{"as_of":"2026-08-17T08:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f2ac85275ab4e9f85317a5fc89751f477111c59512bd1c1a9837e5a39fae7ada","coverage":[{"denominator":12,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T16:30:39.112363Z","state":"measured"},{"denominator":16,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":16,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T00:45:45.599462Z","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":"2026-07-04T02:49:25.223479Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.01145","last_updated":"2025-06-06T18:16:44Z","snapshot_observed_at":"2026-08-10T05:12:27.881591Z","submitted_at":"2025-02-03T08:25:34Z","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.01145","snapshot_observed_at":"2026-08-07T00:45:45.599462Z","title":"Tackling feature and sample heterogeneity in decentralized multi-task learning: A sheaf-theoretic approach,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.12795","last_updated":"2025-06-15T10:01:44Z","snapshot_observed_at":"2026-08-10T09:10:27.409870Z","submitted_at":"2025-06-15T10:01:44Z","title":"Resilient-native and Intelligent NextG Systems","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T00:45:45.599462Z"},"links":{"cited_paper":"/paper/2502.01145","citing_paper":"/paper/2506.12795"},"observation_digest":"sha256:d5b7699a5ee8e9f9073639854b3beb75d78c91d0301737dfae38d0d9bc58ce81","observation_id":"80a45442-42ab-454e-b6ff-2cdfba790987","resolution":{"observed_at":"2026-08-07T00:45:45.599462Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01145","last_updated":"2025-06-06T18:16:44Z","snapshot_observed_at":"2026-08-10T05:12:27.881591Z","submitted_at":"2025-02-03T08:25:34Z","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach","version":2},"cited_work":{"arxiv_id":"2502.01145","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.01145","snapshot_observed_at":"2026-07-04T02:49:25.223479Z","title":"Tackling feature and sample hetero- geneity in decentralized multi-task learning: A sheaf-theoretic approach","venue":null,"work_id":"cacba0d9-c58c-492f-960f-8f3f9b568bfd","year":2024},"citing_paper":{"arxiv_id":"2605.04108","last_updated":"2026-05-04T16:43:22Z","snapshot_observed_at":"2026-07-06T23:16:54.673178Z","submitted_at":"2026-05-04T16:43:22Z","title":"MuCALD-SplitFed: Causal-Latent Diffusion for Privacy-Preserving Multi-Task Split-Federated Medical Image Segmentation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-08T18:44:45.397374Z"},"links":{"cited_paper":"/paper/2502.01145","citing_paper":"/paper/2605.04108"},"observation_digest":"sha256:b6be33d3d812916fa87b8986ca0a1e728efdcbddcab496500e75e37c21951015","observation_id":"89dec681-bfb7-49d0-9112-81a3b5247750","resolution":{"observed_at":"2026-05-09T06:15:37.577557Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01145","last_updated":"2025-06-06T18:16:44Z","snapshot_observed_at":"2026-08-10T05:12:27.881591Z","submitted_at":"2025-02-03T08:25:34Z","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach","version":2},"cited_work":{"arxiv_id":"2502.01145","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.01145","snapshot_observed_at":"2026-07-04T02:49:25.223479Z","title":"Tackling feature and sample hetero- geneity in decentralized multi-task learning: A sheaf-theoretic approach","venue":null,"work_id":"cacba0d9-c58c-492f-960f-8f3f9b568bfd","year":2024},"citing_paper":{"arxiv_id":"2606.19529","last_updated":"2026-06-17T19:24:07Z","snapshot_observed_at":"2026-08-07T07:23:47.055802Z","submitted_at":"2026-06-17T19:24:07Z","title":"The Sheaf Laplacian: A Topological Framework for Data Fusion and Consensus in Distributed Sensing