{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G374UOB6B5M2QFC4ZLH2UZFBHP","short_pith_number":"pith:G374UOB6","schema_version":"1.0","canonical_sha256":"36ffca383e0f59a8145ccacfaa64a13bc3e2a147d5bb3123c95c7ce6e0a54a18","source":{"kind":"arxiv","id":"2607.24732","version":1},"attestation_state":"computed","paper":{"title":"Learning Distributions from Multiple Data Providers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG","stat.ML"],"primary_cat":"cs.DS","authors_text":"Amin Saberi, Grigoris Velegkas, Jon Kleinberg, Xizhi Tan","submitted_at":"2026-07-27T17:57:16Z","abstract_excerpt":"Motivated by learning from heterogeneous and overlapping data providers, we study a stylized model of distribution learning from restricted conditional samples. The goal is to learn an unknown distribution $p$ on a finite domain $[n]$. The learner is given a fixed family of queryable sets $\\mathscr{S} \\subseteq 2^{[n]}$, and each query to $S \\in \\mathscr{S}$ returns an independent sample from the conditional distribution $p(\\cdot \\mid S)$.\n  Learnability is governed by the co-occurrence graph associated with $\\mathscr{S}$: two domain elements are adjacent if they appear together in some querya"},"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":"2607.24732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2026-07-27T17:57:16Z","cross_cats_sorted":["cs.GT","cs.LG","stat.ML"],"title_canon_sha256":"a2f4750f7a5f41d41344aa6229ecdcf345f138759f9ffcc6a790092fb19d672e","abstract_canon_sha256":"5f2dd544b3c12ddd91c00dfae4e09157fca584275f445cdd9cdfb9555139574d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:24:24.763158Z","signature_b64":"0Y+uamBkVM8D4nRK0LafJOvTXaUrDJgpeQqVrFMy2MkH4FxsuGmDhguWDm62bzXXkzn31orNWueUB1lO7seoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36ffca383e0f59a8145ccacfaa64a13bc3e2a147d5bb3123c95c7ce6e0a54a18","last_reissued_at":"2026-07-28T02:24:24.762320Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:24:24.762320Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Distributions from Multiple Data Providers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG","stat.ML"],"primary_cat":"cs.DS","authors_text":"Amin Saberi, Grigoris Velegkas, Jon Kleinberg, Xizhi Tan","submitted_at":"2026-07-27T17:57:16Z","abstract_excerpt":"Motivated by learning from heterogeneous and overlapping data providers, we study a stylized model of distribution learning from restricted conditional samples. The goal is to learn an unknown distribution $p$ on a finite domain $[n]$. The learner is given a fixed family of queryable sets $\\mathscr{S} \\subseteq 2^{[n]}$, and each query to $S \\in \\mathscr{S}$ returns an independent sample from the conditional distribution $p(\\cdot \\mid S)$.\n  Learnability is governed by the co-occurrence graph associated with $\\mathscr{S}$: two domain elements are adjacent if they appear together in some querya"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24732","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/2607.24732/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":"2607.24732","created_at":"2026-07-28T02:24:24.762760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24732v1","created_at":"2026-07-28T02:24:24.762760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24732","created_at":"2026-07-28T02:24:24.762760+00:00"},{"alias_kind":"pith_short_12","alias_value":"G374UOB6B5M2","created_at":"2026-07-28T02:24:24.762760+00:00"},{"alias_kind":"pith_short_16","alias_value":"G374UOB6B5M2QFC4","created_at":"2026-07-28T02:24:24.762760+00:00"},{"alias_kind":"pith_short_8","alias_value":"G374UOB6","created_at":"2026-07-28T02:24:24.762760+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G374UOB6B5M2QFC4ZLH2UZFBHP","json":"https://pith.science/pith/G374UOB6B5M2QFC4ZLH2UZFBHP.json","graph_json":"https://pith.science/api/pith-number/G374UOB6B5M2QFC4ZLH2UZFBHP/graph.json","events_json":"https://pith.science/api/pith-number/G374UOB6B5M2QFC4ZLH2UZFBHP/events.json","paper":"https://pith.science/paper/G374UOB6"},"agent_actions":{"view_html":"https://pith.science/pith/G374UOB6B5M2QFC4ZLH2UZFBHP","download_json":"https://pith.science/pith/G374UOB6B5M2QFC4ZLH2UZFBHP.json","view_paper":"https://pith.science/paper/G374UOB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24732&json=true","fetch_graph":"https://pith.science/api/pith-number/G374UOB6B5M2QFC4ZLH2UZFBHP/graph.json","fetch_events":"https://pith.science/api/pith-number/G374UOB6B5M2QFC4ZLH2UZFBHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G374UOB6B5M2QFC4ZLH2UZFBHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G374UOB6B5M2QFC4ZLH2UZFBHP/action/storage_attestation","attest_author":"https://pith.science/pith/G374UOB6B5M2QFC4ZLH2UZFBHP/action/author_attestation","sign_citation":"https://pith.science/pith/G374UOB6B5M2QFC4ZLH2UZFBHP/action/citation_signature","submit_replication":"https://pith.science/pith/G374UOB6B5M2QFC4ZLH2UZFBHP/action/replication_record"}},"created_at":"2026-07-28T02:24:24.762760+00:00","updated_at":"2026-07-28T02:24:24.762760+00:00"}