{"as_of":"2026-08-23T03:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9aea9104fbe23d3f81ab40491efd53b32776a76f91dc1e717914ff911c94d618","coverage":[{"denominator":20,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T12:28:55.209629Z","state":"measured"},{"denominator":21,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":21,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-22T09:10:05.320094Z","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":"2026-05-22T09:11:21.077299Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"cited_work":{"arxiv_id":"2502.02410","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.02410","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Privacy amplification by structured subsampling for deep differ- entially private time series forecasting","venue":null,"work_id":"b8638307-9e8b-4fef-a816-9ecb9588f4d2","year":2025},"citing_paper":{"arxiv_id":"2605.21780","last_updated":"2026-05-20T22:17:29Z","snapshot_observed_at":"2026-08-18T13:06:01.327843Z","submitted_at":"2026-05-20T22:17:29Z","title":"Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-05-22T09:10:05.320094Z"},"links":{"cited_paper":"/paper/2502.02410","citing_paper":"/paper/2605.21780"},"observation_digest":"sha256:af3571594afe720dcb77de45c801b2c3576849ba9dae487c2b231e55bbabd9b0","observation_id":"d0bee05f-72ab-4f38-a965-9b3e9e517c6c","resolution":{"observed_at":"2026-05-22T09:11:21.079496Z","resolver_source":"arxiv_id","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"}}],"links":{"evidence":"/evidence","html":"/paper/2502.02410/citation-record","integrity":"/paper/2502.02410/integrity","json":"/paper/2502.02410/citation-record.json","paper":"/paper/2502.02410"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.454379Z","title":null,"venue":null,"work_id":"e0830efe-6497-4779-b746-256b7251ca26","year":null},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.147741Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:08be2cf1d055401537b760ecc1badc54d537ce961332d82e0e98663f03db1fad","observation_id":"61a50dc5-d4cd-45f5-981e-11ccf1776527","resolution":{"observed_at":"2026-08-09T12:28:55.458206Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.428358Z","title":null,"venue":null,"work_id":"e77597b3-a78d-4d96-9b1c-14f07a07bbeb","year":null},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.154225Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:7323617298c102ef0fbc6b78ba0fe0f6d2670b95b021895d6e9e2996ddf2b5e4","observation_id":"91613e6b-43e8-4494-8505-33bef2934c48","resolution":{"observed_at":"2026-08-09T12:28:55.432243Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.416138Z","title":null,"venue":null,"work_id":"67333447-230e-4a46-8b1f-37ff248735db","year":2009},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.157333Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:f81ac900d62b50f2c93d473618b6c0880638db500593a362a37767c06ed82041","observation_id":"51fd1c36-9af3-4b01-b325-5f2827dfbc50","resolution":{"observed_at":"2026-08-09T12:28:55.420252Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.404042Z","title":"connect-the-dots","venue":null,"work_id":"d955b630-49ee-4170-bb51-ea7e0fdb7985","year":2018},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.160924Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:880febb619c104e1d9a79d6b686ab89c3ef43a149197094dc830ff9aec5bb02f","observation_id":"dd8c2c09-0653-4609-b5da-ef3386177475","resolution":{"observed_at":"2026-08-09T12:28:55.407597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.465912Z","title":null,"venue":null,"work_id":"f7aa9ccc-e879-4b90-8008-7d76edeb89b5","year":null},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.164403Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:b6664847c837cf6495e010b840d4039fabb56b36383a0b7bfc9e6b05428f4740","observation_id":"922b06dc-1e6c-47ad-a77e-01e8524481ac","resolution":{"observed_at":"2026-08-09T12:28:55.469119Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.393108Z","title":null,"venue":null,"work_id":"9fae51bb-4c80-49fd-a561-d5d411094ed6","year":null},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.167647Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:637ce9d96de683a275e649fe0fbad91fca45c4cbf5d063981c3a4dbca28aa9a9","observation_id":"cd9c00c3-5ec1-4aba-a066-7a5ef1c65ea6","resolution":{"observed_at":"2026-08-09T12:28:55.396299Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.442011Z","title":null,"venue":null,"work_id":"6984f125-73c2-4106-917a-ec1e49a3ae4e","year":null},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.171144Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:44b72df686f1cd86c4a96e8572e62aeaad13abce74a7eb1ad26ebf9f393f3b95","observation_id":"7133b459-cd20-496f-ba46-d0509e0fa62d","resolution":{"observed_at":"2026-08-09T12:28:55.446076Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.381121Z","title":null,"venue":null,"work_id":"81bbf06a-dbd3-4130-a556-cb58fa463ca9","year":null},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.174281Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:86d741d3253d2528ed4e85853c68a4658ef5febe2ea9e3bc0d910aad862a6184","observation_id":"3c79fd98-e2c4-4369-9c92-c9e99e3f6872","resolution":{"observed_at":"2026-08-09T12:28:55.385266Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.367859Z","title":"The first two steps are identical to the pervious section, since they do not depend on the distribution of the bottom-level subsampling procedure (see Appendices E.1.1 and