{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KIME3UTBPARSXGEFKORQBRQMSJ","short_pith_number":"pith:KIME3UTB","schema_version":"1.0","canonical_sha256":"52184dd26178232b988553a300c60c926e5dadd40fb4e6f9269e97b30adbe4e7","source":{"kind":"arxiv","id":"2505.20723","version":1},"attestation_state":"computed","paper":{"title":"LeDiFlow: Learned Distribution-guided Flow Matching to Accelerate Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Lennart Hilbert, Maximilian Beichter, Nils Friederich, Oliver Bringmann, Pascal Zwick, Ralf Mikut","submitted_at":"2025-05-27T05:07:37Z","abstract_excerpt":"Enhancing the efficiency of high-quality image generation using Diffusion Models (DMs) is a significant challenge due to the iterative nature of the process. Flow Matching (FM) is emerging as a powerful generative modeling paradigm based on a simulation-free training objective instead of a score-based one used in DMs. Typical FM approaches rely on a Gaussian distribution prior, which induces curved, conditional probability paths between the prior and target data distribution. These curved paths pose a challenge for the Ordinary Differential Equation (ODE) solver, requiring a large number of in"},"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":"2505.20723","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T05:07:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"88629a86a87c1d38a7a41cc43d4da3373136ef34bbb68fa8d7a7acb565216f9d","abstract_canon_sha256":"3a6a89229c3c6aa0e60c0feb239d0c87f4554bc029a48f0238bae122e6035ee8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:17.484135Z","signature_b64":"0HheS+LB7wzUF3b41VWL+LNeCd9hyWRJaVJJ53DYKf5dpI+uQbCn8PHix+6FnJX/zPf9iiyernGYXHN8QN3NBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52184dd26178232b988553a300c60c926e5dadd40fb4e6f9269e97b30adbe4e7","last_reissued_at":"2026-07-05T11:10:17.483666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:17.483666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LeDiFlow: Learned Distribution-guided Flow Matching to Accelerate Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Lennart Hilbert, Maximilian Beichter, Nils Friederich, Oliver Bringmann, Pascal Zwick, Ralf Mikut","submitted_at":"2025-05-27T05:07:37Z","abstract_excerpt":"Enhancing the efficiency of high-quality image generation using Diffusion Models (DMs) is a significant challenge due to the iterative nature of the process. Flow Matching (FM) is emerging as a powerful generative modeling paradigm based on a simulation-free training objective instead of a score-based one used in DMs. Typical FM approaches rely on a Gaussian distribution prior, which induces curved, conditional probability paths between the prior and target data distribution. These curved paths pose a challenge for the Ordinary Differential Equation (ODE) solver, requiring a large number of in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20723","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/2505.20723/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":"2505.20723","created_at":"2026-07-05T11:10:17.483726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20723v1","created_at":"2026-07-05T11:10:17.483726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20723","created_at":"2026-07-05T11:10:17.483726+00:00"},{"alias_kind":"pith_short_12","alias_value":"KIME3UTBPARS","created_at":"2026-07-05T11:10:17.483726+00:00"},{"alias_kind":"pith_short_16","alias_value":"KIME3UTBPARSXGEF","created_at":"2026-07-05T11:10:17.483726+00:00"},{"alias_kind":"pith_short_8","alias_value":"KIME3UTB","created_at":"2026-07-05T11:10:17.483726+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/KIME3UTBPARSXGEFKORQBRQMSJ","json":"https://pith.science/pith/KIME3UTBPARSXGEFKORQBRQMSJ.json","graph_json":"https://pith.science/api/pith-number/KIME3UTBPARSXGEFKORQBRQMSJ/graph.json","events_json":"https://pith.science/api/pith-number/KIME3UTBPARSXGEFKORQBRQMSJ/events.json","paper":"https://pith.science/paper/KIME3UTB"},"agent_actions":{"view_html":"https://pith.science/pith/KIME3UTBPARSXGEFKORQBRQMSJ","download_json":"https://pith.science/pith/KIME3UTBPARSXGEFKORQBRQMSJ.json","view_paper":"https://pith.science/paper/KIME3UTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20723&json=true","fetch_graph":"https://pith.science/api/pith-number/KIME3UTBPARSXGEFKORQBRQMSJ/graph.json","fetch_events":"https://pith.science/api/pith-number/KIME3UTBPARSXGEFKORQBRQMSJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KIME3UTBPARSXGEFKORQBRQMSJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KIME3UTBPARSXGEFKORQBRQMSJ/action/storage_attestation","attest_author":"https://pith.science/pith/KIME3UTBPARSXGEFKORQBRQMSJ/action/author_attestation","sign_citation":"https://pith.science/pith/KIME3UTBPARSXGEFKORQBRQMSJ/action/citation_signature","submit_replication":"https://pith.science/pith/KIME3UTBPARSXGEFKORQBRQMSJ/action/replication_record"}},"created_at":"2026-07-05T11:10:17.483726+00:00","updated_at":"2026-07-05T11:10:17.483726+00:00"}