{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:SMRWMI4EJ24DNISBOPGQ3W3FI6","short_pith_number":"pith:SMRWMI4E","schema_version":"1.0","canonical_sha256":"93236623844eb836a24173cd0ddb654794d0843e2a1b403a1e15c2a194922901","source":{"kind":"arxiv","id":"1202.0302","version":3},"attestation_state":"computed","paper":{"title":"Kernels on Sample Sets via Nonparametric Divergence Estimates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Barnab\\'as P\\'oczos, Danica J. Sutherland, Jeff Schneider, Liang Xiong","submitted_at":"2012-02-01T21:36:40Z","abstract_excerpt":"Most machine learning algorithms, such as classification or regression, treat the individual data point as the object of interest. Here we consider extending machine learning algorithms to operate on groups of data points. We suggest treating a group of data points as an i.i.d. sample set from an underlying feature distribution for that group. Our approach employs kernel machines with a kernel on i.i.d. sample sets of vectors. We define certain kernel functions on pairs of distributions, and then use a nonparametric estimator to consistently estimate those functions based on sample sets. The p"},"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":"1202.0302","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-01T21:36:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5f3e3fbb6837e76d3975196e8bcdc0f7a2a4f845143768c7bc152588273262f4","abstract_canon_sha256":"4664c0c0f5aa272f309b24975941e4d3b5db5e65b7aea02a53d274fae8631a1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:06:45.898199Z","signature_b64":"kWpfSMXDcdDVXt6XUxW93p9pTSrg0vsWdQZtWLiAl/kbNg1uoPdGnOnBAR8ow+1ZuqUvK9mNSeA0p98YM4F0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93236623844eb836a24173cd0ddb654794d0843e2a1b403a1e15c2a194922901","last_reissued_at":"2026-07-05T02:06:45.897727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:06:45.897727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kernels on Sample Sets via Nonparametric Divergence Estimates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Barnab\\'as P\\'oczos, Danica J. Sutherland, Jeff Schneider, Liang Xiong","submitted_at":"2012-02-01T21:36:40Z","abstract_excerpt":"Most machine learning algorithms, such as classification or regression, treat the individual data point as the object of interest. Here we consider extending machine learning algorithms to operate on groups of data points. We suggest treating a group of data points as an i.i.d. sample set from an underlying feature distribution for that group. Our approach employs kernel machines with a kernel on i.i.d. sample sets of vectors. We define certain kernel functions on pairs of distributions, and then use a nonparametric estimator to consistently estimate those functions based on sample sets. The p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.0302","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/1202.0302/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":"1202.0302","created_at":"2026-07-05T02:06:45.897793+00:00"},{"alias_kind":"arxiv_version","alias_value":"1202.0302v3","created_at":"2026-07-05T02:06:45.897793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.0302","created_at":"2026-07-05T02:06:45.897793+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMRWMI4EJ24D","created_at":"2026-07-05T02:06:45.897793+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMRWMI4EJ24DNISB","created_at":"2026-07-05T02:06:45.897793+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMRWMI4E","created_at":"2026-07-05T02:06:45.897793+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21991","citing_title":"Machine Learning applications to Galaxy Clusters","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SMRWMI4EJ24DNISBOPGQ3W3FI6","json":"https://pith.science/pith/SMRWMI4EJ24DNISBOPGQ3W3FI6.json","graph_json":"https://pith.science/api/pith-number/SMRWMI4EJ24DNISBOPGQ3W3FI6/graph.json","events_json":"https://pith.science/api/pith-number/SMRWMI4EJ24DNISBOPGQ3W3FI6/events.json","paper":"https://pith.science/paper/SMRWMI4E"},"agent_actions":{"view_html":"https://pith.science/pith/SMRWMI4EJ24DNISBOPGQ3W3FI6","download_json":"https://pith.science/pith/SMRWMI4EJ24DNISBOPGQ3W3FI6.json","view_paper":"https://pith.science/paper/SMRWMI4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1202.0302&json=true","fetch_graph":"https://pith.science/api/pith-number/SMRWMI4EJ24DNISBOPGQ3W3FI6/graph.json","fetch_events":"https://pith.science/api/pith-number/SMRWMI4EJ24DNISBOPGQ3W3FI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMRWMI4EJ24DNISBOPGQ3W3FI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMRWMI4EJ24DNISBOPGQ3W3FI6/action/storage_attestation","attest_author":"https://pith.science/pith/SMRWMI4EJ24DNISBOPGQ3W3FI6/action/author_attestation","sign_citation":"https://pith.science/pith/SMRWMI4EJ24DNISBOPGQ3W3FI6/action/citation_signature","submit_replication":"https://pith.science/pith/SMRWMI4EJ24DNISBOPGQ3W3FI6/action/replication_record"}},"created_at":"2026-07-05T02:06:45.897793+00:00","updated_at":"2026-07-05T02:06:45.897793+00:00"}