{"as_of":"2026-08-09T22:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a6c17a8d09cc6614bb9dd24f2cd603a4def6a50d58839c6e037a08df9b318937","coverage":[{"denominator":23,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":23,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T19:57:19.479647Z","state":"measured"},{"denominator":24,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":24,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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":"2026-08-07T14:15:28.633807Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-07T14:15:30.051679Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"cited_work":{"arxiv_id":"2502.00182","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.00182","snapshot_observed_at":"2026-08-07T14:15:30.051679Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","venue":"cs.LG","work_id":"986846c6-e008-4079-8775-3e6d98492462","year":2025},"citing_paper":{"arxiv_id":"2505.19605","last_updated":"2025-05-26T07:16:00Z","snapshot_observed_at":"2026-08-07T14:08:15.063944Z","submitted_at":"2025-05-26T07:16:00Z","title":"Kuramoto-FedAvg: Using Synchronization Dynamics to Improve Federated Learning Optimization under Statistical Heterogeneity","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T14:15:28.633807Z"},"links":{"cited_paper":"/paper/2502.00182","citing_paper":"/paper/2505.19605"},"observation_digest":"sha256:07db77d1a1631abf19dfb2ae6409dae67bda696327939d95a86649373f551307","observation_id":"fcee1be4-4204-42fb-b7cb-65e397b49626","resolution":{"observed_at":"2026-08-07T14:15:30.104695Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2502.00182/citation-record","integrity":"/paper/2502.00182/integrity","json":"/paper/2502.00182/citation-record.json","paper":"/paper/2502.00182"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T19:57:19.716067Z","title":"In: ICLR (2021)","venue":null,"work_id":"0f222d33-1bfe-4aca-b4ba-f0ac70c6b0f1","year":2021},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.407302Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:bfb86c882cabba10146c911c051fd8f672cc8801ca51c67a414b8dd1032d884a","observation_id":"7f2ed4d0-4507-4240-8345-74101a0e89ff","resolution":{"observed_at":"2026-08-09T19:57:19.719454Z","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":"2026-08-09T19:57:19.707083Z","title":"In: ICLR (2021)","venue":null,"work_id":"72480d06-e992-406f-bb28-7cc36e09766a","year":2021},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.412070Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:9bf955079c5c0c6037ec1ae66b99923134e269fe3f8cef0644e26712f64d3408","observation_id":"6e0f43b9-eea6-44b9-8bbd-3426297f8bfa","resolution":{"observed_at":"2026-08-09T19:57:19.710384Z","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":"2026-08-09T19:57:19.698067Z","title":"NeurIPS (2006)","venue":null,"work_id":"d9968f29-948a-49aa-9e66-d4eb3ae920df","year":2006},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.415479Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:a27c480a8969da59aed84e5015e129f0e2facaa1339497af3bdd89ed6ac95d7f","observation_id":"84e68016-d6b5-4779-8cb4-1e327897278c","resolution":{"observed_at":"2026-08-09T19:57:19.701320Z","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":"2026-08-09T19:57:19.688854Z","title":"NeurIPS (2012)","venue":null,"work_id":"116495d7-dcdb-4d7d-9aab-7f4fb6060dc7","year":2012},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.418772Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:6a06b8b9bbea4c8b722e8da0e62490576ddcfd4faec53fc3e482d9b7d3008eb4","observation_id":"339eb239-479f-4e6e-9d64-3efc2e6582bb","resolution":{"observed_at":"2026-08-09T19:57:19.692405Z","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":"2026-08-09T19:57:19.679409Z","title":"In: ICLR (2021)","venue":null,"work_id":"fa679aa8-4dfe-48be-abe6-3e1cb6021ced","year":2021},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.422274Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:0dc52206963bb1f027d44d877b9466d7476c8ab291610275bcc4d976ad19312a","observation_id":"4c0661d3-c978-4a37-bf16-2791316a503a","resolution":{"observed_at":"2026-08-09T19:57:19.683307Z","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":"2026-08-09T19:57:19.669694Z","title":"Foundations and trends in machine learning (2021)","venue":null,"work_id":"9265fe32-88f1-416f-8e21-e90c56af9d69","year":2021},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.425798Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:aed5551b45878987a28b0d9c96d4c0a8309fd740befe4165f718340a358c8778","observation_id":"6a3c8e1c-4399-4177-9c03-39efe8332347","resolution":{"observed_at":"2026-08-09T19:57:19.673727Z","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":"2026-08-09T19:57:19.660505Z","title":"In: