{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4YSVEDLRC5DNTMNMJFFG2XHBN7","short_pith_number":"pith:4YSVEDLR","schema_version":"1.0","canonical_sha256":"e625520d711746d9b1ac494a6d5ce16fd074f76c87e15299cd622f6a533ea8b1","source":{"kind":"arxiv","id":"2506.02221","version":1},"attestation_state":"computed","paper":{"title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bj\\\"orn Ommer, Frank Fundel, Johannes Schusterbauer, Ming Gui","submitted_at":"2025-06-02T20:05:05Z","abstract_excerpt":"Diffusion models have revolutionized generative tasks through high-fidelity outputs, yet flow matching (FM) offers faster inference and empirical performance gains. However, current foundation FM models are computationally prohibitive for finetuning, while diffusion models like Stable Diffusion benefit from efficient architectures and ecosystem support. This work addresses the critical challenge of efficiently transferring knowledge from pre-trained diffusion models to flow matching. We propose Diff2Flow, a novel framework that systematically bridges diffusion and FM paradigms by rescaling tim"},"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":"2506.02221","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T20:05:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f3f8989c15f05ddd36b3e8754840c6e54f26e87a10b2f04b43337474abe5fcd1","abstract_canon_sha256":"66966c8da1653773d4c8670b703b4f522f0c2adc19736bd8801a0e9d1db8e437"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:34.727307Z","signature_b64":"T5pyqQyo2htD/sUM39Ph59+PcpnSOlkCM+SEvsU4lEsWuPzYFRc1b8GWjeb3AYPUzGL8mweHRiJs/4u+5wfYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e625520d711746d9b1ac494a6d5ce16fd074f76c87e15299cd622f6a533ea8b1","last_reissued_at":"2026-07-05T11:14:34.726712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:34.726712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bj\\\"orn Ommer, Frank Fundel, Johannes Schusterbauer, Ming Gui","submitted_at":"2025-06-02T20:05:05Z","abstract_excerpt":"Diffusion models have revolutionized generative tasks through high-fidelity outputs, yet flow matching (FM) offers faster inference and empirical performance gains. However, current foundation FM models are computationally prohibitive for finetuning, while diffusion models like Stable Diffusion benefit from efficient architectures and ecosystem support. This work addresses the critical challenge of efficiently transferring knowledge from pre-trained diffusion models to flow matching. We propose Diff2Flow, a novel framework that systematically bridges diffusion and FM paradigms by rescaling tim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02221","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/2506.02221/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":"2506.02221","created_at":"2026-07-05T11:14:34.726786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02221v1","created_at":"2026-07-05T11:14:34.726786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02221","created_at":"2026-07-05T11:14:34.726786+00:00"},{"alias_kind":"pith_short_12","alias_value":"4YSVEDLRC5DN","created_at":"2026-07-05T11:14:34.726786+00:00"},{"alias_kind":"pith_short_16","alias_value":"4YSVEDLRC5DNTMNM","created_at":"2026-07-05T11:14:34.726786+00:00"},{"alias_kind":"pith_short_8","alias_value":"4YSVEDLR","created_at":"2026-07-05T11:14:34.726786+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.32020","citing_title":"Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28185","citing_title":"Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4YSVEDLRC5DNTMNMJFFG2XHBN7","json":"https://pith.science/pith/4YSVEDLRC5DNTMNMJFFG2XHBN7.json","graph_json":"https://pith.science/api/pith-number/4YSVEDLRC5DNTMNMJFFG2XHBN7/graph.json","events_json":"https://pith.science/api/pith-number/4YSVEDLRC5DNTMNMJFFG2XHBN7/events.json","paper":"https://pith.science/paper/4YSVEDLR"},"agent_actions":{"view_html":"https://pith.science/pith/4YSVEDLRC5DNTMNMJFFG2XHBN7","download_json":"https://pith.science/pith/4YSVEDLRC5DNTMNMJFFG2XHBN7.json","view_paper":"https://pith.science/paper/4YSVEDLR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02221&json=true","fetch_graph":"https://pith.science/api/pith-number/4YSVEDLRC5DNTMNMJFFG2XHBN7/graph.json","fetch_events":"https://pith.science/api/pith-number/4YSVEDLRC5DNTMNMJFFG2XHBN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4YSVEDLRC5DNTMNMJFFG2XHBN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4YSVEDLRC5DNTMNMJFFG2XHBN7/action/storage_attestation","attest_author":"https://pith.science/pith/4YSVEDLRC5DNTMNMJFFG2XHBN7/action/author_attestation","sign_citation":"https://pith.science/pith/4YSVEDLRC5DNTMNMJFFG2XHBN7/action/citation_signature","submit_replication":"https://pith.science/pith/4YSVEDLRC5DNTMNMJFFG2XHBN7/action/replication_record"}},"created_at":"2026-07-05T11:14:34.726786+00:00","updated_at":"2026-07-05T11:14:34.726786+00:00"}