{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EASKERXMZGVPV22SXIOVEX5PYY","short_pith_number":"pith:EASKERXM","schema_version":"1.0","canonical_sha256":"2024a246ecc9aafaeb52ba1d525fafc61dc74c9c92e52594f712d7dd6d16e343","source":{"kind":"arxiv","id":"2607.26860","version":1},"attestation_state":"computed","paper":{"title":"Amortized Moment Matching for Visual Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Pengfei Wan, Wenze Liu, Xiangyu Yue, Xintao Wang","submitted_at":"2026-07-29T12:44:19Z","abstract_excerpt":"We propose amortized moment matching, utilizing neural networks to learn data moments as distributional training signals. By casting diffusion denoisers through polynomial projections, we establish a general framework for moment amortization, revealing that an $n$-th degree projection explicitly identifies data moments up to order $n+1$. Derived from the tractable affine case, we instantiate the Amortized Fr\\'{e}chet Distance (AMFD) loss. Unlike FD-loss which relies on explicit marginal moment calculations, AMFD is able to dynamically learn conditional moments via an alternating, matrix-free o"},"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":"2607.26860","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T12:44:19Z","cross_cats_sorted":[],"title_canon_sha256":"0de8b44c3298be135e8234510df75e82cd73c49596ac2cb91a25bfef1540405c","abstract_canon_sha256":"a26bd2316bf571a158107b585ae43172b131ddfdc6b1bb14b2ad7e91304dca2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2024a246ecc9aafaeb52ba1d525fafc61dc74c9c92e52594f712d7dd6d16e343","last_reissued_at":"2026-07-30T01:22:33.144412Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:22:33.144412Z"},"graph_snapshot":{"paper":{"title":"Amortized Moment Matching for Visual Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Pengfei Wan, Wenze Liu, Xiangyu Yue, Xintao Wang","submitted_at":"2026-07-29T12:44:19Z","abstract_excerpt":"We propose amortized moment matching, utilizing neural networks to learn data moments as distributional training signals. By casting diffusion denoisers through polynomial projections, we establish a general framework for moment amortization, revealing that an $n$-th degree projection explicitly identifies data moments up to order $n+1$. Derived from the tractable affine case, we instantiate the Amortized Fr\\'{e}chet Distance (AMFD) loss. Unlike FD-loss which relies on explicit marginal moment calculations, AMFD is able to dynamically learn conditional moments via an alternating, matrix-free o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26860","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/2607.26860/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":"2607.26860","created_at":"2026-07-30T01:22:33.149503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.26860v1","created_at":"2026-07-30T01:22:33.149503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26860","created_at":"2026-07-30T01:22:33.149503+00:00"},{"alias_kind":"pith_short_12","alias_value":"EASKERXMZGVP","created_at":"2026-07-30T01:22:33.149503+00:00"},{"alias_kind":"pith_short_16","alias_value":"EASKERXMZGVPV22S","created_at":"2026-07-30T01:22:33.149503+00:00"},{"alias_kind":"pith_short_8","alias_value":"EASKERXM","created_at":"2026-07-30T01:22:33.149503+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/EASKERXMZGVPV22SXIOVEX5PYY","json":"https://pith.science/pith/EASKERXMZGVPV22SXIOVEX5PYY.json","graph_json":"https://pith.science/api/pith-number/EASKERXMZGVPV22SXIOVEX5PYY/graph.json","events_json":"https://pith.science/api/pith-number/EASKERXMZGVPV22SXIOVEX5PYY/events.json","paper":"https://pith.science/paper/EASKERXM"},"agent_actions":{"view_html":"https://pith.science/pith/EASKERXMZGVPV22SXIOVEX5PYY","download_json":"https://pith.science/pith/EASKERXMZGVPV22SXIOVEX5PYY.json","view_paper":"https://pith.science/paper/EASKERXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.26860&json=true","fetch_graph":"https://pith.science/api/pith-number/EASKERXMZGVPV22SXIOVEX5PYY/graph.json","fetch_events":"https://pith.science/api/pith-number/EASKERXMZGVPV22SXIOVEX5PYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EASKERXMZGVPV22SXIOVEX5PYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EASKERXMZGVPV22SXIOVEX5PYY/action/storage_attestation","attest_author":"https://pith.science/pith/EASKERXMZGVPV22SXIOVEX5PYY/action/author_attestation","sign_citation":"https://pith.science/pith/EASKERXMZGVPV22SXIOVEX5PYY/action/citation_signature","submit_replication":"https://pith.science/pith/EASKERXMZGVPV22SXIOVEX5PYY/action/replication_record"}},"created_at":"2026-07-30T01:22:33.149503+00:00","updated_at":"2026-07-30T01:22:33.149503+00:00"}