Networks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-26T18:57:22.630484Z"},"links":{"cited_paper":"/paper/2502.01145","citing_paper":"/paper/2606.19529"},"observation_digest":"sha256:7fb852f689774d51a47fecb6dba4458ddb8ee86c2147381724f03130567376a9","observation_id":"cf09c9c5-41ff-4516-9f08-1ff6baae3705","resolution":{"observed_at":"2026-07-04T02:49:25.225063Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01145","last_updated":"2025-06-06T18:16:44Z","snapshot_observed_at":"2026-08-10T05:12:27.881591Z","submitted_at":"2025-02-03T08:25:34Z","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.01145","snapshot_observed_at":"2026-07-12T02:12:36.752296Z","title":"Tackling feature and sample heterogeneity in decentralized multi-task learning: A sheaf- theoretic approach,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.03480","last_updated":"2026-07-03T16:47:38Z","snapshot_observed_at":"2026-08-13T06:59:07.856935Z","submitted_at":"2026-07-03T16:47:38Z","title":"A Sheaf-Theoretic Framework for Distributed Multi-Site Channel Charting","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-12T02:12:36.752296Z"},"links":{"cited_paper":"/paper/2502.01145","citing_paper":"/paper/2607.03480"},"observation_digest":"sha256:183ed3f96cf65839f2bc84f8906a97c5668f4c3152103c568b6ef7c65643f0a0","observation_id":"531f3a3e-4ebd-45f8-95fe-662988703848","resolution":{"observed_at":"2026-07-12T02:12:36.752296Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.01145/citation-record","integrity":"/paper/2502.01145/integrity","json":"/paper/2502.01145/citation-record.json","paper":"/paper/2502.01145"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T16:30:39.234856Z","title":"FMTL often involves clients with different data distributions, model architectures, or task objectives","venue":null,"work_id":"47c9a466-403a-4cdb-aea7-000d13e4871c","year":null},"citing_paper":{"arxiv_id":"2502.01145","last_updated":"2025-06-06T18:16:44Z","snapshot_observed_at":"2026-08-10T05:12:27.881591Z","submitted_at":"2025-02-03T08:25:34Z","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T16:30:39.082400Z"},"links":{"citing_paper":"/paper/2502.01145"},"observation_digest":"sha256:a50aeb4a7d9ebac2eede5a525eb36728eea7f1f8a911121372f73f126d291075","observation_id":"cfa25528-a19d-4785-b384-002c4cd7508d","resolution":{"observed_at":"2026-08-09T16:30:39.238037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T16:30:39.226448Z","title":"Sheaves provide a natural way to ensure consistency between local (client-specific) and global (network-wide) information","venue":null,"work_id":"f5a9633a-c6f8-4e7d-956a-616dab2a3fb7","year":null},"citing_paper":{"arxiv_id":"2502.01145","last_updated":"2025-06-06T18:16:44Z","snapshot_observed_at":"2026-08-10T05:12:27.881591Z","submitted_at":"2025-02-03T08:25:34Z","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T16:30:39.085443Z"},"links":{"citing_paper":"/paper/2502.01145"},"observation_digest":"sha256:49adb3e567d039e747b756a61594a4eb1fc12c1dbe90c7ecc8da4b49ea7fcf8f","observation_id":"ef313189-123a-4381-8c21-71c96ae1cbb2","resolution":{"observed_at":"2026-08-09T16:30:39.229742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T16:30:39.218249Z","title":"This nuanced representation is more sophisticated than traditional approaches that often assume uniform relationships across the