{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MFMFMCOOW6LMWSYDKBNN2HV4BW","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":"7873ca2cb6c902caf3f985d1bb5ba63fdb961700bedac3b36377cb032ad74207","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-05T19:13:44Z","title_canon_sha256":"edd1c32da07207bd2adb1ae628d3824dd48dd46a905ebe0c5d9504ee225cd208"},"schema_version":"1.0","source":{"id":"2602.06138","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.06138","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"arxiv_version","alias_value":"2602.06138v2","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06138","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"pith_short_12","alias_value":"MFMFMCOOW6LM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"MFMFMCOOW6LMWSYD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"MFMFMCOO","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:845e5b39c20ad87a083d8d9cef4130fc06a5587a09de300ef966e67021f90614","target":"graph","created_at":"2026-05-18T03:09:23Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We theoretically show that, under idealized conditions, optimizing this objective recovers the optimal policy."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The idealized conditions required for the theoretical recovery of the optimal policy via the Q-weighted flow matching objective on continuous-time Markov chains."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Flow matching is adapted to discrete actions via continuous-time Markov chains and Q-weighted objectives, recovering optimal policies under idealized conditions and outperforming baselines in multi-agent and multi-objective offline RL experiments."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Flow matching with continuous-time Markov chains recovers the optimal policy for offline RL with discrete actions under idealized conditions."}],"snapshot_sha256":"257b3c19fed51e739de024701a9845a8ff131855ca4c1e688c555be4955e9c8b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Generative policies based on diffusion models and flow matching have shown strong promise for offline reinforcement learning (RL), but their applicability remains largely confined to continuous action spaces. To address a broader range of offline RL settings, we extend flow matching to a general framework that supports discrete action spaces with multiple objectives. Specifically, we replace continuous flows with continuous-time Markov chains, trained using a Q-weighted flow matching objective. We then extend our design to multi-agent settings, mitigating the exponential growth of joint action","authors_text":"Fairoz Nower Khan, Haibo Yang, Nabuat Zaman Nahim, Peizhong Ju, Ruiquan Huang","cross_cats":[],"headline":"Flow matching with continuous-time Markov chains recovers the optimal policy for offline RL with discrete actions under idealized conditions.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-05T19:13:44Z","title":"Flow Matching for Offline Reinforcement Learning with Discrete Actions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.06138","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T06:36:26.134774Z","id":"a0619a25-7229-4b5d-abfb-ad74b8166353","model_set":{"reader":"grok-4.3"},"one_line_summary":"Flow matching is adapted to discrete actions via continuous-time Markov chains and Q-weighted objectives, recovering optimal policies under idealized conditions and outperforming baselines in multi-agent and multi-objective offline RL experiments.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Flow matching with continuous-time Markov chains recovers the optimal policy for offline RL with discrete actions under idealized conditions.","strongest_claim":"We theoretically show that, under idealized conditions, optimizing this objective recovers the optimal policy.","weakest_assumption":"The idealized conditions required for the theoretical recovery of the optimal policy via the Q-weighted flow matching objective on continuous-time Markov chains."}},"verdict_id":"a0619a25-7229-4b5d-abfb-ad74b8166353"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:20d82adacba7c040e51a58749b325d34c381da92eac3a10c084cc5f6951905c2","target":"record","created_at":"2026-05-18T03:09:23Z","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":"7873ca2cb6c902caf3f985d1bb5ba63fdb961700bedac3b36377cb032ad74207","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-05T19:13:44Z","title_canon_sha256":"edd1c32da07207bd2adb1ae628d3824dd48dd46a905ebe0c5d9504ee225cd208"},"schema_version":"1.0","source":{"id":"2602.06138","kind":"arxiv","version":2}},"canonical_sha256":"61585609ceb796cb4b03505add1ebc0db5caf821c4e12b7a9affbd03d2823f50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61585609ceb796cb4b03505add1ebc0db5caf821c4e12b7a9affbd03d2823f50","first_computed_at":"2026-05-18T03:09:23.801072Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:23.801072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ExzgJBw0Jl+nuGvksg7rpFlWkWjiPGuuDYls1NT+LxC7XC3fvQFkRDf3Vt3iPTOVErRiphDAiS3EL29zUkybAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:23.801846Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.06138","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20d82adacba7c040e51a58749b325d34c381da92eac3a10c084cc5f6951905c2","sha256:845e5b39c20ad87a083d8d9cef4130fc06a5587a09de300ef966e67021f90614"],"state_sha256":"b988dc83574ba830f0ad2eb3dcd2fc01db1531f1094b9705dbb20e0153bf59de"}