{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JA5XQIMZDOA5NUTEBPIH5EM2S3","short_pith_number":"pith:JA5XQIMZ","schema_version":"1.0","canonical_sha256":"483b7821991b81d6d2640bd07e919a96c856177951a4f745d2f5995d2f3b83d7","source":{"kind":"arxiv","id":"2607.13841","version":1},"attestation_state":"computed","paper":{"title":"Heavy-Tailed Flow Matching via Random Clocks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Haoyang Cao, Kenji Kawaguchi, Vladimir Braverman, Yezhen Wang, Zhouhao Yang","submitted_at":"2026-07-15T13:48:05Z","abstract_excerpt":"Heavy-tailed data arise in many domains where rare events carry disproportionate importance, such as imbalanced image datasets, financial returns, and weather extremes. Standard diffusion and flow-matching models typically begin from Gaussian noise or Gaussian source distributions, which yield tractable training targets but provide a poor inductive match for heavy-tailed data. We propose Heavy-Tailed Flow Matching via Random Clocks (HTFM), a framework that portrays heavy-tailed sources as mixtures of clock-conditioned Gaussian sources. Conditioning on a given clock path, the source distributio"},"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":"2607.13841","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T13:48:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bc51302d520c4d9f7ad9c90b1abaeb0b60fbc987300b18773008f2170d9060be","abstract_canon_sha256":"370840802bceeddd5f4e013bce4d3ffa8b3eda15d9a9cb07a32505beb24ebacb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T01:23:09.195949Z","signature_b64":"qzRa+Tf9ojq87Zg2SWwobg6AZ1l8HuDepJEQhH3rxoK1j24RrcYNbNzVsbLfHczjRligp6uVGaw/mPx1WcnpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"483b7821991b81d6d2640bd07e919a96c856177951a4f745d2f5995d2f3b83d7","last_reissued_at":"2026-07-16T01:23:09.195124Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T01:23:09.195124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heavy-Tailed Flow Matching via Random Clocks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Haoyang Cao, Kenji Kawaguchi, Vladimir Braverman, Yezhen Wang, Zhouhao Yang","submitted_at":"2026-07-15T13:48:05Z","abstract_excerpt":"Heavy-tailed data arise in many domains where rare events carry disproportionate importance, such as imbalanced image datasets, financial returns, and weather extremes. Standard diffusion and flow-matching models typically begin from Gaussian noise or Gaussian source distributions, which yield tractable training targets but provide a poor inductive match for heavy-tailed data. We propose Heavy-Tailed Flow Matching via Random Clocks (HTFM), a framework that portrays heavy-tailed sources as mixtures of clock-conditioned Gaussian sources. Conditioning on a given clock path, the source distributio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13841","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/2607.13841/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":"2607.13841","created_at":"2026-07-16T01:23:09.195560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13841v1","created_at":"2026-07-16T01:23:09.195560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13841","created_at":"2026-07-16T01:23:09.195560+00:00"},{"alias_kind":"pith_short_12","alias_value":"JA5XQIMZDOA5","created_at":"2026-07-16T01:23:09.195560+00:00"},{"alias_kind":"pith_short_16","alias_value":"JA5XQIMZDOA5NUTE","created_at":"2026-07-16T01:23:09.195560+00:00"},{"alias_kind":"pith_short_8","alias_value":"JA5XQIMZ","created_at":"2026-07-16T01:23:09.195560+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/JA5XQIMZDOA5NUTEBPIH5EM2S3","json":"https://pith.science/pith/JA5XQIMZDOA5NUTEBPIH5EM2S3.json","graph_json":"https://pith.science/api/pith-number/JA5XQIMZDOA5NUTEBPIH5EM2S3/graph.json","events_json":"https://pith.science/api/pith-number/JA5XQIMZDOA5NUTEBPIH5EM2S3/events.json","paper":"https://pith.science/paper/JA5XQIMZ"},"agent_actions":{"view_html":"https://pith.science/pith/JA5XQIMZDOA5NUTEBPIH5EM2S3","download_json":"https://pith.science/pith/JA5XQIMZDOA5NUTEBPIH5EM2S3.json","view_paper":"https://pith.science/paper/JA5XQIMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13841&json=true","fetch_graph":"https://pith.science/api/pith-number/JA5XQIMZDOA5NUTEBPIH5EM2S3/graph.json","fetch_events":"https://pith.science/api/pith-number/JA5XQIMZDOA5NUTEBPIH5EM2S3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JA5XQIMZDOA5NUTEBPIH5EM2S3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JA5XQIMZDOA5NUTEBPIH5EM2S3/action/storage_attestation","attest_author":"https://pith.science/pith/JA5XQIMZDOA5NUTEBPIH5EM2S3/action/author_attestation","sign_citation":"https://pith.science/pith/JA5XQIMZDOA5NUTEBPIH5EM2S3/action/citation_signature","submit_replication":"https://pith.science/pith/JA5XQIMZDOA5NUTEBPIH5EM2S3/action/replication_record"}},"created_at":"2026-07-16T01:23:09.195560+00:00","updated_at":"2026-07-16T01:23:09.195560+00:00"}