{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:43JTTJYN3PMQFSW7E5S4JIS4YL","short_pith_number":"pith:43JTTJYN","schema_version":"1.0","canonical_sha256":"e6d339a70ddbd902cadf2765c4a25cc2c137544a26d2506cdaeed4448745d978","source":{"kind":"arxiv","id":"2602.10326","version":2},"attestation_state":"computed","paper":{"title":"Flow Matching with Uncertainty Quantification and Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"UA-Flow adds per-sample uncertainty prediction to flow matching and uses it for guided sampling that improves image generation quality over baselines.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Juyeop Han, Lukas Lao Beyer, Sertac Karaman","submitted_at":"2026-02-10T22:03:13Z","abstract_excerpt":"Despite the remarkable success of sampling-based generative models such as flow matching, they can still produce samples of inconsistent or degraded quality. To assess sample reliability and generate higher-quality outputs, we propose uncertainty-aware flow matching (UA-Flow), a lightweight extension of flow matching that predicts the velocity field together with heteroscedastic uncertainty. UA-Flow estimates per-sample uncertainty by propagating velocity uncertainty through the flow dynamics. These uncertainty estimates act as a reliability signal for individual samples, and we further use th"},"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":true},"canonical_record":{"source":{"id":"2602.10326","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-10T22:03:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5992b8595b7bca4ce389940d8bad5a3331073fc55473fd9979ee636864d7cd08","abstract_canon_sha256":"8f5810cecd4fe8eee84d8ec873ce75931257e11ec1715ba7c5ad64cd0a2ace11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:03.560671Z","signature_b64":"BfgFIyGCdRmR/SdJ7xUHjLKNIl92NpKct0Vk5hXwORWriZRp6jfTUv9B/vxA7PBJU5B3qqW0eADH9oddAKI9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6d339a70ddbd902cadf2765c4a25cc2c137544a26d2506cdaeed4448745d978","last_reissued_at":"2026-05-18T03:10:03.560134Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:03.560134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow Matching with Uncertainty Quantification and Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"UA-Flow adds per-sample uncertainty prediction to flow matching and uses it for guided sampling that improves image generation quality over baselines.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Juyeop Han, Lukas Lao Beyer, Sertac Karaman","submitted_at":"2026-02-10T22:03:13Z","abstract_excerpt":"Despite the remarkable success of sampling-based generative models such as flow matching, they can still produce samples of inconsistent or degraded quality. To assess sample reliability and generate higher-quality outputs, we propose uncertainty-aware flow matching (UA-Flow), a lightweight extension of flow matching that predicts the velocity field together with heteroscedastic uncertainty. UA-Flow estimates per-sample uncertainty by propagating velocity uncertainty through the flow dynamics. These uncertainty estimates act as a reliability signal for individual samples, and we further use th"},"claims":{"count":3,"items":[{"kind":"strongest_claim","text":"UA-Flow produces uncertainty signals more highly correlated with sample fidelity than baseline methods, and uncertainty-guided sampling further improves generation quality.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That propagating the predicted heteroscedastic velocity uncertainty through the flow ODE yields a calibrated per-sample reliability signal that can be directly used for guidance without introducing new biases or requiring additional calibration data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"UA-Flow adds per-sample uncertainty prediction to flow matching and uses it for guided sampling that improves image generation quality over baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"}],"snapshot_sha256":"34992cffed99fe94ff42ca5009eb35cec80905a64ef5242df1ab060d9d7221fc"},"source":{"id":"2602.10326","kind":"arxiv","version":2},"verdict":{"id":"18c38307-4b42-4cf7-9fab-0ded5d880d4d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T02:01:22.821249Z","strongest_claim":"UA-Flow produces uncertainty signals more highly correlated with sample fidelity than baseline methods, and uncertainty-guided sampling further improves generation quality.","one_line_summary":"UA-Flow adds per-sample uncertainty prediction to flow matching and uses it for guided sampling that improves image generation quality over baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That propagating the predicted heteroscedastic velocity uncertainty through the flow ODE yields a calibrated per-sample reliability signal that can be directly used for guidance without introducing new biases or requiring additional calibration data.","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8110dec389c22c1106897dc7d6caea7b806631f2fc2f95708409fb0261f33bc2"},"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":"2602.10326","created_at":"2026-05-18T03:10:03.560208+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.10326v2","created_at":"2026-05-18T03:10:03.560208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.10326","created_at":"2026-05-18T03:10:03.560208+00:00"},{"alias_kind":"pith_short_12","alias_value":"43JTTJYN3PMQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"43JTTJYN3PMQFSW7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"43JTTJYN","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.00941","citing_title":"Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00941","citing_title":"Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/43JTTJYN3PMQFSW7E5S4JIS4YL","json":"https://pith.science/pith/43JTTJYN3PMQFSW7E5S4JIS4YL.json","graph_json":"https://pith.science/api/pith-number/43JTTJYN3PMQFSW7E5S4JIS4YL/graph.json","events_json":"https://pith.science/api/pith-number/43JTTJYN3PMQFSW7E5S4JIS4YL/events.json","paper":"https://pith.science/paper/43JTTJYN"},"agent_actions":{"view_html":"https://pith.science/pith/43JTTJYN3PMQFSW7E5S4JIS4YL","download_json":"https://pith.science/pith/43JTTJYN3PMQFSW7E5S4JIS4YL.json","view_paper":"https://pith.science/paper/43JTTJYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.10326&json=true","fetch_graph":"https://pith.science/api/pith-number/43JTTJYN3PMQFSW7E5S4JIS4YL/graph.json","fetch_events":"https://pith.science/api/pith-number/43JTTJYN3PMQFSW7E5S4JIS4YL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/43JTTJYN3PMQFSW7E5S4JIS4YL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/43JTTJYN3PMQFSW7E5S4JIS4YL/action/storage_attestation","attest_author":"https://pith.science/pith/43JTTJYN3PMQFSW7E5S4JIS4YL/action/author_attestation","sign_citation":"https://pith.science/pith/43JTTJYN3PMQFSW7E5S4JIS4YL/action/citation_signature","submit_replication":"https://pith.science/pith/43JTTJYN3PMQFSW7E5S4JIS4YL/action/replication_record"}},"created_at":"2026-05-18T03:10:03.560208+00:00","updated_at":"2026-05-18T03:10:03.560208+00:00"}