{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CLOHWCEXKHNIQZUEPSGXPVVRO2","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":"3f3a162edf001ecd84af7930fd8d7816dd472b81c71f0d31899ee8c0113292b8","cross_cats_sorted":["cs.AI","cs.LG","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T07:33:49Z","title_canon_sha256":"86f5dd8dd7f1a599842c2cc72711f602a4d66584a6b5e4267de78571f8b866af"},"schema_version":"1.0","source":{"id":"2410.05760","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05760","created_at":"2026-07-05T10:20:40Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05760v2","created_at":"2026-07-05T10:20:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05760","created_at":"2026-07-05T10:20:40Z"},{"alias_kind":"pith_short_12","alias_value":"CLOHWCEXKHNI","created_at":"2026-07-05T10:20:40Z"},{"alias_kind":"pith_short_16","alias_value":"CLOHWCEXKHNIQZUE","created_at":"2026-07-05T10:20:40Z"},{"alias_kind":"pith_short_8","alias_value":"CLOHWCEX","created_at":"2026-07-05T10:20:40Z"}],"graph_snapshots":[{"event_id":"sha256:8097aad1eb2c353e59a435af90168c7a48b5003f202059baa5c93f62ce467bd0","target":"graph","created_at":"2026-07-05T10:20:40Z","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/2410.05760/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning diffusion models with user preferences has been a key challenge. Existing methods for aligning diffusion models either require retraining or are limited to differentiable reward functions. To address these limitations, we propose a stochastic optimization approach, dubbed Demon, to guide the denoising process at inference time without backpropagation through reward functions or model retraining. Our approach works by controlling noise distribution in denoising steps to concentrate density on regions corresponding to high rewards through stochastic optimization. We provide comprehensiv","authors_text":"Jun-Cheng Chen, Kuang-Huei Lee, Po-Hung Yeh","cross_cats":["cs.AI","cs.LG","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T07:33:49Z","title":"Training-free Diffusion Model Alignment with Sampling Demons"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05760","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":"sha256:7b90f4c5c4eae53d53fb1e9feca9590a4db0d88659d5350f2faea82dbd9e2081","target":"record","created_at":"2026-07-05T10:20:40Z","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":"3f3a162edf001ecd84af7930fd8d7816dd472b81c71f0d31899ee8c0113292b8","cross_cats_sorted":["cs.AI","cs.LG","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-08T07:33:49Z","title_canon_sha256":"86f5dd8dd7f1a599842c2cc72711f602a4d66584a6b5e4267de78571f8b866af"},"schema_version":"1.0","source":{"id":"2410.05760","kind":"arxiv","version":2}},"canonical_sha256":"12dc7b089751da8866847c8d77d6b1769d58625f1f8aa4df85c0bd9ac48412f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12dc7b089751da8866847c8d77d6b1769d58625f1f8aa4df85c0bd9ac48412f8","first_computed_at":"2026-07-05T10:20:40.317146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:20:40.317146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ebCqhpMH5nk3LnLp5cNMeY+0s8ngCCYPJXTq+HRQY/sfUKztkHwwq2nsPQ7yYg7yp45DL9AZvawwS3bz9BqBDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:20:40.317744Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.05760","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b90f4c5c4eae53d53fb1e9feca9590a4db0d88659d5350f2faea82dbd9e2081","sha256:8097aad1eb2c353e59a435af90168c7a48b5003f202059baa5c93f62ce467bd0"],"state_sha256":"30dcdc4cb931df33ee94b66427f2b172dc36916ba2dd61bdd9cb22db32ba74ea"}