{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T3UTE2U5B5Y4N3472DKLNSOVM4","short_pith_number":"pith:T3UTE2U5","schema_version":"1.0","canonical_sha256":"9ee9326a9d0f71c6ef9fd0d4b6c9d5673f3b43517395684ab5ddfa00170037a8","source":{"kind":"arxiv","id":"2511.17812","version":3},"attestation_state":"computed","paper":{"title":"Score-Regularized Joint Sampling with Importance Weights for Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Runfa Blark Li, Shaoxiu Wei, Truong Nguyen, Xinshuang Liu","submitted_at":"2025-11-21T22:05:56Z","abstract_excerpt":"Flow matching models effectively represent complex distributions, yet estimating expectations of functions of their outputs remains challenging under limited sampling budgets. Independent sampling often yields high-variance estimates, especially when rare but high-impact outcomes dominate the expectation. We propose a non-IID sampling framework that jointly draws multiple samples to cover diverse, salient regions of a flow matching model's generative distribution. To balance diversity and quality, we introduce a score-based regularization for the diversity mechanism (SR), which uses the score "},"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":"2511.17812","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-21T22:05:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3d33ead7d07cfa793cec47cb2d09d87f34b89d4210a943c8b597c4bf47cad9f7","abstract_canon_sha256":"a930d055fca821e4ab11fcf51ff3f64822710b6225dc394630284bf6b04ac4da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:30.551799Z","signature_b64":"XmMIoGKj3ok/xU+d9jINUUTNY++FARpLy3djVR4YOjLJKU50z5wYlldUAwXENojsnjbyOmRMiLWWkwr9yrcPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ee9326a9d0f71c6ef9fd0d4b6c9d5673f3b43517395684ab5ddfa00170037a8","last_reissued_at":"2026-07-07T02:18:30.550815Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:30.550815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Score-Regularized Joint Sampling with Importance Weights for Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Runfa Blark Li, Shaoxiu Wei, Truong Nguyen, Xinshuang Liu","submitted_at":"2025-11-21T22:05:56Z","abstract_excerpt":"Flow matching models effectively represent complex distributions, yet estimating expectations of functions of their outputs remains challenging under limited sampling budgets. Independent sampling often yields high-variance estimates, especially when rare but high-impact outcomes dominate the expectation. We propose a non-IID sampling framework that jointly draws multiple samples to cover diverse, salient regions of a flow matching model's generative distribution. To balance diversity and quality, we introduce a score-based regularization for the diversity mechanism (SR), which uses the score "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.17812","kind":"arxiv","version":3},"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/2511.17812/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":"2511.17812","created_at":"2026-07-07T02:18:30.550941+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.17812v3","created_at":"2026-07-07T02:18:30.550941+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.17812","created_at":"2026-07-07T02:18:30.550941+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3UTE2U5B5Y4","created_at":"2026-07-07T02:18:30.550941+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3UTE2U5B5Y4N347","created_at":"2026-07-07T02:18:30.550941+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3UTE2U5","created_at":"2026-07-07T02:18:30.550941+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.06553","citing_title":"Diverse Sampling in Diffusion Models with Marginal Preserving Particle Guidance","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T3UTE2U5B5Y4N3472DKLNSOVM4","json":"https://pith.science/pith/T3UTE2U5B5Y4N3472DKLNSOVM4.json","graph_json":"https://pith.science/api/pith-number/T3UTE2U5B5Y4N3472DKLNSOVM4/graph.json","events_json":"https://pith.science/api/pith-number/T3UTE2U5B5Y4N3472DKLNSOVM4/events.json","paper":"https://pith.science/paper/T3UTE2U5"},"agent_actions":{"view_html":"https://pith.science/pith/T3UTE2U5B5Y4N3472DKLNSOVM4","download_json":"https://pith.science/pith/T3UTE2U5B5Y4N3472DKLNSOVM4.json","view_paper":"https://pith.science/paper/T3UTE2U5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.17812&json=true","fetch_graph":"https://pith.science/api/pith-number/T3UTE2U5B5Y4N3472DKLNSOVM4/graph.json","fetch_events":"https://pith.science/api/pith-number/T3UTE2U5B5Y4N3472DKLNSOVM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3UTE2U5B5Y4N3472DKLNSOVM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3UTE2U5B5Y4N3472DKLNSOVM4/action/storage_attestation","attest_author":"https://pith.science/pith/T3UTE2U5B5Y4N3472DKLNSOVM4/action/author_attestation","sign_citation":"https://pith.science/pith/T3UTE2U5B5Y4N3472DKLNSOVM4/action/citation_signature","submit_replication":"https://pith.science/pith/T3UTE2U5B5Y4N3472DKLNSOVM4/action/replication_record"}},"created_at":"2026-07-07T02:18:30.550941+00:00","updated_at":"2026-07-07T02:18:30.550941+00:00"}