{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:R4DSVE6FEPTDA6PXMKGMTZAWAB","short_pith_number":"pith:R4DSVE6F","schema_version":"1.0","canonical_sha256":"8f072a93c523e63079f7628cc9e416007f0f3c03c49a0968febffdc2a0481042","source":{"kind":"arxiv","id":"1711.08113","version":1},"attestation_state":"computed","paper":{"title":"Learning Discrete Distributions from Untrusted Batches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gregory Valiant, Mingda Qiao","submitted_at":"2017-11-22T02:39:21Z","abstract_excerpt":"We consider the problem of learning a discrete distribution in the presence of an $\\epsilon$ fraction of malicious data sources. Specifically, we consider the setting where there is some underlying distribution, $p$, and each data source provides a batch of $\\ge k$ samples, with the guarantee that at least a $(1-\\epsilon)$ fraction of the sources draw their samples from a distribution with total variation distance at most $\\eta$ from $p$. We make no assumptions on the data provided by the remaining $\\epsilon$ fraction of sources--this data can even be chosen as an adversarial function of the $"},"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":"1711.08113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-22T02:39:21Z","cross_cats_sorted":[],"title_canon_sha256":"3d8307f571e4bc31260f8ce31d452327ba7583d5d9400110289f2a32579b2977","abstract_canon_sha256":"35115cf2d4806e454b32a3d498e9196f855471401a34f4a67c7513a869feb1a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:50.650329Z","signature_b64":"izIZ8hN3F/utqhdYA2Pzz3myFJDJmoaQ8oMAKuYTblViNqfWYMUkwaiuiUXWAgXAFctaq+F/dxyoYlDTJ0fRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f072a93c523e63079f7628cc9e416007f0f3c03c49a0968febffdc2a0481042","last_reissued_at":"2026-05-18T00:29:50.649840Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:50.649840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Discrete Distributions from Untrusted Batches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gregory Valiant, Mingda Qiao","submitted_at":"2017-11-22T02:39:21Z","abstract_excerpt":"We consider the problem of learning a discrete distribution in the presence of an $\\epsilon$ fraction of malicious data sources. Specifically, we consider the setting where there is some underlying distribution, $p$, and each data source provides a batch of $\\ge k$ samples, with the guarantee that at least a $(1-\\epsilon)$ fraction of the sources draw their samples from a distribution with total variation distance at most $\\eta$ from $p$. We make no assumptions on the data provided by the remaining $\\epsilon$ fraction of sources--this data can even be chosen as an adversarial function of the $"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08113","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":""},"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":"1711.08113","created_at":"2026-05-18T00:29:50.649915+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.08113v1","created_at":"2026-05-18T00:29:50.649915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08113","created_at":"2026-05-18T00:29:50.649915+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4DSVE6FEPTD","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4DSVE6FEPTDA6PX","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4DSVE6F","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.02972","citing_title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4DSVE6FEPTDA6PXMKGMTZAWAB","json":"https://pith.science/pith/R4DSVE6FEPTDA6PXMKGMTZAWAB.json","graph_json":"https://pith.science/api/pith-number/R4DSVE6FEPTDA6PXMKGMTZAWAB/graph.json","events_json":"https://pith.science/api/pith-number/R4DSVE6FEPTDA6PXMKGMTZAWAB/events.json","paper":"https://pith.science/paper/R4DSVE6F"},"agent_actions":{"view_html":"https://pith.science/pith/R4DSVE6FEPTDA6PXMKGMTZAWAB","download_json":"https://pith.science/pith/R4DSVE6FEPTDA6PXMKGMTZAWAB.json","view_paper":"https://pith.science/paper/R4DSVE6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.08113&json=true","fetch_graph":"https://pith.science/api/pith-number/R4DSVE6FEPTDA6PXMKGMTZAWAB/graph.json","fetch_events":"https://pith.science/api/pith-number/R4DSVE6FEPTDA6PXMKGMTZAWAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4DSVE6FEPTDA6PXMKGMTZAWAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4DSVE6FEPTDA6PXMKGMTZAWAB/action/storage_attestation","attest_author":"https://pith.science/pith/R4DSVE6FEPTDA6PXMKGMTZAWAB/action/author_attestation","sign_citation":"https://pith.science/pith/R4DSVE6FEPTDA6PXMKGMTZAWAB/action/citation_signature","submit_replication":"https://pith.science/pith/R4DSVE6FEPTDA6PXMKGMTZAWAB/action/replication_record"}},"created_at":"2026-05-18T00:29:50.649915+00:00","updated_at":"2026-05-18T00:29:50.649915+00:00"}