{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GTBPLFLT63KTPFSWDNESV4NH2S","short_pith_number":"pith:GTBPLFLT","schema_version":"1.0","canonical_sha256":"34c2f59573f6d53796561b492af1a7d487a27c84cf5c137fe2343ca9ae346b38","source":{"kind":"arxiv","id":"2110.10582","version":1},"attestation_state":"computed","paper":{"title":"Distributionally Robust Semi-Supervised Learning Over Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alireza Sadeghi, Bingcong Li, Georgios B. Giannakis, Meng Ma","submitted_at":"2021-10-20T14:23:54Z","abstract_excerpt":"Semi-supervised learning (SSL) over graph-structured data emerges in many network science applications. To efficiently manage learning over graphs, variants of graph neural networks (GNNs) have been developed recently. By succinctly encoding local graph structures and features of nodes, state-of-the-art GNNs can scale linearly with the size of graph. Despite their success in practice, most of existing methods are unable to handle graphs with uncertain nodal attributes. Specifically whenever mismatches between training and testing data distribution exists, these models fail in practice. Challen"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2110.10582","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-20T14:23:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"01e53d50c537c35da7f891607cdeda0ddc68a48c255ef649bfbb67c31e7bcdec","abstract_canon_sha256":"53e3fde0912bc51ba2ffbb3f659e18d73dfe76c4c2edded2b6d1e56d74217ddd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:19.025483Z","signature_b64":"v3VA8w0Rsk5nPPZfXO44+4OAiVn3xgFogMoiGEuWInOewuRiEEo/NWdRGHb+DsEsPlmdbqWfQwkUK+gHzwG/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34c2f59573f6d53796561b492af1a7d487a27c84cf5c137fe2343ca9ae346b38","last_reissued_at":"2026-07-05T03:24:19.025040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:19.025040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributionally Robust Semi-Supervised Learning Over Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alireza Sadeghi, Bingcong Li, Georgios B. Giannakis, Meng Ma","submitted_at":"2021-10-20T14:23:54Z","abstract_excerpt":"Semi-supervised learning (SSL) over graph-structured data emerges in many network science applications. To efficiently manage learning over graphs, variants of graph neural networks (GNNs) have been developed recently. By succinctly encoding local graph structures and features of nodes, state-of-the-art GNNs can scale linearly with the size of graph. Despite their success in practice, most of existing methods are unable to handle graphs with uncertain nodal attributes. Specifically whenever mismatches between training and testing data distribution exists, these models fail in practice. Challen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10582","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.10582/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2110.10582","created_at":"2026-07-05T03:24:19.025110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.10582v1","created_at":"2026-07-05T03:24:19.025110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10582","created_at":"2026-07-05T03:24:19.025110+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTBPLFLT63KT","created_at":"2026-07-05T03:24:19.025110+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTBPLFLT63KTPFSW","created_at":"2026-07-05T03:24:19.025110+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTBPLFLT","created_at":"2026-07-05T03:24:19.025110+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00305","citing_title":"diffIRM: A Diffusion-Augmented Invariant Risk Minimization Framework for Spatiotemporal Prediction over Graphs","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GTBPLFLT63KTPFSWDNESV4NH2S","json":"https://pith.science/pith/GTBPLFLT63KTPFSWDNESV4NH2S.json","graph_json":"https://pith.science/api/pith-number/GTBPLFLT63KTPFSWDNESV4NH2S/graph.json","events_json":"https://pith.science/api/pith-number/GTBPLFLT63KTPFSWDNESV4NH2S/events.json","paper":"https://pith.science/paper/GTBPLFLT"},"agent_actions":{"view_html":"https://pith.science/pith/GTBPLFLT63KTPFSWDNESV4NH2S","download_json":"https://pith.science/pith/GTBPLFLT63KTPFSWDNESV4NH2S.json","view_paper":"https://pith.science/paper/GTBPLFLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.10582&json=true","fetch_graph":"https://pith.science/api/pith-number/GTBPLFLT63KTPFSWDNESV4NH2S/graph.json","fetch_events":"https://pith.science/api/pith-number/GTBPLFLT63KTPFSWDNESV4NH2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTBPLFLT63KTPFSWDNESV4NH2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTBPLFLT63KTPFSWDNESV4NH2S/action/storage_attestation","attest_author":"https://pith.science/pith/GTBPLFLT63KTPFSWDNESV4NH2S/action/author_attestation","sign_citation":"https://pith.science/pith/GTBPLFLT63KTPFSWDNESV4NH2S/action/citation_signature","submit_replication":"https://pith.science/pith/GTBPLFLT63KTPFSWDNESV4NH2S/action/replication_record"}},"created_at":"2026-07-05T03:24:19.025110+00:00","updated_at":"2026-07-05T03:24:19.025110+00:00"}