{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KZVMB6SJACTFM2KQSTSQHE6EDR","short_pith_number":"pith:KZVMB6SJ","schema_version":"1.0","canonical_sha256":"566ac0fa4900a656695094e50393c41c480f0c3747d90ad89775a554399dbac0","source":{"kind":"arxiv","id":"2504.14425","version":2},"attestation_state":"computed","paper":{"title":"Optimal Scheduling of Dynamic Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.CA","math.FA"],"primary_cat":"stat.ML","authors_text":"Jakob Zech, Panos Tsimpos, Youssef Marzouk, Zhi Ren","submitted_at":"2025-04-19T23:40:54Z","abstract_excerpt":"Flow-based methods for sampling and generative modeling use continuous-time dynamical systems to represent a {transport map} that pushes forward a source measure to a target measure. The introduction of a time axis provides considerable design freedom, and a central question is how to exploit this freedom. Though many popular methods seek straight line (i.e., zero acceleration) trajectories, we show here that a specific class of ``curved'' trajectories can significantly improve approximation and learning. In particular, we consider the unit-time interpolation of any given transport map $T$ and"},"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":"2504.14425","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-04-19T23:40:54Z","cross_cats_sorted":["cs.LG","math.CA","math.FA"],"title_canon_sha256":"d3c0e0512d647b844ff8e81df4ca69d8ce7593c14ad9569f2d90ea904badb452","abstract_canon_sha256":"cac83c383ada688d539b4e7d1586d6ace177e77ed671580d4c654374759ac088"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:27.603871Z","signature_b64":"x10qRx28gPApd5I6duuQkZjaPhvgqJQSs4HMnvijLhb/7A9n2KHijPZL6m4BkcSmAMiQ4l/E60GxaylE7Y4tDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"566ac0fa4900a656695094e50393c41c480f0c3747d90ad89775a554399dbac0","last_reissued_at":"2026-07-05T11:23:27.603271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:27.603271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Scheduling of Dynamic Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.CA","math.FA"],"primary_cat":"stat.ML","authors_text":"Jakob Zech, Panos Tsimpos, Youssef Marzouk, Zhi Ren","submitted_at":"2025-04-19T23:40:54Z","abstract_excerpt":"Flow-based methods for sampling and generative modeling use continuous-time dynamical systems to represent a {transport map} that pushes forward a source measure to a target measure. The introduction of a time axis provides considerable design freedom, and a central question is how to exploit this freedom. Though many popular methods seek straight line (i.e., zero acceleration) trajectories, we show here that a specific class of ``curved'' trajectories can significantly improve approximation and learning. In particular, we consider the unit-time interpolation of any given transport map $T$ and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14425","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/2504.14425/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":"2504.14425","created_at":"2026-07-05T11:23:27.603337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14425v2","created_at":"2026-07-05T11:23:27.603337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14425","created_at":"2026-07-05T11:23:27.603337+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZVMB6SJACTF","created_at":"2026-07-05T11:23:27.603337+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZVMB6SJACTFM2KQ","created_at":"2026-07-05T11:23:27.603337+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZVMB6SJ","created_at":"2026-07-05T11:23:27.603337+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.01629","citing_title":"Lipschitz-Guided Design of Interpolation Schedules in Generative Models","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16126","citing_title":"Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schr\\\"odinger Samplers","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08318","citing_title":"Is Flow Matching Just Trajectory Replay for Sequential Data?","ref_index":100,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KZVMB6SJACTFM2KQSTSQHE6EDR","json":"https://pith.science/pith/KZVMB6SJACTFM2KQSTSQHE6EDR.json","graph_json":"https://pith.science/api/pith-number/KZVMB6SJACTFM2KQSTSQHE6EDR/graph.json","events_json":"https://pith.science/api/pith-number/KZVMB6SJACTFM2KQSTSQHE6EDR/events.json","paper":"https://pith.science/paper/KZVMB6SJ"},"agent_actions":{"view_html":"https://pith.science/pith/KZVMB6SJACTFM2KQSTSQHE6EDR","download_json":"https://pith.science/pith/KZVMB6SJACTFM2KQSTSQHE6EDR.json","view_paper":"https://pith.science/paper/KZVMB6SJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14425&json=true","fetch_graph":"https://pith.science/api/pith-number/KZVMB6SJACTFM2KQSTSQHE6EDR/graph.json","fetch_events":"https://pith.science/api/pith-number/KZVMB6SJACTFM2KQSTSQHE6EDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZVMB6SJACTFM2KQSTSQHE6EDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZVMB6SJACTFM2KQSTSQHE6EDR/action/storage_attestation","attest_author":"https://pith.science/pith/KZVMB6SJACTFM2KQSTSQHE6EDR/action/author_attestation","sign_citation":"https://pith.science/pith/KZVMB6SJACTFM2KQSTSQHE6EDR/action/citation_signature","submit_replication":"https://pith.science/pith/KZVMB6SJACTFM2KQSTSQHE6EDR/action/replication_record"}},"created_at":"2026-07-05T11:23:27.603337+00:00","updated_at":"2026-07-05T11:23:27.603337+00:00"}