{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PRMQLNCEGULOM2X53G3753KADO","short_pith_number":"pith:PRMQLNCE","schema_version":"1.0","canonical_sha256":"7c5905b4443516e66afdd9b7feed401b95f121e3ffa0dad1d542c4908489473f","source":{"kind":"arxiv","id":"2504.18897","version":1},"attestation_state":"computed","paper":{"title":"ReLU integral probability metric and its applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Insung Kong, Kunwoong Kim, Yongdai Kim, Yuha Park","submitted_at":"2025-04-26T11:49:43Z","abstract_excerpt":"We propose a parametric integral probability metric (IPM) to measure the discrepancy between two probability measures. The proposed IPM leverages a specific parametric family of discriminators, such as single-node neural networks with ReLU activation, to effectively distinguish between distributions, making it applicable in high-dimensional settings. By optimizing over the parameters of the chosen discriminator class, the proposed IPM demonstrates that its estimators have good convergence rates and can serve as a surrogate for other IPMs that use smooth nonparametric discriminator classes. We "},"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":"2504.18897","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-04-26T11:49:43Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"e6187b3cf12dfe4cdb8f3d863459797a42b591ea6165a580c0181c0393d7982b","abstract_canon_sha256":"b24d82f4b24a372e29913aaa17720b5d1a21ee4aec99361feb9b195a8266d5c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:23.332233Z","signature_b64":"2VgM6PbTzBGk8ixK+kKJGFzLNfvZL+VU72z5nEkJg4XxExQxMgk1Ml+03Qwrk9FysOBpPtf9eP+InjngBzOACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c5905b4443516e66afdd9b7feed401b95f121e3ffa0dad1d542c4908489473f","last_reissued_at":"2026-07-05T10:54:23.331638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:23.331638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReLU integral probability metric and its applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Insung Kong, Kunwoong Kim, Yongdai Kim, Yuha Park","submitted_at":"2025-04-26T11:49:43Z","abstract_excerpt":"We propose a parametric integral probability metric (IPM) to measure the discrepancy between two probability measures. The proposed IPM leverages a specific parametric family of discriminators, such as single-node neural networks with ReLU activation, to effectively distinguish between distributions, making it applicable in high-dimensional settings. By optimizing over the parameters of the chosen discriminator class, the proposed IPM demonstrates that its estimators have good convergence rates and can serve as a surrogate for other IPMs that use smooth nonparametric discriminator classes. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18897","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/2504.18897/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":"2504.18897","created_at":"2026-07-05T10:54:23.331703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.18897v1","created_at":"2026-07-05T10:54:23.331703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18897","created_at":"2026-07-05T10:54:23.331703+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRMQLNCEGULO","created_at":"2026-07-05T10:54:23.331703+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRMQLNCEGULOM2X5","created_at":"2026-07-05T10:54:23.331703+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRMQLNCE","created_at":"2026-07-05T10:54:23.331703+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/PRMQLNCEGULOM2X53G3753KADO","json":"https://pith.science/pith/PRMQLNCEGULOM2X53G3753KADO.json","graph_json":"https://pith.science/api/pith-number/PRMQLNCEGULOM2X53G3753KADO/graph.json","events_json":"https://pith.science/api/pith-number/PRMQLNCEGULOM2X53G3753KADO/events.json","paper":"https://pith.science/paper/PRMQLNCE"},"agent_actions":{"view_html":"https://pith.science/pith/PRMQLNCEGULOM2X53G3753KADO","download_json":"https://pith.science/pith/PRMQLNCEGULOM2X53G3753KADO.json","view_paper":"https://pith.science/paper/PRMQLNCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.18897&json=true","fetch_graph":"https://pith.science/api/pith-number/PRMQLNCEGULOM2X53G3753KADO/graph.json","fetch_events":"https://pith.science/api/pith-number/PRMQLNCEGULOM2X53G3753KADO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRMQLNCEGULOM2X53G3753KADO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRMQLNCEGULOM2X53G3753KADO/action/storage_attestation","attest_author":"https://pith.science/pith/PRMQLNCEGULOM2X53G3753KADO/action/author_attestation","sign_citation":"https://pith.science/pith/PRMQLNCEGULOM2X53G3753KADO/action/citation_signature","submit_replication":"https://pith.science/pith/PRMQLNCEGULOM2X53G3753KADO/action/replication_record"}},"created_at":"2026-07-05T10:54:23.331703+00:00","updated_at":"2026-07-05T10:54:23.331703+00:00"}