ICML","venue":null,"work_id":"d6d8c643-d36c-4e34-945d-1765f154c3a1","year":2020},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.429375Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:169e2d1df0ca8f098a756d19dd2e6acce5e06d462cb7de602be5e8e3ae2b8abf","observation_id":"c5e90bcf-566b-40ec-9cfe-4d135ff79a4b","resolution":{"observed_at":"2026-08-09T19:57:19.664224Z","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":"2026-08-09T19:57:19.650607Z","title":"In: ICLR (2017)","venue":null,"work_id":"fe812540-0ddd-4acd-a725-19a1a427206d","year":2017},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.432492Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:33f0b529da2ae311bd4f4915a5adecd57eb1d3c5bf1a1a9034986b52f87235bc","observation_id":"5daae462-f4d5-4ff9-9dee-3ad6ba791958","resolution":{"observed_at":"2026-08-09T19:57:19.653879Z","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":"2026-08-09T19:57:19.641787Z","title":"In: CVPR (2024)","venue":null,"work_id":"d99c98e4-c0d8-4251-81e2-62eeb2f5300d","year":2024},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.435735Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:a4dd109be9d7080effba77078b75c6952cc45e322acbc961761e964c3bdc9479","observation_id":"ea6294f7-c066-4071-89c0-8ea1028d8c31","resolution":{"observed_at":"2026-08-09T19:57:19.645074Z","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":"2026-08-09T19:57:19.632791Z","title":"NeurIPS (2022)","venue":null,"work_id":"824cc130-f2e2-4336-a923-7661540e3d8c","year":2022},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.439071Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:1600a690555a4f34cfe7de6ef837e702b8939fb7b1731a26f703881709f658c3","observation_id":"55114f0b-a41d-4128-a0e4-9cd397068788","resolution":{"observed_at":"2026-08-09T19:57:19.636059Z","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":"2026-08-09T19:57:19.623340Z","title":"NeurIPS (2018)","venue":null,"work_id":"a385938a-0348-4250-86b9-279b85203e1d","year":2018},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.442273Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:f597f2363b73b31630dfe443d121b5a8be83737b3db33677e44b3e4a9cb22646","observation_id":"dd24b965-d951-4e2a-ab96-a5048df69358","resolution":{"observed_at":"2026-08-09T19:57:19.626656Z","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":"2026-08-09T19:57:19.613386Z","title":"In: CVPR (2021) Title Suppressed Due to Excessive Length 15","venue":null,"work_id":"5ce68c67-9ccb-46a8-8a65-86ff95965c6d","year":2021},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.445356Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:3c14c1ff05cf69d1b08c503945bd74fdec10ec32933ea9c318c26e432f931462","observation_id":"2e5ba8f0-25f6-43f6-9f86-9d52c1d4f501","resolution":{"observed_at":"2026-08-09T19:57:19.617250Z","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":"2026-08-09T19:57:19.603691Z","title":"MLSys (2020)","venue":null,"work_id":"9afb7c96-dca4-43dc-9da5-2c9d3db2ac8d","year":2020},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.448526Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:a5aa4ee1f5bdc43837e34b8b09ab7bef4a35e63610722267e69ea2a875be6f16","observation_id":"0c542f90-45fe-43e7-9226-70de6f655356","resolution":{"observed_at":"2026-08-09T19:57:19.607283Z","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":"2026-08-09T19:57:19.593970Z","title":"In: AISTATS","venue":null,"work_id":"9838a35a-a4f5-42ce-b413-90255f323984","year":2017},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.451480Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:909a57f5c14dcd9c30721ba615ce265194ccfe5455a81e5c24f30625ddd23704","observation_id":"9f76a741-87ae-4917-bc94-25dd42196682","resolution":{"observed_at":"2026-08-09T19:57:19.597559Z","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":"2026-08-09T19:57:19.583946Z","title":"In: ICML","venue":null,"work_id":"7c17d122-2af1-47e5-95f8-cb330536553c","year":2022},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.454500Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:4477949be3e442c306355803da98a1c455a6396a4e72032e5774c8fd442e6ba5","observation_id":"ab9fa6fc-597a-407d-8a5c-1f9415a476d3","resolution":{"observed_at":"2026-08-09T19:57:19.587555Z","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":"2026-08-09T19:57:19.573855Z","title":"In: ICLR (2021)","venue":null,"work_id":"eba21f5b-296e-47d7-8a3e-0fa7c9bc5011","year":2021},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.457381Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:cb79e7d24a1e65e9833c0c387794231c463144fa3e04c8a43ebf34a1a4444ece","observation_id":"2eda2842-6d9c-4bf1-acd5-90c5e8bf7334","resolution":{"observed_at":"2026-08-09T19:57:19.577260Z","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":{"arxiv_id":"1609.04747","last_updated":"2017-06-15T13:21:04Z","snapshot_observed_at":"2026-08-04T02:05:40.539691Z","submitted_at":"2016-09-15T17:32:34Z","title":"An