{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F3KR56FVW2E62F6RSBVALWTJ4U","short_pith_number":"pith:F3KR56FV","schema_version":"1.0","canonical_sha256":"2ed51ef8b5b689ed17d1906a05da69e51fb10e06fb9df683c9f0158b6fe39dac","source":{"kind":"arxiv","id":"2507.16884","version":1},"attestation_state":"computed","paper":{"title":"SplitMeanFlow: Interval Splitting Consistency in Few-Step Generative Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kuan Chen, Rong Cao, Shouda Liu, Wei Wang, Yang Zhang, Yi Guo, Yuanyuan Huo, Yuping Wang, Yuxuan Wang, Zhengyang Chen, Zhihang Yuan","submitted_at":"2025-07-22T16:26:58Z","abstract_excerpt":"Generative models like Flow Matching have achieved state-of-the-art performance but are often hindered by a computationally expensive iterative sampling process. To address this, recent work has focused on few-step or one-step generation by learning the average velocity field, which directly maps noise to data. MeanFlow, a leading method in this area, learns this field by enforcing a differential identity that connects the average and instantaneous velocities. In this work, we argue that this differential formulation is a limiting special case of a more fundamental principle. We return to the "},"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":"2507.16884","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T16:26:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a3072a3433ceddd9de9f2f8160402b2d462f6865fcb4804dc14da73e0970acc","abstract_canon_sha256":"3952da78b87ac84faa59c0d0b423d99dda68b5ef5364683740f582c368ecdcc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:57.922715Z","signature_b64":"hCMGqrHKZfRWj+/EQk+Jt1OHtRjQKCGQCZdNA2+TH1vsCgOW5nk/m0tSYPh/74ggRkMYD0ZE20uYNKqJhgShBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ed51ef8b5b689ed17d1906a05da69e51fb10e06fb9df683c9f0158b6fe39dac","last_reissued_at":"2026-07-05T11:41:57.922237Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:57.922237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SplitMeanFlow: Interval Splitting Consistency in Few-Step Generative Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kuan Chen, Rong Cao, Shouda Liu, Wei Wang, Yang Zhang, Yi Guo, Yuanyuan Huo, Yuping Wang, Yuxuan Wang, Zhengyang Chen, Zhihang Yuan","submitted_at":"2025-07-22T16:26:58Z","abstract_excerpt":"Generative models like Flow Matching have achieved state-of-the-art performance but are often hindered by a computationally expensive iterative sampling process. To address this, recent work has focused on few-step or one-step generation by learning the average velocity field, which directly maps noise to data. MeanFlow, a leading method in this area, learns this field by enforcing a differential identity that connects the average and instantaneous velocities. In this work, we argue that this differential formulation is a limiting special case of a more fundamental principle. We return to the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16884","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/2507.16884/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":"2507.16884","created_at":"2026-07-05T11:41:57.922294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16884v1","created_at":"2026-07-05T11:41:57.922294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16884","created_at":"2026-07-05T11:41:57.922294+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3KR56FVW2E6","created_at":"2026-07-05T11:41:57.922294+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3KR56FVW2E62F6R","created_at":"2026-07-05T11:41:57.922294+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3KR56FV","created_at":"2026-07-05T11:41:57.922294+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02237","citing_title":"Why Are DMD Students Lazy? Understanding the Copying Behavior in Few-Step Distillation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28226","citing_title":"Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04165","citing_title":"CaloTrilogy: Toward a Breakthrough in One-Step, End-to-End, Physics-Guided Shower Generation for Modern Calorimeters","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2602.10764","citing_title":"Dual-End Consistency Model","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01457","citing_title":"CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13724","citing_title":"AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01457","citing_title":"CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09328","citing_title":"Noise-Started One-Step Real-World Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01457","citing_title":"CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18168","citing_title":"Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F3KR56FVW2E62F6RSBVALWTJ4U","json":"https://pith.science/pith/F3KR56FVW2E62F6RSBVALWTJ4U.json","graph_json":"https://pith.science/api/pith-number/F3KR56FVW2E62F6RSBVALWTJ4U/graph.json","events_json":"https://pith.science/api/pith-number/F3KR56FVW2E62F6RSBVALWTJ4U/events.json","paper":"https://pith.science/paper/F3KR56FV"},"agent_actions":{"view_html":"https://pith.science/pith/F3KR56FVW2E62F6RSBVALWTJ4U","download_json":"https://pith.science/pith/F3KR56FVW2E62F6RSBVALWTJ4U.json","view_paper":"https://pith.science/paper/F3KR56FV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16884&json=true","fetch_graph":"https://pith.science/api/pith-number/F3KR56FVW2E62F6RSBVALWTJ4U/graph.json","fetch_events":"https://pith.science/api/pith-number/F3KR56FVW2E62F6RSBVALWTJ4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3KR56FVW2E62F6RSBVALWTJ4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3KR56FVW2E62F6RSBVALWTJ4U/action/storage_attestation","attest_author":"https://pith.science/pith/F3KR56FVW2E62F6RSBVALWTJ4U/action/author_attestation","sign_citation":"https://pith.science/pith/F3KR56FVW2E62F6RSBVALWTJ4U/action/citation_signature","submit_replication":"https://pith.science/pith/F3KR56FVW2E62F6RSBVALWTJ4U/action/replication_record"}},"created_at":"2026-07-05T11:41:57.922294+00:00","updated_at":"2026-07-05T11:41:57.922294+00:00"}