{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EAUKGLNCNEBNMU7CL2TURWE4WP","short_pith_number":"pith:EAUKGLNC","canonical_record":{"source":{"id":"2501.05803","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-10T09:10:30Z","cross_cats_sorted":["cs.AI","cs.CV","math.ST","stat.TH"],"title_canon_sha256":"9fa7fbd6b0874e56e69c28d68922ed7d7c552a3acce613a0f11c3c2bfe2c2698","abstract_canon_sha256":"ea7a463ce70eb8305b5fb7edff75fb56b937285982b6a3aa870fbe4d4541001f"},"schema_version":"1.0"},"canonical_sha256":"2028a32da26902d653e25ea748d89cb3f475e33a1cda75c7669113b8e828900e","source":{"kind":"arxiv","id":"2501.05803","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05803","created_at":"2026-07-05T10:50:31Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05803v3","created_at":"2026-07-05T10:50:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05803","created_at":"2026-07-05T10:50:31Z"},{"alias_kind":"pith_short_12","alias_value":"EAUKGLNCNEBN","created_at":"2026-07-05T10:50:31Z"},{"alias_kind":"pith_short_16","alias_value":"EAUKGLNCNEBNMU7C","created_at":"2026-07-05T10:50:31Z"},{"alias_kind":"pith_short_8","alias_value":"EAUKGLNC","created_at":"2026-07-05T10:50:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EAUKGLNCNEBNMU7CL2TURWE4WP","target":"record","payload":{"canonical_record":{"source":{"id":"2501.05803","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-10T09:10:30Z","cross_cats_sorted":["cs.AI","cs.CV","math.ST","stat.TH"],"title_canon_sha256":"9fa7fbd6b0874e56e69c28d68922ed7d7c552a3acce613a0f11c3c2bfe2c2698","abstract_canon_sha256":"ea7a463ce70eb8305b5fb7edff75fb56b937285982b6a3aa870fbe4d4541001f"},"schema_version":"1.0"},"canonical_sha256":"2028a32da26902d653e25ea748d89cb3f475e33a1cda75c7669113b8e828900e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:31.998976Z","signature_b64":"h7TikCCbm70CvDjyxN7BKtganSoMSMzJvYWMphXYPEDVtYgXXTJ1uJ24gYmn1WF07bvnA4d9fvnoPeqPdgJwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2028a32da26902d653e25ea748d89cb3f475e33a1cda75c7669113b8e828900e","last_reissued_at":"2026-07-05T10:50:31.998455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:31.998455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.05803","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:50:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ABU0XOlulq2bdJYH2z/y/zp/dPxl383dm8qGt77pH4XU9nBtPGLlMRaYMEtfUwurf4o55VVpYt86gJqcXllAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T13:03:03.106886Z"},"content_sha256":"1e067e6d1dd7a54781fe2b7b96a8145183141ac1e1fb8803cc458dcade532505","schema_version":"1.0","event_id":"sha256:1e067e6d1dd7a54781fe2b7b96a8145183141ac1e1fb8803cc458dcade532505"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EAUKGLNCNEBNMU7CL2TURWE4WP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Test-time Alignment of Diffusion Models without Reward Over-optimization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Dongmin Park, Minkyu Kim, Sunwoo Kim","submitted_at":"2025-01-10T09:10:30Z","abstract_excerpt":"Diffusion models excel in generative tasks, but aligning them with specific objectives while maintaining their versatility remains challenging. Existing fine-tuning methods often suffer from reward over-optimization, while approximate guidance approaches fail to optimize target rewards effectively. Addressing these limitations, we propose a training-free, test-time method based on Sequential Monte Carlo (SMC) to sample from the reward-aligned target distribution. Our approach, tailored for diffusion sampling and incorporating tempering techniques, achieves comparable or superior target rewards"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05803","kind":"arxiv","version":3},"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/2501.05803/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:50:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+DHHCWkny7V+51nDFTEMLGeLKqIxymofwLsU43zdmA4e0MR+WMixwiuQIpWH/evi3VpS4Yrh2oHjrJsXo7PIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T13:03:03.107521Z"},"content_sha256":"a54478b095f2272bb578305fe151fb1d4fe37f2a4a2fbe1aa975fc3eb1511a60","schema_version":"1.0","event_id":"sha256:a54478b095f2272bb578305fe151fb1d4fe37f2a4a2fbe1aa975fc3eb1511a60"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EAUKGLNCNEBNMU7CL2TURWE4WP/bundle.json","state_url":"https://pith.science/pith/EAUKGLNCNEBNMU7CL2TURWE4WP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EAUKGLNCNEBNMU7CL2TURWE4WP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T13:03:03Z","links":{"resolver":"https://pith.science/pith/EAUKGLNCNEBNMU7CL2TURWE4WP","bundle":"https://pith.science/pith/EAUKGLNCNEBNMU7CL2TURWE4WP/bundle.json","state":"https://pith.science/pith/EAUKGLNCNEBNMU7CL2TURWE4WP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EAUKGLNCNEBNMU7CL2TURWE4WP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EAUKGLNCNEBNMU7CL2TURWE4WP","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":"ea7a463ce70eb8305b5fb7edff75fb56b937285982b6a3aa870fbe4d4541001f","cross_cats_sorted":["cs.AI","cs.CV","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-10T09:10:30Z","title_canon_sha256":"9fa7fbd6b0874e56e69c28d68922ed7d7c552a3acce613a0f11c3c2bfe2c2698"},"schema_version":"1.0","source":{"id":"2501.05803","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05803","created_at":"2026-07-05T10:50:31Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05803v3","created_at":"2026-07-05T10:50:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05803","created_at":"2026-07-05T10:50:31Z"},{"alias_kind":"pith_short_12","alias_value":"EAUKGLNCNEBN","created_at":"2026-07-05T10:50:31Z"},{"alias_kind":"pith_short_16","alias_value":"EAUKGLNCNEBNMU7C","created_at":"2026-07-05T10:50:31Z"},{"alias_kind":"pith_short_8","alias_value":"EAUKGLNC","created_at":"2026-07-05T10:50:31Z"}],"graph_snapshots":[{"event_id":"sha256:a54478b095f2272bb578305fe151fb1d4fe37f2a4a2fbe1aa975fc3eb1511a60","target":"graph","created_at":"2026-07-05T10:50:31Z","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/2501.05803/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models excel in generative tasks, but aligning them with specific objectives while maintaining their versatility remains challenging. Existing fine-tuning methods often suffer from reward over-optimization, while approximate guidance approaches fail to optimize target rewards effectively. Addressing these limitations, we propose a training-free, test-time method based on Sequential Monte Carlo (SMC) to sample from the reward-aligned target distribution. Our approach, tailored for diffusion sampling and incorporating tempering techniques, achieves comparable or superior target rewards","authors_text":"Dongmin Park, Minkyu Kim, Sunwoo Kim","cross_cats":["cs.AI","cs.CV","math.ST","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-10T09:10:30Z","title":"Test-time Alignment of Diffusion Models without Reward Over-optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05803","kind":"arxiv","version":3},"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":"sha256:1e067e6d1dd7a54781fe2b7b96a8145183141ac1e1fb8803cc458dcade532505","target":"record","created_at":"2026-07-05T10:50:31Z","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":"ea7a463ce70eb8305b5fb7edff75fb56b937285982b6a3aa870fbe4d4541001f","cross_cats_sorted":["cs.AI","cs.CV","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-10T09:10:30Z","title_canon_sha256":"9fa7fbd6b0874e56e69c28d68922ed7d7c552a3acce613a0f11c3c2bfe2c2698"},"schema_version":"1.0","source":{"id":"2501.05803","kind":"arxiv","version":3}},"canonical_sha256":"2028a32da26902d653e25ea748d89cb3f475e33a1cda75c7669113b8e828900e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2028a32da26902d653e25ea748d89cb3f475e33a1cda75c7669113b8e828900e","first_computed_at":"2026-07-05T10:50:31.998455Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:31.998455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h7TikCCbm70CvDjyxN7BKtganSoMSMzJvYWMphXYPEDVtYgXXTJ1uJ24gYmn1WF07bvnA4d9fvnoPeqPdgJwDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:31.998976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.05803","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e067e6d1dd7a54781fe2b7b96a8145183141ac1e1fb8803cc458dcade532505","sha256:a54478b095f2272bb578305fe151fb1d4fe37f2a4a2fbe1aa975fc3eb1511a60"],"state_sha256":"3ddb114a320c7f2125e462c53f96547e5666ebef3733d80de06d546d390ac942"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6oqQscvhOjyMVadWTq9+Y46A/6c/D4JrWy55yYjQIzoVqxBKEKfMPX3kdkz4DJvA7Js2k6xj2kDwcRt/CH+zDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T13:03:03.113298Z","bundle_sha256":"2386ad7d44c1a1ef2426c7f6b06294b8c8275aa3f66deca52335ad6c455d825a"}}