overview of gradient descent optimization algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.04747","snapshot_observed_at":"2026-08-09T19:57:19.460289Z","title":"arXiv preprint arXiv:1609.04747 (2016)","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.460289Z"},"links":{"cited_paper":"/paper/1609.04747","citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:2a4d289215f7cdacdb626cf54baefb7c5b9a1813390fb4dde6c13437f66342ba","observation_id":"7332f7ad-1de9-45a2-b9c1-663592e6307b","resolution":{"observed_at":"2026-08-09T19:57:19.460289Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.05799","last_updated":"2018-02-21T04:30:30Z","snapshot_observed_at":"2026-07-06T06:23:45.215820Z","submitted_at":"2018-02-15T23:36:51Z","title":"Horovod: fast and easy distributed deep learning in TensorFlow","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.05799","snapshot_observed_at":"2026-08-09T19:57:19.463843Z","title":"arXiv preprint arXiv:1802.05799 (2018)","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.463843Z"},"links":{"cited_paper":"/paper/1802.05799","citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:0e07b258db5c8b9ac703cdd1004e1c7154fb2530e8c7ae87738d5b695f0ec851","observation_id":"6862694d-d459-4ab8-a928-a3f22f6811be","resolution":{"observed_at":"2026-08-09T19:57:19.463843Z","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":"2026-08-09T19:57:19.563918Z","title":"In: ICLR (2019)","venue":null,"work_id":"5c168bcf-6938-422a-9bac-243b8a0a035f","year":2019},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.467158Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:70258fc46ff1630377a9facd24c1a65a4c5c7ff9a2e209ba793780e3071390f8","observation_id":"1253b496-5bba-4c77-b1cc-13ab032c4431","resolution":{"observed_at":"2026-08-09T19:57:19.567411Z","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":"2026-08-09T19:57:19.553575Z","title":"In: ICML","venue":null,"work_id":"51e94b32-301c-4e2f-9d4e-36aa6cbc7e28","year":2023},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.469968Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:1c15a469707abe00179c131b7dd504bcc747d9a8a400020dadc7db54e9df1390","observation_id":"7c9effa4-4058-446a-86d6-c44753fe6558","resolution":{"observed_at":"2026-08-09T19:57:19.557058Z","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":"2026-08-09T19:57:19.543519Z","title":"In: ICML","venue":null,"work_id":"ef02e6e6-8ce2-4da1-9e76-f2deee66f3ba","year":2022},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.473159Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:a04023e0073a3b97747b6bca5b3928abf14c0305ccd98378eadf778470996efa","observation_id":"2af4501e-38dd-48cb-b8bd-7b74dc1628c1","resolution":{"observed_at":"2026-08-09T19:57:19.546959Z","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":{"arxiv_id":"1806.00582","last_updated":"2022-07-21T12:33:15Z","snapshot_observed_at":"2026-07-06T06:42:35.645776Z","submitted_at":"2018-06-02T04:45:58Z","title":"Federated Learning with Non-IID Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.00582","snapshot_observed_at":"2026-08-09T19:57:19.476164Z","title":"arXiv preprint arXiv:1806.00582 (2018)","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.476164Z"},"links":{"cited_paper":"/paper/1806.00582","citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:585a9931c6df526c829e462e09ca62784bc1483b2a78a1bf490455ed935630b4","observation_id":"02944cd8-1920-418c-a48d-e4d410fa481f","resolution":{"observed_at":"2026-08-09T19:57:19.476164Z","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":"2026-08-09T19:57:19.532045Z","title":"NeurIPS (2010)","venue":null,"work_id":"fe068415-e82a-41b4-913c-dbf7ad79c5d5","year":2010},"citing_paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T19:57:19.479647Z"},"links":{"citing_paper":"/paper/2502.00182"},"observation_digest":"sha256:32a39ba5a839bd7da77faaa847a5c1befc161065e4199911717b9f798e647669","observation_id":"8797258c-f85a-4539-a020-c043918da888","resolution":{"observed_at":"2026-08-09T19:57:19.536652Z","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"}}],"paper":{"arxiv_id":"2502.00182","last_updated":"2025-06-03T16:38:42Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T19:51:15.675914Z","submitted_at":"2025-01-31T21:58:15Z","title":"Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study"},"reference_resolution":{"displayed":23,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":3,"verified_exact":0,"verified_fuzzy":20},"total_outbound_references":23},"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 23 of 23 outbound references and 1 inbound Pith citation observation for arXiv:2502.00182."}