{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WUD3MHYBHKCNKWNZBFGUJJOGIT","short_pith_number":"pith:WUD3MHYB","schema_version":"1.0","canonical_sha256":"b507b61f013a84d559b9094d44a5c644c0f21936eae2dc59ee01ad49b657fe7d","source":{"kind":"arxiv","id":"2606.15614","version":2},"attestation_state":"computed","paper":{"title":"Variational Test-time Optimization for Diffusion Synchronization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Farrin Marouf Sofian, Hyunsoo Lee, Kushagra Pandey, Stephan Mandt","submitted_at":"2026-06-14T05:52:11Z","abstract_excerpt":"Collaborative generation, which coordinates multiple diffusion trajectories to extend the capabilities of pretrained priors, has emerged as a powerful paradigm for extending the applicability of diffusion models. Among existing approaches, diffusion synchronization provides a scenario-agnostic solution by introducing general guidance mechanisms. However, current synchronization approaches rely heavily on heuristics and still require task-specific tailoring, which limits their generalizability and performance. In this work, we mathematically derive a synchronization framework based on optimal c"},"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":"2606.15614","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-14T05:52:11Z","cross_cats_sorted":[],"title_canon_sha256":"bd58e6d3eb0b0e855a524d314b37a06d51bd4ffc08039ea856307fc641572240","abstract_canon_sha256":"5a2a47a98e200c80f04f2ffd0c749fc80714bfec6927ebd4708462cd322b2abb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:01.364924Z","signature_b64":"BmMpVg1rEnC2rqSL1kmqCgdroBhRupwHqIgUlT/TBaL4Bqgx1BjbOfo4qpERdlgPQnpifKYlIhlM4+M2UhxyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b507b61f013a84d559b9094d44a5c644c0f21936eae2dc59ee01ad49b657fe7d","last_reissued_at":"2026-06-19T16:10:01.364478Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:01.364478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Test-time Optimization for Diffusion Synchronization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Farrin Marouf Sofian, Hyunsoo Lee, Kushagra Pandey, Stephan Mandt","submitted_at":"2026-06-14T05:52:11Z","abstract_excerpt":"Collaborative generation, which coordinates multiple diffusion trajectories to extend the capabilities of pretrained priors, has emerged as a powerful paradigm for extending the applicability of diffusion models. Among existing approaches, diffusion synchronization provides a scenario-agnostic solution by introducing general guidance mechanisms. However, current synchronization approaches rely heavily on heuristics and still require task-specific tailoring, which limits their generalizability and performance. In this work, we mathematically derive a synchronization framework based on optimal c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.15614","kind":"arxiv","version":2},"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/2606.15614/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":"2606.15614","created_at":"2026-06-19T16:10:01.364535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.15614v2","created_at":"2026-06-19T16:10:01.364535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.15614","created_at":"2026-06-19T16:10:01.364535+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUD3MHYBHKCN","created_at":"2026-06-19T16:10:01.364535+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUD3MHYBHKCNKWNZ","created_at":"2026-06-19T16:10:01.364535+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUD3MHYB","created_at":"2026-06-19T16:10:01.364535+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/WUD3MHYBHKCNKWNZBFGUJJOGIT","json":"https://pith.science/pith/WUD3MHYBHKCNKWNZBFGUJJOGIT.json","graph_json":"https://pith.science/api/pith-number/WUD3MHYBHKCNKWNZBFGUJJOGIT/graph.json","events_json":"https://pith.science/api/pith-number/WUD3MHYBHKCNKWNZBFGUJJOGIT/events.json","paper":"https://pith.science/paper/WUD3MHYB"},"agent_actions":{"view_html":"https://pith.science/pith/WUD3MHYBHKCNKWNZBFGUJJOGIT","download_json":"https://pith.science/pith/WUD3MHYBHKCNKWNZBFGUJJOGIT.json","view_paper":"https://pith.science/paper/WUD3MHYB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.15614&json=true","fetch_graph":"https://pith.science/api/pith-number/WUD3MHYBHKCNKWNZBFGUJJOGIT/graph.json","fetch_events":"https://pith.science/api/pith-number/WUD3MHYBHKCNKWNZBFGUJJOGIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUD3MHYBHKCNKWNZBFGUJJOGIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUD3MHYBHKCNKWNZBFGUJJOGIT/action/storage_attestation","attest_author":"https://pith.science/pith/WUD3MHYBHKCNKWNZBFGUJJOGIT/action/author_attestation","sign_citation":"https://pith.science/pith/WUD3MHYBHKCNKWNZBFGUJJOGIT/action/citation_signature","submit_replication":"https://pith.science/pith/WUD3MHYBHKCNKWNZBFGUJJOGIT/action/replication_record"}},"created_at":"2026-06-19T16:10:01.364535+00:00","updated_at":"2026-06-19T16:10:01.364535+00:00"}