E.1.2)","venue":null,"work_id":"ef1ba8da-16c8-4936-a6d4-8cc4f6e62177","year":2024},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.177744Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:078ff9bfd88fcd626ac35598514bdef12a405c750996fb9b842d91105be94243","observation_id":"39ece967-29ab-4cf5-8d28-ecbb46e2ef46","resolution":{"observed_at":"2026-08-09T12:28:55.372807Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.356633Z","title":null,"venue":null,"work_id":"ce09c7e5-97fe-4158-b1c0-bbd9add70f66","year":null},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.181325Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:cb8b39307c80c10959b7f1168894ae7c76bd5f55f6b5426b24c0f4838c3bc9f9","observation_id":"762cff4a-7903-4cdb-8d3b-33c754dc8699","resolution":{"observed_at":"2026-08-09T12:28:55.360261Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.344819Z","title":null,"venue":null,"work_id":"65a4f86b-d61d-43d1-83e8-7cecd54eddbd","year":null},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.184816Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:5e77a2d8c9f19bbdb3b6f47043a40736ee612bc7b831ba8c36af50cb3da0c39c","observation_id":"1784dadf-1e68-4107-ab6e-5273508e6df5","resolution":{"observed_at":"2026-08-09T12:28:55.348999Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.333171Z","title":null,"venue":null,"work_id":"c0492081-e80d-4bf5-a953-db9ffc4bfdd1","year":null},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.188322Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:512f89bbd268f8ccf7613b391a57dacb71d4c4e706b0802b08f16703a4df22dc","observation_id":"902eb597-1b89-4b10-b588-6a75b15cf359","resolution":{"observed_at":"2026-08-09T12:28:55.336578Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.321700Z","title":null,"venue":null,"work_id":"0f1d23fc-f082-4dad-8a57-0396a254c7c1","year":null},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.191878Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:9115aa67d3d78c50477711b1b06acccf8f10334be3dce5f4437949816057212b","observation_id":"b9a1dce4-2317-4849-8daf-0634718dd262","resolution":{"observed_at":"2026-08-09T12:28:55.324958Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.308808Z","title":"connect-the-dots","venue":null,"work_id":"1a23507d-dca5-4ea8-87ca-1cb98e1ba02c","year":2022},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.195232Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:3b0114fa680d5941d935f7304af514a3e0101324c0ef20be86c4e22d29336109","observation_id":"3505f851-7f8b-4073-81b5-7b911750ff61","resolution":{"observed_at":"2026-08-09T12:28:55.312388Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.297190Z","title":null,"venue":null,"work_id":"6c7a0fa1-e6ef-4491-9d73-88186a9f9d3c","year":null},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.199486Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:f4debc0f6b42c20c5dfbcdbd0bf519a24dda37f35f7b31440e218d7991134653","observation_id":"3af1e6a6-35fe-4ec9-abcf-efbb974a7be7","resolution":{"observed_at":"2026-08-09T12:28:55.300462Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.284704Z","title":null,"venue":null,"work_id":"10448258-77c5-4f99-98fa-75df0df106ec","year":2018},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.202950Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:e4a66811fe6c7c1c21260e3c9188f2edea21d2b2c433dec099be561c059c2622","observation_id":"335cae23-c856-4394-b90c-28ef1d458166","resolution":{"observed_at":"2026-08-09T12:28:55.288672Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.271307Z","title":null,"venue":null,"work_id":"1c0101c3-df32-40aa-9b41-725f1d088c82","year":null},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.206415Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:d70f718d780d547503f012fbe31d2f4fb4f17347319c38e79a228776db6ea3b7","observation_id":"0e1e8b0e-426d-484b-99a2-1ed1ee30d1a2","resolution":{"observed_at":"2026-08-09T12:28:55.275435Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:28:55.256434Z","title":null,"venue":null,"work_id":"f260f8fc-88b2-483d-a978-8126c6066d23","year":2024},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.209629Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:bffa43659c03b716438bdcf5643bbb7ea19f1f26b7529ff037c37962683d5588","observation_id":"bcc397c7-765e-4524-85b7-b558a97609ac","resolution":{"observed_at":"2026-08-09T12:28:55.261123Z","resolver_source":"raw_fallback","status":"unresolved"},"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":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-09T12:28:55.135176Z","title":"Wang, Q., Zhang, Y ., Lu, X., Wang, Z., Qin, Z., and Ren, K","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.135176Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:4681bca55ee6e8b0f4795c3a9d5f8a83840d80e3b23aba651799e68a44ee7356","observation_id":"8eb927d6-982f-432a-bfc1-eaa789a6e4d9","resolution":{"observed_at":"2026-08-09T12:28:55.135176Z","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":"2026-08-09T12:28:55.477432Z","title":"Group Privacy","venue":null,"work_id":"93073c1e-fca1-4f70-b2a3-684bf7bc8cf3","year":2022},"citing_paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting","version":3},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-09T12:28:55.139802Z"},"links":{"citing_paper":"/paper/2502.02410"},"observation_digest":"sha256:17c328225f1946488a8dcbac52d9b241b60cefd7b5a1a83eb2d435c12d2a1242","observation_id":"26d6f33e-e8ad-4707-bf8f-a5a2e7f82361","resolution":{"observed_at":"2026-08-09T12:28:55.480941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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"}}],"paper":{"arxiv_id":"2502.02410","last_updated":"2025-08-04T13:44:01Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T23:29:35.402882Z","submitted_at":"2025-02-04T15:29:00Z","title":"Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting"},"reference_resolution":{"displayed":20,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":0,"verified_fuzzy":4},"total_outbound_references":20},"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 23 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 1 inbound Pith citation observation for arXiv:2502.02410."}