{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RT5JXJYJNFXU223RWSSY56IUKV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a991b671ffe87ab43e1210c145f2b6bcba097759a78e950fb86e934fa65621fd","cross_cats_sorted":["stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2026-05-15T13:27:24Z","title_canon_sha256":"e1641f9fa931143bd8bb533d779774600240d4e14583c5d232ad59ce1da6a832"},"schema_version":"1.0","source":{"id":"2605.15943","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15943","created_at":"2026-05-20T00:01:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15943v1","created_at":"2026-05-20T00:01:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15943","created_at":"2026-05-20T00:01:46Z"},{"alias_kind":"pith_short_12","alias_value":"RT5JXJYJNFXU","created_at":"2026-05-20T00:01:46Z"},{"alias_kind":"pith_short_16","alias_value":"RT5JXJYJNFXU223R","created_at":"2026-05-20T00:01:46Z"},{"alias_kind":"pith_short_8","alias_value":"RT5JXJYJ","created_at":"2026-05-20T00:01:46Z"}],"graph_snapshots":[{"event_id":"sha256:bf74bd203f357b9c5e340f68c96a4b0b37a6faf8309397c21b0d5d6a4434791d","target":"graph","created_at":"2026-05-20T00:01:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We develop novel algorithms based on (1) sampling from an exponential mechanism with a Lipschitz extension and (2) a general framework for constructing smooth projections from the space of undirected graphs to the space of bounded-degree graphs, which can then be combined with various edge-private algorithms. [...] We also develop novel lower bounds on the growth rate of ε required in order to achieve consistent community estimation under node privacy."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The analysis assumes that the underlying stochastic block model parameters (edge probabilities within and between communities) are such that consistent community recovery is possible even in the non-private case; the privacy mechanisms are then shown to preserve this consistency provided ε grows sufficiently fast. This modeling choice is stated in the problem setup and is used to define the target accuracy level for the private estimators."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Develops tractable node-differentially private algorithms for community estimation in fixed-community stochastic block models together with lower bounds on the privacy parameter ε needed for consistency."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Consistent community recovery in stochastic block models is achievable under node differential privacy using new polynomial-time algorithms that require the privacy parameter epsilon to grow at a controlled rate."}],"snapshot_sha256":"73e47bf276f3835c529cc66766b3958fb705d15f03e3da06295e232a2f31a46e"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"22d8047770df651359ed60bdfcd182801e2c89bcd581d949ae93751065b22276"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T19:31:19.035276Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T19:12:07.755521Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:44.885742Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T17:01:55.723328Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.15943/integrity.json","findings":[],"snapshot_sha256":"ac45b2c542490b7a3a2a025f8a55c678d5835dce5783b4e6ad12a7ef090401fe","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the classical problem of community recovery in stochastic block models with a fixed number of communities, with a twist: We seek algorithms that are stable with respect to node-wise changes in the graph structure, formally defined as a differential privacy constraint. The algorithms we develop are based on spectral clustering, where we introduce privacy to the community recovery pipeline in the form of directly privatizing the adjacency matrix; private PCA; private convex optimization; private low-rank matrix estimation; and private approximate subspace estimation. Straightforward app","authors_text":"Ethan D'souza, Laurentiu Marchis, Po-Ling Loh, Tom\\'a\\v{s} Fl\\'idr","cross_cats":["stat.ML","stat.TH"],"headline":"Consistent community recovery in stochastic block models is achievable under node differential privacy using new polynomial-time algorithms that require the privacy parameter epsilon to grow at a controlled rate.