{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UDTK665R32FWMICMBWUDHCMRMJ","short_pith_number":"pith:UDTK665R","schema_version":"1.0","canonical_sha256":"a0e6af7bb1de8b66204c0da833899162510b2d8330d2c806ddb2802f695878dd","source":{"kind":"arxiv","id":"2501.11361","version":1},"attestation_state":"computed","paper":{"title":"Block Flow: Learning Straight Flow on Data Blocks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Xiangyun Zhang, Zhiyuan Ouyang, Zibin Wang","submitted_at":"2025-01-20T09:46:12Z","abstract_excerpt":"Flow-matching models provide a powerful framework for various applications, offering efficient sampling and flexible probability path modeling. These models are characterized by flows with low curvature in learned generative trajectories, which results in reduced truncation error at each sampling step. To further reduce curvature, we propose block matching. This novel approach leverages label information to partition the data distribution into blocks and match them with a prior distribution parameterized using the same label information, thereby learning straighter flows. We demonstrate that t"},"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":"2501.11361","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-20T09:46:12Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b89d794411518e25785fc898815d86178e3d20a7ef3e5de9185bda970b5bef12","abstract_canon_sha256":"9b61e5c4e6273d6dfac7bd49885d3b25743fa8fe8caee97aec8d1e9682df5e47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:07.580032Z","signature_b64":"a23KYJaNSXAI2tl9ZtdANx2ZY68hc4rPEI4ST7wvVC1ESzEyUet1UdLIIrEOoOEjh2ssLKr36Ct0JrDuqvwACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0e6af7bb1de8b66204c0da833899162510b2d8330d2c806ddb2802f695878dd","last_reissued_at":"2026-07-05T10:03:07.579560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:07.579560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Block Flow: Learning Straight Flow on Data Blocks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Xiangyun Zhang, Zhiyuan Ouyang, Zibin Wang","submitted_at":"2025-01-20T09:46:12Z","abstract_excerpt":"Flow-matching models provide a powerful framework for various applications, offering efficient sampling and flexible probability path modeling. These models are characterized by flows with low curvature in learned generative trajectories, which results in reduced truncation error at each sampling step. To further reduce curvature, we propose block matching. This novel approach leverages label information to partition the data distribution into blocks and match them with a prior distribution parameterized using the same label information, thereby learning straighter flows. We demonstrate that t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11361","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/2501.11361/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":"2501.11361","created_at":"2026-07-05T10:03:07.579613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11361v1","created_at":"2026-07-05T10:03:07.579613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11361","created_at":"2026-07-05T10:03:07.579613+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDTK665R32FW","created_at":"2026-07-05T10:03:07.579613+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDTK665R32FWMICM","created_at":"2026-07-05T10:03:07.579613+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDTK665R","created_at":"2026-07-05T10:03:07.579613+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/UDTK665R32FWMICMBWUDHCMRMJ","json":"https://pith.science/pith/UDTK665R32FWMICMBWUDHCMRMJ.json","graph_json":"https://pith.science/api/pith-number/UDTK665R32FWMICMBWUDHCMRMJ/graph.json","events_json":"https://pith.science/api/pith-number/UDTK665R32FWMICMBWUDHCMRMJ/events.json","paper":"https://pith.science/paper/UDTK665R"},"agent_actions":{"view_html":"https://pith.science/pith/UDTK665R32FWMICMBWUDHCMRMJ","download_json":"https://pith.science/pith/UDTK665R32FWMICMBWUDHCMRMJ.json","view_paper":"https://pith.science/paper/UDTK665R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11361&json=true","fetch_graph":"https://pith.science/api/pith-number/UDTK665R32FWMICMBWUDHCMRMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/UDTK665R32FWMICMBWUDHCMRMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDTK665R32FWMICMBWUDHCMRMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDTK665R32FWMICMBWUDHCMRMJ/action/storage_attestation","attest_author":"https://pith.science/pith/UDTK665R32FWMICMBWUDHCMRMJ/action/author_attestation","sign_citation":"https://pith.science/pith/UDTK665R32FWMICMBWUDHCMRMJ/action/citation_signature","submit_replication":"https://pith.science/pith/UDTK665R32FWMICMBWUDHCMRMJ/action/replication_record"}},"created_at":"2026-07-05T10:03:07.579613+00:00","updated_at":"2026-07-05T10:03:07.579613+00:00"}