{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:COW2VO242Q7WJKDTJPDFTWZ5LK","short_pith_number":"pith:COW2VO24","schema_version":"1.0","canonical_sha256":"13adaabb5cd43f64a8734bc659db3d5aaa72505bc32bdd1a3552d5ff5b9b2f12","source":{"kind":"arxiv","id":"2607.00535","version":1},"attestation_state":"computed","paper":{"title":"Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bo Zhu, Wen Zhang, Zhiqi Li","submitted_at":"2026-07-01T07:25:11Z","abstract_excerpt":"Few-step flow-map generators, such as consistency models and MeanFlow, accelerate sampling by directly learning long-range transport maps between noise and data. However, these models are typically deterministic, which makes them difficult to optimize with reinforcement learning (RL) post-training methods that require stochastic trajectories and well-defined likelihood ratios. Existing SDE-based stochasticization techniques are designed for velocity-based samplers with infinitesimal or finely discretized transitions, and therefore do not directly apply to long-range flow maps. In this work, we"},"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":"2607.00535","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T07:25:11Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"2c0218aeec0c6f6dc7119d959b777569ea3344255d423f88b9af23e74ac5fa55","abstract_canon_sha256":"86c621b70455bb819668bc5bd412f8ba80efee82f5cb97edf9af5838e6b680ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:46.929805Z","signature_b64":"UdumaMPueOHxQGkbf2eMNHmThzvNU1J5FA6lZUxR9NnoO4BMi/R0GfwVLr72n81csxpSmvBlGmVrLe8Y6rKKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13adaabb5cd43f64a8734bc659db3d5aaa72505bc32bdd1a3552d5ff5b9b2f12","last_reissued_at":"2026-07-02T01:17:46.929423Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:46.929423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bo Zhu, Wen Zhang, Zhiqi Li","submitted_at":"2026-07-01T07:25:11Z","abstract_excerpt":"Few-step flow-map generators, such as consistency models and MeanFlow, accelerate sampling by directly learning long-range transport maps between noise and data. However, these models are typically deterministic, which makes them difficult to optimize with reinforcement learning (RL) post-training methods that require stochastic trajectories and well-defined likelihood ratios. Existing SDE-based stochasticization techniques are designed for velocity-based samplers with infinitesimal or finely discretized transitions, and therefore do not directly apply to long-range flow maps. In this work, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00535","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/2607.00535/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":"2607.00535","created_at":"2026-07-02T01:17:46.929478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00535v1","created_at":"2026-07-02T01:17:46.929478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00535","created_at":"2026-07-02T01:17:46.929478+00:00"},{"alias_kind":"pith_short_12","alias_value":"COW2VO242Q7W","created_at":"2026-07-02T01:17:46.929478+00:00"},{"alias_kind":"pith_short_16","alias_value":"COW2VO242Q7WJKDT","created_at":"2026-07-02T01:17:46.929478+00:00"},{"alias_kind":"pith_short_8","alias_value":"COW2VO24","created_at":"2026-07-02T01:17:46.929478+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/COW2VO242Q7WJKDTJPDFTWZ5LK","json":"https://pith.science/pith/COW2VO242Q7WJKDTJPDFTWZ5LK.json","graph_json":"https://pith.science/api/pith-number/COW2VO242Q7WJKDTJPDFTWZ5LK/graph.json","events_json":"https://pith.science/api/pith-number/COW2VO242Q7WJKDTJPDFTWZ5LK/events.json","paper":"https://pith.science/paper/COW2VO24"},"agent_actions":{"view_html":"https://pith.science/pith/COW2VO242Q7WJKDTJPDFTWZ5LK","download_json":"https://pith.science/pith/COW2VO242Q7WJKDTJPDFTWZ5LK.json","view_paper":"https://pith.science/paper/COW2VO24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00535&json=true","fetch_graph":"https://pith.science/api/pith-number/COW2VO242Q7WJKDTJPDFTWZ5LK/graph.json","fetch_events":"https://pith.science/api/pith-number/COW2VO242Q7WJKDTJPDFTWZ5LK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/COW2VO242Q7WJKDTJPDFTWZ5LK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/COW2VO242Q7WJKDTJPDFTWZ5LK/action/storage_attestation","attest_author":"https://pith.science/pith/COW2VO242Q7WJKDTJPDFTWZ5LK/action/author_attestation","sign_citation":"https://pith.science/pith/COW2VO242Q7WJKDTJPDFTWZ5LK/action/citation_signature","submit_replication":"https://pith.science/pith/COW2VO242Q7WJKDTJPDFTWZ5LK/action/replication_record"}},"created_at":"2026-07-02T01:17:46.929478+00:00","updated_at":"2026-07-02T01:17:46.929478+00:00"}