{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3SOW4HNOGUKWVOOPQZ2G5FRSVP","short_pith_number":"pith:3SOW4HNO","schema_version":"1.0","canonical_sha256":"dc9d6e1dae35156ab9cf86746e9632abf68a601aa114a5488e16c72230ea4ce7","source":{"kind":"arxiv","id":"2502.05725","version":1},"attestation_state":"computed","paper":{"title":"Predictive Coresets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.CO","authors_text":"Bernardo Flores","submitted_at":"2025-02-08T23:57:43Z","abstract_excerpt":"Modern data analysis often involves massive datasets with hundreds of thousands of observations, making traditional inference algorithms computationally prohibitive. Coresets are selection methods designed to choose a smaller subset of observations while maintaining similar learning performance. Conventional coreset approaches determine these weights by minimizing the Kullback-Leibler (KL) divergence between the likelihood functions of the full and weighted datasets; as a result, this makes them ill-posed for nonparametric models, where the likelihood is often intractable. We propose an altern"},"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":"2502.05725","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.CO","submitted_at":"2025-02-08T23:57:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"55a795076a7772e40c6d027747e2d844cc26d5d236bcb70db0a2f8e403d6111c","abstract_canon_sha256":"ed6f261a0307eb163e36215f93d2c65f4fb64d41a61580c03c5a229add5d5140"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:08.713320Z","signature_b64":"rHEXahkZLJSC7OD4B0aqXmAytpGMJ3Wivy/Lw/SV4Jzw8nQsFyZtjwPAs3wRWoYPo+3wcZAUZKnj6wNfZCI3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc9d6e1dae35156ab9cf86746e9632abf68a601aa114a5488e16c72230ea4ce7","last_reissued_at":"2026-07-05T10:13:08.712747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:08.712747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predictive Coresets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.CO","authors_text":"Bernardo Flores","submitted_at":"2025-02-08T23:57:43Z","abstract_excerpt":"Modern data analysis often involves massive datasets with hundreds of thousands of observations, making traditional inference algorithms computationally prohibitive. Coresets are selection methods designed to choose a smaller subset of observations while maintaining similar learning performance. Conventional coreset approaches determine these weights by minimizing the Kullback-Leibler (KL) divergence between the likelihood functions of the full and weighted datasets; as a result, this makes them ill-posed for nonparametric models, where the likelihood is often intractable. We propose an altern"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05725","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/2502.05725/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":"2502.05725","created_at":"2026-07-05T10:13:08.712809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05725v1","created_at":"2026-07-05T10:13:08.712809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05725","created_at":"2026-07-05T10:13:08.712809+00:00"},{"alias_kind":"pith_short_12","alias_value":"3SOW4HNOGUKW","created_at":"2026-07-05T10:13:08.712809+00:00"},{"alias_kind":"pith_short_16","alias_value":"3SOW4HNOGUKWVOOP","created_at":"2026-07-05T10:13:08.712809+00:00"},{"alias_kind":"pith_short_8","alias_value":"3SOW4HNO","created_at":"2026-07-05T10:13:08.712809+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/3SOW4HNOGUKWVOOPQZ2G5FRSVP","json":"https://pith.science/pith/3SOW4HNOGUKWVOOPQZ2G5FRSVP.json","graph_json":"https://pith.science/api/pith-number/3SOW4HNOGUKWVOOPQZ2G5FRSVP/graph.json","events_json":"https://pith.science/api/pith-number/3SOW4HNOGUKWVOOPQZ2G5FRSVP/events.json","paper":"https://pith.science/paper/3SOW4HNO"},"agent_actions":{"view_html":"https://pith.science/pith/3SOW4HNOGUKWVOOPQZ2G5FRSVP","download_json":"https://pith.science/pith/3SOW4HNOGUKWVOOPQZ2G5FRSVP.json","view_paper":"https://pith.science/paper/3SOW4HNO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05725&json=true","fetch_graph":"https://pith.science/api/pith-number/3SOW4HNOGUKWVOOPQZ2G5FRSVP/graph.json","fetch_events":"https://pith.science/api/pith-number/3SOW4HNOGUKWVOOPQZ2G5FRSVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3SOW4HNOGUKWVOOPQZ2G5FRSVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3SOW4HNOGUKWVOOPQZ2G5FRSVP/action/storage_attestation","attest_author":"https://pith.science/pith/3SOW4HNOGUKWVOOPQZ2G5FRSVP/action/author_attestation","sign_citation":"https://pith.science/pith/3SOW4HNOGUKWVOOPQZ2G5FRSVP/action/citation_signature","submit_replication":"https://pith.science/pith/3SOW4HNOGUKWVOOPQZ2G5FRSVP/action/replication_record"}},"created_at":"2026-07-05T10:13:08.712809+00:00","updated_at":"2026-07-05T10:13:08.712809+00:00"}