{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OPSMST36XZH2EGGLPGNFJD7BVP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1ef10ba3dacc089c7ae3839b8b899bca171a4475daefb76a78511f78b837b505","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T05:55:22Z","title_canon_sha256":"2d88e70c65e5ea1c24eabeff446d9a73781580a68964f13783c2727bbeb8c78d"},"schema_version":"1.0","source":{"id":"2405.16852","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16852","created_at":"2026-07-05T09:45:10Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16852v2","created_at":"2026-07-05T09:45:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16852","created_at":"2026-07-05T09:45:10Z"},{"alias_kind":"pith_short_12","alias_value":"OPSMST36XZH2","created_at":"2026-07-05T09:45:10Z"},{"alias_kind":"pith_short_16","alias_value":"OPSMST36XZH2EGGL","created_at":"2026-07-05T09:45:10Z"},{"alias_kind":"pith_short_8","alias_value":"OPSMST36","created_at":"2026-07-05T09:45:10Z"}],"graph_snapshots":[{"event_id":"sha256:3981bdab83d6aa84a9611399cb7488fa9d3d00ede4439fab7731b68f14c43932","target":"graph","created_at":"2026-07-05T09:45:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.16852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While diffusion models can learn complex distributions, sampling requires a computationally expensive iterative process. Existing distillation methods enable efficient sampling, but have notable limitations, such as performance degradation with very few sampling steps, reliance on training data access, or mode-seeking optimization that may fail to capture the full distribution. We propose EM Distillation (EMD), a maximum likelihood-based approach that distills a diffusion model to a one-step generator model with minimal loss of perceptual quality. Our approach is derived through the lens of Ex","authors_text":"Ben Poole, Diederik P Kingma, Kevin Patrick Murphy, Ruiqi Gao, Sirui Xie, Tim Salimans, Tingbo Hou, Ying Nian Wu, Zhisheng Xiao","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T05:55:22Z","title":"EM Distillation for One-step Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16852","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:13dc928214312664a36bcb7f097acd87f70636797dc18fa350da2248fb36199b","target":"record","created_at":"2026-07-05T09:45:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1ef10ba3dacc089c7ae3839b8b899bca171a4475daefb76a78511f78b837b505","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T05:55:22Z","title_canon_sha256":"2d88e70c65e5ea1c24eabeff446d9a73781580a68964f13783c2727bbeb8c78d"},"schema_version":"1.0","source":{"id":"2405.16852","kind":"arxiv","version":2}},"canonical_sha256":"73e4c94f7ebe4fa218cb799a548fe1abec13505e9e727c2ccf956bb19cf9e783","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73e4c94f7ebe4fa218cb799a548fe1abec13505e9e727c2ccf956bb19cf9e783","first_computed_at":"2026-07-05T09:45:10.254988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:10.254988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fKvh0hF2t9EfkM60/PrVkpqEuOkiRr4PI2R7m1NTJe92Yc33Iwv7qXZAafGxhojWaIVbBYLmJXpPSpCJ2YKgAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:10.255471Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16852","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13dc928214312664a36bcb7f097acd87f70636797dc18fa350da2248fb36199b","sha256:3981bdab83d6aa84a9611399cb7488fa9d3d00ede4439fab7731b68f14c43932"],"state_sha256":"a0b064e7c6e58cd36d8994337fef0e2fdf55c978dbf255ecc38ae7ca28376b6b"}