{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GBO5NY6P73FD4SV3OIS4EUTG7A","short_pith_number":"pith:GBO5NY6P","schema_version":"1.0","canonical_sha256":"305dd6e3cffeca3e4abb7225c25266f815029dfa247ae0ca75e6b51aa1c74248","source":{"kind":"arxiv","id":"2404.12290","version":3},"attestation_state":"computed","paper":{"title":"Debiased Distribution Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.CO","stat.ME"],"primary_cat":"stat.ML","authors_text":"Lester Mackey, Lingxiao Li, Raaz Dwivedi","submitted_at":"2024-04-18T16:11:16Z","abstract_excerpt":"Modern compression methods can summarize a target distribution $\\mathbb{P}$ more succinctly than i.i.d. sampling but require access to a low-bias input sequence like a Markov chain converging quickly to $\\mathbb{P}$. We introduce a new suite of compression methods suitable for compression with biased input sequences. Given $n$ points targeting the wrong distribution and quadratic time, Stein kernel thinning (SKT) returns $\\sqrt{n}$ equal-weighted points with $\\widetilde{O}(n^{-1/2})$ maximum mean discrepancy (MMD) to $\\mathbb{P}$. For larger-scale compression tasks, low-rank SKT achieves the s"},"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":"2404.12290","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-04-18T16:11:16Z","cross_cats_sorted":["cs.LG","stat.CO","stat.ME"],"title_canon_sha256":"7df16c3b304671416f3fe583dd4717648b2dc4dd28c2bcf8c3d9ce24f4b60565","abstract_canon_sha256":"c5fca42ab7481bfbcd52a2771c2d0663eee3f19f54f11a9c73697ce714fd6f05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:55.892977Z","signature_b64":"nhBttRzw8hhi+jmrHyOz8iMvo0APo+aNozZA691axVMpesKTrbAOhae0Uw6rpiS6/iR7V+/M4oHvmtUob5OJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"305dd6e3cffeca3e4abb7225c25266f815029dfa247ae0ca75e6b51aa1c74248","last_reissued_at":"2026-07-05T08:50:55.892569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:55.892569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Debiased Distribution Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.CO","stat.ME"],"primary_cat":"stat.ML","authors_text":"Lester Mackey, Lingxiao Li, Raaz Dwivedi","submitted_at":"2024-04-18T16:11:16Z","abstract_excerpt":"Modern compression methods can summarize a target distribution $\\mathbb{P}$ more succinctly than i.i.d. sampling but require access to a low-bias input sequence like a Markov chain converging quickly to $\\mathbb{P}$. We introduce a new suite of compression methods suitable for compression with biased input sequences. Given $n$ points targeting the wrong distribution and quadratic time, Stein kernel thinning (SKT) returns $\\sqrt{n}$ equal-weighted points with $\\widetilde{O}(n^{-1/2})$ maximum mean discrepancy (MMD) to $\\mathbb{P}$. For larger-scale compression tasks, low-rank SKT achieves the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12290","kind":"arxiv","version":3},"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/2404.12290/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":"2404.12290","created_at":"2026-07-05T08:50:55.892621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.12290v3","created_at":"2026-07-05T08:50:55.892621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12290","created_at":"2026-07-05T08:50:55.892621+00:00"},{"alias_kind":"pith_short_12","alias_value":"GBO5NY6P73FD","created_at":"2026-07-05T08:50:55.892621+00:00"},{"alias_kind":"pith_short_16","alias_value":"GBO5NY6P73FD4SV3","created_at":"2026-07-05T08:50:55.892621+00:00"},{"alias_kind":"pith_short_8","alias_value":"GBO5NY6P","created_at":"2026-07-05T08:50:55.892621+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.20194","citing_title":"Coreset selection for the Sinkhorn divergence and generic smooth divergences","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GBO5NY6P73FD4SV3OIS4EUTG7A","json":"https://pith.science/pith/GBO5NY6P73FD4SV3OIS4EUTG7A.json","graph_json":"https://pith.science/api/pith-number/GBO5NY6P73FD4SV3OIS4EUTG7A/graph.json","events_json":"https://pith.science/api/pith-number/GBO5NY6P73FD4SV3OIS4EUTG7A/events.json","paper":"https://pith.science/paper/GBO5NY6P"},"agent_actions":{"view_html":"https://pith.science/pith/GBO5NY6P73FD4SV3OIS4EUTG7A","download_json":"https://pith.science/pith/GBO5NY6P73FD4SV3OIS4EUTG7A.json","view_paper":"https://pith.science/paper/GBO5NY6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.12290&json=true","fetch_graph":"https://pith.science/api/pith-number/GBO5NY6P73FD4SV3OIS4EUTG7A/graph.json","fetch_events":"https://pith.science/api/pith-number/GBO5NY6P73FD4SV3OIS4EUTG7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GBO5NY6P73FD4SV3OIS4EUTG7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GBO5NY6P73FD4SV3OIS4EUTG7A/action/storage_attestation","attest_author":"https://pith.science/pith/GBO5NY6P73FD4SV3OIS4EUTG7A/action/author_attestation","sign_citation":"https://pith.science/pith/GBO5NY6P73FD4SV3OIS4EUTG7A/action/citation_signature","submit_replication":"https://pith.science/pith/GBO5NY6P73FD4SV3OIS4EUTG7A/action/replication_record"}},"created_at":"2026-07-05T08:50:55.892621+00:00","updated_at":"2026-07-05T08:50:55.892621+00:00"}