{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LMFEYTVVFCI4CLYQXRSOZORDJQ","short_pith_number":"pith:LMFEYTVV","schema_version":"1.0","canonical_sha256":"5b0a4c4eb52891c12f10bc64ecba234c32624bda400332c85129c835f7c6e8ae","source":{"kind":"arxiv","id":"2502.17436","version":2},"attestation_state":"computed","paper":{"title":"Towards Hierarchical Rectified Flow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Alex Schwing, Yichi Zhang, Yici Yan, Zhizhen Zhao","submitted_at":"2025-02-24T18:59:55Z","abstract_excerpt":"We formulate a hierarchical rectified flow to model data distributions. It hierarchically couples multiple ordinary differential equations (ODEs) and defines a time-differentiable stochastic process that generates a data distribution from a known source distribution. Each ODE resembles the ODE that is solved in a classic rectified flow, but differs in its domain, i.e., location, velocity, acceleration, etc. Unlike the classic rectified flow formulation, which formulates a single ODE in the location domain and only captures the expected velocity field (sufficient to capture a multi-modal data d"},"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":"2502.17436","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-24T18:59:55Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ca1e0280b2f12bcd658617582160a6be775abbd0483f13508f6f260bee03435a","abstract_canon_sha256":"a85f1bc0107a004acbdcfcdff0af616173f3f4735aa40b7f25bcbf7b6663b10b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:14.449572Z","signature_b64":"Aiv53iqBx5E66gPcWm0yyZIZGHtAA5D1pKbdpRVWTUUiOkskYKZ/RA3W1J4S6ZW6YnbjLowfDHp5RFxU/E5EAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b0a4c4eb52891c12f10bc64ecba234c32624bda400332c85129c835f7c6e8ae","last_reissued_at":"2026-07-05T10:22:14.449009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:14.449009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Hierarchical Rectified Flow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Alex Schwing, Yichi Zhang, Yici Yan, Zhizhen Zhao","submitted_at":"2025-02-24T18:59:55Z","abstract_excerpt":"We formulate a hierarchical rectified flow to model data distributions. It hierarchically couples multiple ordinary differential equations (ODEs) and defines a time-differentiable stochastic process that generates a data distribution from a known source distribution. Each ODE resembles the ODE that is solved in a classic rectified flow, but differs in its domain, i.e., location, velocity, acceleration, etc. Unlike the classic rectified flow formulation, which formulates a single ODE in the location domain and only captures the expected velocity field (sufficient to capture a multi-modal data d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17436","kind":"arxiv","version":2},"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/2502.17436/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":"2502.17436","created_at":"2026-07-05T10:22:14.449069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17436v2","created_at":"2026-07-05T10:22:14.449069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17436","created_at":"2026-07-05T10:22:14.449069+00:00"},{"alias_kind":"pith_short_12","alias_value":"LMFEYTVVFCI4","created_at":"2026-07-05T10:22:14.449069+00:00"},{"alias_kind":"pith_short_16","alias_value":"LMFEYTVVFCI4CLYQ","created_at":"2026-07-05T10:22:14.449069+00:00"},{"alias_kind":"pith_short_8","alias_value":"LMFEYTVV","created_at":"2026-07-05T10:22:14.449069+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04646","citing_title":"Training-Free Refinement of Flow Matching with Divergence-based Sampling","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LMFEYTVVFCI4CLYQXRSOZORDJQ","json":"https://pith.science/pith/LMFEYTVVFCI4CLYQXRSOZORDJQ.json","graph_json":"https://pith.science/api/pith-number/LMFEYTVVFCI4CLYQXRSOZORDJQ/graph.json","events_json":"https://pith.science/api/pith-number/LMFEYTVVFCI4CLYQXRSOZORDJQ/events.json","paper":"https://pith.science/paper/LMFEYTVV"},"agent_actions":{"view_html":"https://pith.science/pith/LMFEYTVVFCI4CLYQXRSOZORDJQ","download_json":"https://pith.science/pith/LMFEYTVVFCI4CLYQXRSOZORDJQ.json","view_paper":"https://pith.science/paper/LMFEYTVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17436&json=true","fetch_graph":"https://pith.science/api/pith-number/LMFEYTVVFCI4CLYQXRSOZORDJQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LMFEYTVVFCI4CLYQXRSOZORDJQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LMFEYTVVFCI4CLYQXRSOZORDJQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LMFEYTVVFCI4CLYQXRSOZORDJQ/action/storage_attestation","attest_author":"https://pith.science/pith/LMFEYTVVFCI4CLYQXRSOZORDJQ/action/author_attestation","sign_citation":"https://pith.science/pith/LMFEYTVVFCI4CLYQXRSOZORDJQ/action/citation_signature","submit_replication":"https://pith.science/pith/LMFEYTVVFCI4CLYQXRSOZORDJQ/action/replication_record"}},"created_at":"2026-07-05T10:22:14.449069+00:00","updated_at":"2026-07-05T10:22:14.449069+00:00"}