{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BEBOFXDUDPCNHR225V643FJUS7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"391b80b04bb535a7e0c92f169ad9f5e6b9ab662c31e56fac3ad5b9ae47e2ee47","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-09T22:45:15Z","title_canon_sha256":"f16f7594e57fed67175826afbd295f3ff4914a984f065c103c15f314eafd7b49"},"schema_version":"1.0","source":{"id":"2502.06061","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06061","created_at":"2026-07-05T10:11:47Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06061v1","created_at":"2026-07-05T10:11:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06061","created_at":"2026-07-05T10:11:47Z"},{"alias_kind":"pith_short_12","alias_value":"BEBOFXDUDPCN","created_at":"2026-07-05T10:11:47Z"},{"alias_kind":"pith_short_16","alias_value":"BEBOFXDUDPCNHR22","created_at":"2026-07-05T10:11:47Z"},{"alias_kind":"pith_short_8","alias_value":"BEBOFXDU","created_at":"2026-07-05T10:11:47Z"}],"graph_snapshots":[{"event_id":"sha256:c006fdcfe9c66492e2bd58ea8edc4b27b60421221dfd2071dd461d5e037d7502","target":"graph","created_at":"2026-07-05T10:11:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.06061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in reinforcement learning (RL) have achieved great success in fine-tuning diffusion-based generative models. However, fine-tuning continuous flow-based generative models to align with arbitrary user-defined reward functions remains challenging, particularly due to issues such as policy collapse from overoptimization and the prohibitively high computational cost of likelihoods in continuous-time flows. In this paper, we propose an easy-to-use and theoretically sound RL fine-tuning method, which we term Online Reward-Weighted Conditional Flow Matching with Wasserstein-2 Regul","authors_text":"Chaoran Cheng, Chumeng Liang, Ge Liu, Jiajun Fan, Shuaike Shen, Yuxin Chen","cross_cats":["cs.AI","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-09T22:45:15Z","title":"Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06061","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:80660339a01fd77f456f7dcc2107b594502e8684fc615874bd4200183451d9cd","target":"record","created_at":"2026-07-05T10:11:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"391b80b04bb535a7e0c92f169ad9f5e6b9ab662c31e56fac3ad5b9ae47e2ee47","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-09T22:45:15Z","title_canon_sha256":"f16f7594e57fed67175826afbd295f3ff4914a984f065c103c15f314eafd7b49"},"schema_version":"1.0","source":{"id":"2502.06061","kind":"arxiv","version":1}},"canonical_sha256":"0902e2dc741bc4d3c75aed7dcd953497ec64e00086807454a3f2e6ce610f9a5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0902e2dc741bc4d3c75aed7dcd953497ec64e00086807454a3f2e6ce610f9a5f","first_computed_at":"2026-07-05T10:11:47.152337Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:47.152337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FhPwMmrTFEXU5EyUFZ8DypHSK65BkQ98mtWa+fXfqujMvjhzXUsLCNuLfD36OX3Bxf3y0MD/gzwoBpzuboWsCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:47.152808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06061","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80660339a01fd77f456f7dcc2107b594502e8684fc615874bd4200183451d9cd","sha256:c006fdcfe9c66492e2bd58ea8edc4b27b60421221dfd2071dd461d5e037d7502"],"state_sha256":"b1abf36366ac965eb9fca458ad49af253d67ff88cef97cced393dc0ca3ffe0c0"}