network","venue":null,"work_id":"172ccff9-5eb3-4b26-becb-48f16dbca0fb","year":null},"citing_paper":{"arxiv_id":"2502.01145","last_updated":"2025-06-06T18:16:44Z","snapshot_observed_at":"2026-08-10T05:12:27.881591Z","submitted_at":"2025-02-03T08:25:34Z","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T16:30:39.088472Z"},"links":{"citing_paper":"/paper/2502.01145"},"observation_digest":"sha256:32b6ff101d9db9c392c978be607414d7741f4b3087764bab9effde1232f6cb6a","observation_id":"72b287a5-5569-44a7-86a5-945be64345a2","resolution":{"observed_at":"2026-08-09T16:30:39.221285Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T16:30:39.209812Z","title":null,"venue":null,"work_id":"0329385b-ba71-4584-939a-89e3e7231e78","year":null},"citing_paper":{"arxiv_id":"2502.01145","last_updated":"2025-06-06T18:16:44Z","snapshot_observed_at":"2026-08-10T05:12:27.881591Z","submitted_at":"2025-02-03T08:25:34Z","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T16:30:39.091757Z"},"links":{"citing_paper":"/paper/2502.01145"},"observation_digest":"sha256:1bda71baed5d94fe07ef620599c9805149cb24c9f0aa0899d368b5d99220796d","observation_id":"123b7b72-caa7-4063-b6e0-388b6d7d11d8","resolution":{"observed_at":"2026-08-09T16:30:39.212852Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T16:30:39.200596Z","title":"Our approach enforces consistency between the projections of local models onto the interaction space","venue":null,"work_id":"f94af19b-a71c-48d0-9173-908dd251fb99","year":null},"citing_paper":{"arxiv_id":"2502.01145","last_updated":"2025-06-06T18:16:44Z","snapshot_observed_at":"2026-08-10T05:12:27.881591Z","submitted_at":"2025-02-03T08:25:34Z","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T16:30:39.094890Z"},"links":{"citing_paper":"/paper/2502.01145"},"observation_digest":"sha256:b6cd670323d41462b088381efa249a6d2fceaf091311a25192ef9951ec658667","observation_id":"83003f62-779d-4917-b112-191c601a17be","resolution":{"observed_at":"2026-08-09T16:30:39.203988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T16:30:39.191647Z","title":"By minimizing the sheaf Laplacian term, local models are en- couraged to collaborate effectively, leveraging shared information to improve overall performance","venue":null,"work_id":"1cb36625-cdb1-49ac-afd6-7da3c27b074d","year":null},"citing_paper":{"arxiv_id":"2502.01145","last_updated":"2025-06-06T18:16:44Z","snapshot_observed_at":"2026-08-10T05:12:27.881591Z","submitted_at":"2025-02-03T08:25:34Z","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T16:30:39.098110Z"},"links":{"citing_paper":"/paper/2502.01145"},"observation_digest":"sha256:a9edc6d846e9d781a8b462d5248cfa64034e750967749020862dc7fe78203613","observation_id":"9133feda-08cd-4f48-aeed-4c8b09387a66","resolution":{"observed_at":"2026-08-09T16:30:39.194858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T16:30:39.182303Z","title":"Pij acts as a feature selection matrix, identifying common or comparable features between clientsi and j","venue":null,"work_id":"c96406cb-25d5-4d5a-bc4a-905c77c821dd","year":null},"citing_paper":{"arxiv_id":"2502.01145","last_updated":"2025-06-06T18:16:44Z","snapshot_observed_at":"2026-08-10T05:12:27.881591Z","submitted_at":"2025-02-03T08:25:34Z","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T16:30:39.101220Z"},"links":{"citing_paper":"/paper/2502.01145"},"observation_digest":"sha256:6a6045ba180464154875e50e1075cf96d91a6d9c86e5b4ebbe1fe028d2e684f4","observation_id":"6e7fe880-c36a-40fa-b009-c0826297b240","resolution":{"observed_at":"2026-08-09T16:30:39.185970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T16:30:39.173709Z","title":null,"venue":null,"work_id":"1f6eda27-7e61-4037-b4b0-937be8e772c5","year":null},"citing_paper":{"arxiv_id":"2502.01145","last_updated":"2025-06-06T18:16:44Z","snapshot_observed_at":"2026-08-10T05:12:27.881591Z","submitted_at":"2025-02-03T08:25:34Z","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T16:30:39.104025Z"},"links":{"citing_paper":"/paper/2502.01145"},"observation_digest":"sha256:7881e1e9a2bd4d8570532608e838bb07c366605adc52f89196e9e30adca355a3","observation_id":"5bc058e8-d0a1-4629-bf57-ab9f398083d3","resolution":{"observed_at":"2026-08-09T16:30:39.176715Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T16:30:39.164427Z","title":"The restriction maps allow for meaningful comparisons by projecting onto