{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BZXL4ZNPLJHR6OGSXJOKL425NE","short_pith_number":"pith:BZXL4ZNP","schema_version":"1.0","canonical_sha256":"0e6ebe65af5a4f1f38d2ba5ca5f35d691fe0762fe10f84ba83a75c38297ee2df","source":{"kind":"arxiv","id":"2312.16414","version":3},"attestation_state":"computed","paper":{"title":"Bellman Optimal Stepsize Straightening of Flow-Matching Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bao Nguyen, Binh Nguyen, Viet Anh Nguyen","submitted_at":"2023-12-27T05:20:20Z","abstract_excerpt":"Flow matching is a powerful framework for generating high-quality samples in various applications, especially image synthesis. However, the intensive computational demands of these models, especially during the finetuning process and sampling processes, pose significant challenges for low-resource scenarios. This paper introduces Bellman Optimal Stepsize Straightening (BOSS) technique for distilling flow-matching generative models: it aims specifically for a few-step efficient image sampling while adhering to a computational budget constraint. First, this technique involves a dynamic programmi"},"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":"2312.16414","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-27T05:20:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"95426540f361d66bde79a6b85cf5efa3d56d6fb0ae1621a462db5f2c8ff3b4ea","abstract_canon_sha256":"4fa7e50cbf5eba88e129ba20907c73266c54a1bd76f68a8e37148e94b87fdaf3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:07.579881Z","signature_b64":"bk1i5BrO9bvrx6c2+k0QmaFYhP2wW+uAGDUZQBD1e/c0gxsNFo5B0VF6sVq+6RLM3KTCEW/r8i1TkVhqexLhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e6ebe65af5a4f1f38d2ba5ca5f35d691fe0762fe10f84ba83a75c38297ee2df","last_reissued_at":"2026-07-05T07:47:07.579392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:07.579392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bellman Optimal Stepsize Straightening of Flow-Matching Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bao Nguyen, Binh Nguyen, Viet Anh Nguyen","submitted_at":"2023-12-27T05:20:20Z","abstract_excerpt":"Flow matching is a powerful framework for generating high-quality samples in various applications, especially image synthesis. However, the intensive computational demands of these models, especially during the finetuning process and sampling processes, pose significant challenges for low-resource scenarios. This paper introduces Bellman Optimal Stepsize Straightening (BOSS) technique for distilling flow-matching generative models: it aims specifically for a few-step efficient image sampling while adhering to a computational budget constraint. First, this technique involves a dynamic programmi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16414","kind":"arxiv","version":3},"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/2312.16414/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":"2312.16414","created_at":"2026-07-05T07:47:07.579450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.16414v3","created_at":"2026-07-05T07:47:07.579450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16414","created_at":"2026-07-05T07:47:07.579450+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZXL4ZNPLJHR","created_at":"2026-07-05T07:47:07.579450+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZXL4ZNPLJHR6OGS","created_at":"2026-07-05T07:47:07.579450+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZXL4ZNP","created_at":"2026-07-05T07:47:07.579450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.11361","citing_title":"Block Flow: Learning Straight Flow on Data Blocks","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BZXL4ZNPLJHR6OGSXJOKL425NE","json":"https://pith.science/pith/BZXL4ZNPLJHR6OGSXJOKL425NE.json","graph_json":"https://pith.science/api/pith-number/BZXL4ZNPLJHR6OGSXJOKL425NE/graph.json","events_json":"https://pith.science/api/pith-number/BZXL4ZNPLJHR6OGSXJOKL425NE/events.json","paper":"https://pith.science/paper/BZXL4ZNP"},"agent_actions":{"view_html":"https://pith.science/pith/BZXL4ZNPLJHR6OGSXJOKL425NE","download_json":"https://pith.science/pith/BZXL4ZNPLJHR6OGSXJOKL425NE.json","view_paper":"https://pith.science/paper/BZXL4ZNP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.16414&json=true","fetch_graph":"https://pith.science/api/pith-number/BZXL4ZNPLJHR6OGSXJOKL425NE/graph.json","fetch_events":"https://pith.science/api/pith-number/BZXL4ZNPLJHR6OGSXJOKL425NE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZXL4ZNPLJHR6OGSXJOKL425NE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZXL4ZNPLJHR6OGSXJOKL425NE/action/storage_attestation","attest_author":"https://pith.science/pith/BZXL4ZNPLJHR6OGSXJOKL425NE/action/author_attestation","sign_citation":"https://pith.science/pith/BZXL4ZNPLJHR6OGSXJOKL425NE/action/citation_signature","submit_replication":"https://pith.science/pith/BZXL4ZNPLJHR6OGSXJOKL425NE/action/replication_record"}},"created_at":"2026-07-05T07:47:07.579450+00:00","updated_at":"2026-07-05T07:47:07.579450+00:00"}