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2026-05-15T13:27:24Z","title":"Node-private community estimation in stochastic block models: Tractable algorithms and lower bounds"},"references":{"count":74,"internal_anchors":6,"resolved_work":74,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"E. Abbe. Community detection and stochastic block models: recent developments.Journal of Machine Learning Research, 18(177):1–86, 2018","work_id":"bcdc14ef-0f98-41f0-a1c6-066216c9008d","year":2018},{"cited_arxiv_id":"1304.6133","doi":"","is_internal_anchor":true,"ref_index":2,"title":"On Maximal Correlation, Hypercontractivity, and the Data Processing Inequality studied by Erkip and Cover","work_id":"468427fe-0bf9-4623-a5fa-5f6b9f99d089","year":2013},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Avella-Medina","work_id":"c9beaf3a-8215-4726-b312-b5c30543403b","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"M. Avella-Medina, C. Bradshaw, and P. Loh. Differentially private inference via noisy optimization. The Annals of Statistics, 51(5):2067–2092, 2023","work_id":"c6f6c27c-abf8-433a-aa75-064431191d16","year":2067},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"J. Blocki, A. Blum, A. Datta, and O. Sheffet. The Johnson-Lindenstrauss transform itself preserves differential privacy. In2012 IEEE 53rd Annual Symposium on Foundations of Computer Science, pages 410","work_id":"30cbd78d-84e4-41b6-aac8-2ec41026b283","year":2012}],"snapshot_sha256":"3e155ab23b3407b12f37992c3dc13bc7a325e8eb6b321bddb6a67ff1f8ac8725"},"source":{"id":"2605.15943","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T19:06:07.531719Z","id":"60832e0c-a77a-4cae-9376-930d0f8cf04b","model_set":{"reader":"grok-4.3"},"one_line_summary":"Develops tractable node-differentially private algorithms for community estimation in fixed-community stochastic block models together with lower bounds on the privacy parameter ε needed for consistency.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Consistent community recovery in stochastic block models is achievable under node differential privacy using new polynomial-time algorithms that require the privacy parameter epsilon to grow at a controlled rate.","strongest_claim":"We develop novel algorithms based on (1) sampling from an exponential mechanism with a Lipschitz extension and (2) a general framework for constructing smooth projections from the space of undirected graphs to the space of bounded-degree graphs, which can then be combined with various edge-private algorithms. [...] We also develop novel lower bounds on the growth rate of ε required in order to achieve consistent community estimation under node privacy.","weakest_assumption":"The analysis assumes that the underlying stochastic block model parameters (edge probabilities within and between communities) are such that consistent community recovery is possible even in the non-private case; the privacy mechanisms are then shown to preserve this consistency provided ε grows sufficiently fast. This modeling choice is stated in the problem setup and is used to define the target accuracy level for the private estimators."}},"verdict_id":"60832e0c-a77a-4cae-9376-930d0f8cf04b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9fb6320692809b4aeab848fc3c6af3db21fec5d2b87158877f65960ebc4638f0","target":"record","created_at":"2026-05-20T00:01:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a991b671ffe87ab43e1210c145f2b6bcba097759a78e950fb86e934fa65621fd","cross_cats_sorted":["stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2026-05-15T13:27:24Z","title_canon_sha256":"e1641f9fa931143bd8bb533d779774600240d4e14583c5d232ad59ce1da6a832"},"schema_version":"1.0","source":{"id":"2605.15943","kind":"arxiv","version":1}},"canonical_sha256":"8cfa9ba709696f4d6b71b4a58ef9145554408aa12dc556f97faa9eca3eb0dc8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8cfa9ba709696f4d6b71b4a58ef9145554408aa12dc556f97faa9eca3eb0dc8c","first_computed_at":"2026-05-20T00:01:46.021984Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:46.021984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qDfEpyMkc4h0gJV80YuTMYcHs9zWJUrE3I2SoG+Jnr9Vt0lL0JPhUM7aB0zLKMQYGQgUo9TSzO5vIVWhla0cCA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:46.022695Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15943","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fb6320692809b4aeab848fc3c6af3db21fec5d2b87158877f65960ebc4638f0","sha256:bf74bd203f357b9c5e340f68c96a4b0b37a6faf8309397c21b0d5d6a4434791d"],"state_sha256":"f5b8d00c7d27b0cff4225b1ae3a75fcdfedea077b8e4685c455630b21a671375"}