a common space","venue":null,"work_id":"8eaac327-d05a-48fd-bf56-9cffd53920a0","year":null},"citing_paper":{"arxiv_id":"2502.01145","last_updated":"2025-06-06T18:16:44Z","snapshot_observed_at":"2026-08-10T05:12:27.881591Z","submitted_at":"2025-02-03T08:25:34Z","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T16:30:39.106689Z"},"links":{"citing_paper":"/paper/2502.01145"},"observation_digest":"sha256:f6a3f5302095196b96328ff7c23d9333bc778f5f5919018c61f178058d566fe9","observation_id":"ff707f34-ae5a-4a0c-9304-9672744ff420","resolution":{"observed_at":"2026-08-09T16:30:39.167901Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T16:30:39.155552Z","title":"Unlike many traditional FMTL methods that assume homogeneous models across clients, our approach naturally accommodates heterogeneous model architectures and task objectives","venue":null,"work_id":"2e1602ac-2b54-4977-8e76-dd7702daf321","year":null},"citing_paper":{"arxiv_id":"2502.01145","last_updated":"2025-06-06T18:16:44Z","snapshot_observed_at":"2026-08-10T05:12:27.881591Z","submitted_at":"2025-02-03T08:25:34Z","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T16:30:39.109509Z"},"links":{"citing_paper":"/paper/2502.01145"},"observation_digest":"sha256:89cb9916def624084a2c74a7d2a7f9ce4158a824bba75eca36064e5580782e4a","observation_id":"37e3b8e5-3977-4029-b01f-a5121bfa08d8","resolution":{"observed_at":"2026-08-09T16:30:39.158719Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T16:30:39.144839Z","title":"Our approach allows for more nuanced modelling of inter-client relationships through the interaction space and restriction maps","venue":null,"work_id":"349bcfde-6d71-4eb9-a395-c87c29ffbcdb","year":2020},"citing_paper":{"arxiv_id":"2502.01145","last_updated":"2025-06-06T18:16:44Z","snapshot_observed_at":"2026-08-10T05:12:27.881591Z","submitted_at":"2025-02-03T08:25:34Z","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T16:30:39.112363Z"},"links":{"citing_paper":"/paper/2502.01145"},"observation_digest":"sha256:d2aac20ff7313a79d94b3acc57d057f9bff4be34aaa623fa5f3318f9e15eef6c","observation_id":"78500220-091e-4e0f-96b7-cf1424cb35c3","resolution":{"observed_at":"2026-08-09T16:30:39.149750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.01523","last_updated":"2020-07-14T08:12:35Z","snapshot_observed_at":"2026-08-14T23:16:03.815025Z","submitted_at":"2020-01-06T12:40:21Z","title":"Think Locally, Act Globally: Federated Learning with Local and Global Representations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.01523","snapshot_observed_at":"2026-08-09T16:30:39.078044Z","title":"Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.01145","last_updated":"2025-06-06T18:16:44Z","snapshot_observed_at":"2026-08-10T05:12:27.881591Z","submitted_at":"2025-02-03T08:25:34Z","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach","version":2},"reference_index":978,"source":"pdf_text","source_observed_at":"2026-08-09T16:30:39.078044Z"},"links":{"cited_paper":"/paper/2001.01523","citing_paper":"/paper/2502.01145"},"observation_digest":"sha256:02ef62c14137af5a0ea73614c242e50a36c3453966b13a3b127979eaa497449f","observation_id":"8e18b662-6abf-4f90-adef-f1e5dd2f3a15","resolution":{"observed_at":"2026-08-09T16:30:39.078044Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.01145","last_updated":"2025-06-06T18:16:44Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T05:12:27.881591Z","submitted_at":"2025-02-03T08:25:34Z","title":"Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach"},"reference_resolution":{"displayed":12,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":3,"verified_exact":0,"verified_fuzzy":9},"total_outbound_references":12},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 4 inbound Pith citation observations for arXiv:2502.01145."}