023-03-29T11:34:30Z","snapshot_observed_at":"2026-07-06T11:46:43.815468Z","submitted_at":"2021-09-12T09:40:18Z","title":"Compute and Energy Consumption Trends in Deep Learning Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.05472","snapshot_observed_at":"2026-08-08T13:38:02.274615Z","title":"arXiv preprint arXiv:2109.05472 (2021) 1","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.07192","last_updated":"2025-02-11T02:32:32Z","snapshot_observed_at":"2026-08-09T16:59:05.626327Z","submitted_at":"2025-02-11T02:32:32Z","title":"OscNet: Machine Learning on CMOS Oscillator Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-08T13:38:02.274615Z"},"links":{"cited_paper":"/paper/2109.05472","citing_paper":"/paper/2502.07192"},"observation_digest":"sha256:97d2f44b3180b2e68a471041fea2e631ccb9277990290f41aa93f8fbfc253390","observation_id":"e2e0044b-5498-4854-bbce-786d0a6b1935","resolution":{"observed_at":"2026-08-08T13:38:02.274615Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.05472","last_updated":"2023-03-29T11:34:30Z","snapshot_observed_at":"2026-07-06T11:46:43.815468Z","submitted_at":"2021-09-12T09:40:18Z","title":"Compute and Energy Consumption Trends in Deep Learning Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.05472","snapshot_observed_at":"2026-08-07T00:51:48.992724Z","title":"Compute and energy con- sumption trends in deep learning inference","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.12610","last_updated":"2025-07-17T00:39:38Z","snapshot_observed_at":"2026-08-09T16:59:09.890029Z","submitted_at":"2025-06-14T19:10:23Z","title":"OscNet v1.5: Energy Efficient Hopfield Network on CMOS Oscillators for Image Classification","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T00:51:48.992724Z"},"links":{"cited_paper":"/paper/2109.05472","citing_paper":"/paper/2506.12610"},"observation_digest":"sha256:f3dd3efd45787d244c92bc49851c0cc51c03159883377a070f70b196efcd6056","observation_id":"d451bf7b-1548-498a-b8d2-0ff3e2e5dd27","resolution":{"observed_at":"2026-08-07T00:51:48.992724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.05472","last_updated":"2023-03-29T11:34:30Z","snapshot_observed_at":"2026-07-06T11:46:43.815468Z","submitted_at":"2021-09-12T09:40:18Z","title":"Compute and Energy Consumption Trends in Deep Learning Inference","version":2},"cited_work":{"arxiv_id":"2109.05472","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2109.05472","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv:2109.05472 (2021)","venue":null,"work_id":"9695231b-98c5-43d6-812d-1b2a4247ac85","year":2021},"citing_paper":{"arxiv_id":"2604.03446","last_updated":"2026-04-03T20:37:58Z","snapshot_observed_at":"2026-07-06T22:52:39.423471Z","submitted_at":"2026-04-03T20:37:58Z","title":"Fast Cross-Operator Optimization of Attention Dataflow","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-13T17:48:42.142503Z"},"links":{"cited_paper":"/paper/2109.05472","citing_paper":"/paper/2604.03446"},"observation_digest":"sha256:ca323dbe5652dae1a62ca2b17eaf2c9e71c75556a34524f9bed86dca781aac8d","observation_id":"975ceabd-6ae1-42c3-a578-9ded4b81d03b","resolution":{"observed_at":"2026-05-13T17:53:05.240294Z","resolver_source":"arxiv_id","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"}}],"links":{"evidence":"/evidence","html":"/paper/2109.05472/citation-record","integrity":"/paper/2109.05472/integrity","json":"/paper/2109.05472/citation-record.json","paper":"/paper/2109.05472"},"outbound":[],"paper":{"arxiv_id":"2109.05472","last_updated":"2023-03-29T11:34:30Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T11:46:43.815468Z","submitted_at":"2021-09-12T09:40:18Z","title":"Compute and Energy Consumption Trends in Deep Learning Inference"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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 0 of 0 outbound references and 5 inbound Pith citation observations for arXiv:2109.05472."}