{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KHHL5XDTNNW6NNKXSM6MELXSR4","short_pith_number":"pith:KHHL5XDT","schema_version":"1.0","canonical_sha256":"51cebedc736b6de6b557933cc22ef28f394824052ffd6b29ed22a481c83f014f","source":{"kind":"arxiv","id":"2410.19310","version":1},"attestation_state":"computed","paper":{"title":"Flow Generator Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Guo-jun Qi, Weijian Luo, Zemin Huang, Zhengyang Geng","submitted_at":"2024-10-25T05:41:28Z","abstract_excerpt":"In the realm of Artificial Intelligence Generated Content (AIGC), flow-matching models have emerged as a powerhouse, achieving success due to their robust theoretical underpinnings and solid ability for large-scale generative modeling. These models have demonstrated state-of-the-art performance, but their brilliance comes at a cost. The process of sampling from these models is notoriously demanding on computational resources, as it necessitates the use of multi-step numerical ordinary differential equations (ODEs). Against this backdrop, this paper presents a novel solution with theoretical gu"},"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":"2410.19310","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-25T05:41:28Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"8428de46b36940dfc173e0bec858a15921c3b1fdf8a385fb1fdbd632ef05df01","abstract_canon_sha256":"c2c8bd06972b887ccfff64b8ca6ab6c26949226e059863f54d3a9a0e7dc32af3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:54.829398Z","signature_b64":"JaMe1qQsFcBkNA5YjP3dyEmBlvyztJu8jr7x9nd7CoxqivVxvNuW/aFrHfbEb2Ojpb9zVMkAi4sKKP9ewzUlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51cebedc736b6de6b557933cc22ef28f394824052ffd6b29ed22a481c83f014f","last_reissued_at":"2026-07-05T09:25:54.828900Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:54.828900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow Generator Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Guo-jun Qi, Weijian Luo, Zemin Huang, Zhengyang Geng","submitted_at":"2024-10-25T05:41:28Z","abstract_excerpt":"In the realm of Artificial Intelligence Generated Content (AIGC), flow-matching models have emerged as a powerhouse, achieving success due to their robust theoretical underpinnings and solid ability for large-scale generative modeling. These models have demonstrated state-of-the-art performance, but their brilliance comes at a cost. The process of sampling from these models is notoriously demanding on computational resources, as it necessitates the use of multi-step numerical ordinary differential equations (ODEs). Against this backdrop, this paper presents a novel solution with theoretical gu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19310","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/2410.19310/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":"2410.19310","created_at":"2026-07-05T09:25:54.828955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.19310v1","created_at":"2026-07-05T09:25:54.828955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19310","created_at":"2026-07-05T09:25:54.828955+00:00"},{"alias_kind":"pith_short_12","alias_value":"KHHL5XDTNNW6","created_at":"2026-07-05T09:25:54.828955+00:00"},{"alias_kind":"pith_short_16","alias_value":"KHHL5XDTNNW6NNKX","created_at":"2026-07-05T09:25:54.828955+00:00"},{"alias_kind":"pith_short_8","alias_value":"KHHL5XDT","created_at":"2026-07-05T09:25:54.828955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06281","citing_title":"Straight-Path Flow Matching for Incomplete Multi-View Clustering","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.29920","citing_title":"Midpoint Generative Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08009","citing_title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KHHL5XDTNNW6NNKXSM6MELXSR4","json":"https://pith.science/pith/KHHL5XDTNNW6NNKXSM6MELXSR4.json","graph_json":"https://pith.science/api/pith-number/KHHL5XDTNNW6NNKXSM6MELXSR4/graph.json","events_json":"https://pith.science/api/pith-number/KHHL5XDTNNW6NNKXSM6MELXSR4/events.json","paper":"https://pith.science/paper/KHHL5XDT"},"agent_actions":{"view_html":"https://pith.science/pith/KHHL5XDTNNW6NNKXSM6MELXSR4","download_json":"https://pith.science/pith/KHHL5XDTNNW6NNKXSM6MELXSR4.json","view_paper":"https://pith.science/paper/KHHL5XDT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.19310&json=true","fetch_graph":"https://pith.science/api/pith-number/KHHL5XDTNNW6NNKXSM6MELXSR4/graph.json","fetch_events":"https://pith.science/api/pith-number/KHHL5XDTNNW6NNKXSM6MELXSR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KHHL5XDTNNW6NNKXSM6MELXSR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KHHL5XDTNNW6NNKXSM6MELXSR4/action/storage_attestation","attest_author":"https://pith.science/pith/KHHL5XDTNNW6NNKXSM6MELXSR4/action/author_attestation","sign_citation":"https://pith.science/pith/KHHL5XDTNNW6NNKXSM6MELXSR4/action/citation_signature","submit_replication":"https://pith.science/pith/KHHL5XDTNNW6NNKXSM6MELXSR4/action/replication_record"}},"created_at":"2026-07-05T09:25:54.828955+00:00","updated_at":"2026-07-05T09:25:54.828955+00:00"}