{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TYIYJ4JE7HAR7E7JVMRZENYTO2","short_pith_number":"pith:TYIYJ4JE","schema_version":"1.0","canonical_sha256":"9e1184f124f9c11f93e9ab23923713768340cb656a504b3a68f4fb14992cb924","source":{"kind":"arxiv","id":"2505.19431","version":1},"attestation_state":"computed","paper":{"title":"Importance Weighted Score Matching for Diffusion Samplers with Enhanced Mode Coverage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenguang Wang, Kaiyuan Cui, Tianshu Yu, Weichen Zhao, Xiaoyu Zhang, Yongtao Guan","submitted_at":"2025-05-26T02:48:26Z","abstract_excerpt":"Training neural samplers directly from unnormalized densities without access to target distribution samples presents a significant challenge. A critical desideratum in these settings is achieving comprehensive mode coverage, ensuring the sampler captures the full diversity of the target distribution. However, prevailing methods often circumvent the lack of target data by optimizing reverse KL-based objectives. Such objectives inherently exhibit mode-seeking behavior, potentially leading to incomplete representation of the underlying distribution. While alternative approaches strive for better "},"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":"2505.19431","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T02:48:26Z","cross_cats_sorted":[],"title_canon_sha256":"4286b3dacf42a448c8aaba6fdb384e6ba350212edb8037032a311f09ff0ca46f","abstract_canon_sha256":"0cea4cbc3d586fe6677330baacc4b01ab97274955c0e0d1f34532405ee8fa1b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:30.116048Z","signature_b64":"Q9jCbUjYbPP8a383BCERdamaDMhH1yR6Aqo7ZRlgWObOMayIFXS4H9uGTRZpzF7evAueo/QN07C26Vg69IBYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e1184f124f9c11f93e9ab23923713768340cb656a504b3a68f4fb14992cb924","last_reissued_at":"2026-07-05T11:09:30.115550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:30.115550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Importance Weighted Score Matching for Diffusion Samplers with Enhanced Mode Coverage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenguang Wang, Kaiyuan Cui, Tianshu Yu, Weichen Zhao, Xiaoyu Zhang, Yongtao Guan","submitted_at":"2025-05-26T02:48:26Z","abstract_excerpt":"Training neural samplers directly from unnormalized densities without access to target distribution samples presents a significant challenge. A critical desideratum in these settings is achieving comprehensive mode coverage, ensuring the sampler captures the full diversity of the target distribution. However, prevailing methods often circumvent the lack of target data by optimizing reverse KL-based objectives. Such objectives inherently exhibit mode-seeking behavior, potentially leading to incomplete representation of the underlying distribution. While alternative approaches strive for better "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19431","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/2505.19431/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":"2505.19431","created_at":"2026-07-05T11:09:30.115609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19431v1","created_at":"2026-07-05T11:09:30.115609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19431","created_at":"2026-07-05T11:09:30.115609+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYIYJ4JE7HAR","created_at":"2026-07-05T11:09:30.115609+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYIYJ4JE7HAR7E7J","created_at":"2026-07-05T11:09:30.115609+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYIYJ4JE","created_at":"2026-07-05T11:09:30.115609+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.12518","citing_title":"Towards Adaptive External Communication in Autonomous Vehicles: A Conceptual Design Framework","ref_index":136,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYIYJ4JE7HAR7E7JVMRZENYTO2","json":"https://pith.science/pith/TYIYJ4JE7HAR7E7JVMRZENYTO2.json","graph_json":"https://pith.science/api/pith-number/TYIYJ4JE7HAR7E7JVMRZENYTO2/graph.json","events_json":"https://pith.science/api/pith-number/TYIYJ4JE7HAR7E7JVMRZENYTO2/events.json","paper":"https://pith.science/paper/TYIYJ4JE"},"agent_actions":{"view_html":"https://pith.science/pith/TYIYJ4JE7HAR7E7JVMRZENYTO2","download_json":"https://pith.science/pith/TYIYJ4JE7HAR7E7JVMRZENYTO2.json","view_paper":"https://pith.science/paper/TYIYJ4JE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19431&json=true","fetch_graph":"https://pith.science/api/pith-number/TYIYJ4JE7HAR7E7JVMRZENYTO2/graph.json","fetch_events":"https://pith.science/api/pith-number/TYIYJ4JE7HAR7E7JVMRZENYTO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYIYJ4JE7HAR7E7JVMRZENYTO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYIYJ4JE7HAR7E7JVMRZENYTO2/action/storage_attestation","attest_author":"https://pith.science/pith/TYIYJ4JE7HAR7E7JVMRZENYTO2/action/author_attestation","sign_citation":"https://pith.science/pith/TYIYJ4JE7HAR7E7JVMRZENYTO2/action/citation_signature","submit_replication":"https://pith.science/pith/TYIYJ4JE7HAR7E7JVMRZENYTO2/action/replication_record"}},"created_at":"2026-07-05T11:09:30.115609+00:00","updated_at":"2026-07-05T11:09:30.115609+00:00"}