{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2GZUIZ5M5WEJGHPEOKWZZHXTE2","short_pith_number":"pith:2GZUIZ5M","canonical_record":{"source":{"id":"2307.07055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-13T20:20:40Z","cross_cats_sorted":[],"title_canon_sha256":"854d87b0818d84a9773b178e0d3441bb1179ac89e39b3568ba7734bab9f6148a","abstract_canon_sha256":"027329fd7270f45aafcfc454d958f610b3b98f21298e3f6979a7d154c1da7dcf"},"schema_version":"1.0"},"canonical_sha256":"d1b34467aced88931de472ad9c9ef326a1196f2821cfc6b71f685bb1ef245058","source":{"kind":"arxiv","id":"2307.07055","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.07055","created_at":"2026-07-05T06:30:49Z"},{"alias_kind":"arxiv_version","alias_value":"2307.07055v1","created_at":"2026-07-05T06:30:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07055","created_at":"2026-07-05T06:30:49Z"},{"alias_kind":"pith_short_12","alias_value":"2GZUIZ5M5WEJ","created_at":"2026-07-05T06:30:49Z"},{"alias_kind":"pith_short_16","alias_value":"2GZUIZ5M5WEJGHPE","created_at":"2026-07-05T06:30:49Z"},{"alias_kind":"pith_short_8","alias_value":"2GZUIZ5M","created_at":"2026-07-05T06:30:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2GZUIZ5M5WEJGHPEOKWZZHXTE2","target":"record","payload":{"canonical_record":{"source":{"id":"2307.07055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-13T20:20:40Z","cross_cats_sorted":[],"title_canon_sha256":"854d87b0818d84a9773b178e0d3441bb1179ac89e39b3568ba7734bab9f6148a","abstract_canon_sha256":"027329fd7270f45aafcfc454d958f610b3b98f21298e3f6979a7d154c1da7dcf"},"schema_version":"1.0"},"canonical_sha256":"d1b34467aced88931de472ad9c9ef326a1196f2821cfc6b71f685bb1ef245058","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:49.834053Z","signature_b64":"QK97HApsZ2NgoVlYMoBuf/CQ1+6GZHKjEi/t/IXf4a++o07BeWWoSr7iy/UYC1E4A+mPWJUfHivBM6aYeaHZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1b34467aced88931de472ad9c9ef326a1196f2821cfc6b71f685bb1ef245058","last_reissued_at":"2026-07-05T06:30:49.833605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:49.833605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.07055","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:30:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"huw/9rnhTsMFmVHzL5yfvHzSXCvwb7MKIjp2ua+nSVeCag1xikHZNez5rW3mDrWBnxwYqqB1GYEOqbXh11+8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:28:45.636646Z"},"content_sha256":"6d2343f845d154ace89a6f0dcc00abc97ecd78d2e2b503da3ecd4d271c2d31fb","schema_version":"1.0","event_id":"sha256:6d2343f845d154ace89a6f0dcc00abc97ecd78d2e2b503da3ecd4d271c2d31fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2GZUIZ5M5WEJGHPEOKWZZHXTE2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chengzhuo Ni, Hui Yuan, Kaixuan Huang, Mengdi Wang, Minshuo Chen","submitted_at":"2023-07-13T20:20:40Z","abstract_excerpt":"We explore the methodology and theory of reward-directed generation via conditional diffusion models. Directed generation aims to generate samples with desired properties as measured by a reward function, which has broad applications in generative AI, reinforcement learning, and computational biology. We consider the common learning scenario where the data set consists of unlabeled data along with a smaller set of data with noisy reward labels. Our approach leverages a learned reward function on the smaller data set as a pseudolabeler. From a theoretical standpoint, we show that this directed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07055","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/2307.07055/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":"2026-07-05T06:30:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ry00ApkK8ZARfZ56B1GWpZBE9ekTCC2H5fjJFbGFNifQr2MCdJE8aZhqA9kZPrDZeH4dJQwCzYhWSujlJUAUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:28:45.637158Z"},"content_sha256":"3c386929d9ba65a5871b5f147ceca5450e4b198d5b24b344100ba39f55247c32","schema_version":"1.0","event_id":"sha256:3c386929d9ba65a5871b5f147ceca5450e4b198d5b24b344100ba39f55247c32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2GZUIZ5M5WEJGHPEOKWZZHXTE2/bundle.json","state_url":"https://pith.science/pith/2GZUIZ5M5WEJGHPEOKWZZHXTE2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2GZUIZ5M5WEJGHPEOKWZZHXTE2/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":"2026-08-09T07:28:45Z","links":{"resolver":"https://pith.science/pith/2GZUIZ5M5WEJGHPEOKWZZHXTE2","bundle":"https://pith.science/pith/2GZUIZ5M5WEJGHPEOKWZZHXTE2/bundle.json","state":"https://pith.science/pith/2GZUIZ5M5WEJGHPEOKWZZHXTE2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2GZUIZ5M5WEJGHPEOKWZZHXTE2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2GZUIZ5M5WEJGHPEOKWZZHXTE2","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":"027329fd7270f45aafcfc454d958f610b3b98f21298e3f6979a7d154c1da7dcf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-13T20:20:40Z","title_canon_sha256":"854d87b0818d84a9773b178e0d3441bb1179ac89e39b3568ba7734bab9f6148a"},"schema_version":"1.0","source":{"id":"2307.07055","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.07055","created_at":"2026-07-05T06:30:49Z"},{"alias_kind":"arxiv_version","alias_value":"2307.07055v1","created_at":"2026-07-05T06:30:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07055","created_at":"2026-07-05T06:30:49Z"},{"alias_kind":"pith_short_12","alias_value":"2GZUIZ5M5WEJ","created_at":"2026-07-05T06:30:49Z"},{"alias_kind":"pith_short_16","alias_value":"2GZUIZ5M5WEJGHPE","created_at":"2026-07-05T06:30:49Z"},{"alias_kind":"pith_short_8","alias_value":"2GZUIZ5M","created_at":"2026-07-05T06:30:49Z"}],"graph_snapshots":[{"event_id":"sha256:3c386929d9ba65a5871b5f147ceca5450e4b198d5b24b344100ba39f55247c32","target":"graph","created_at":"2026-07-05T06:30:49Z","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/2307.07055/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore the methodology and theory of reward-directed generation via conditional diffusion models. Directed generation aims to generate samples with desired properties as measured by a reward function, which has broad applications in generative AI, reinforcement learning, and computational biology. We consider the common learning scenario where the data set consists of unlabeled data along with a smaller set of data with noisy reward labels. Our approach leverages a learned reward function on the smaller data set as a pseudolabeler. From a theoretical standpoint, we show that this directed ","authors_text":"Chengzhuo Ni, Hui Yuan, Kaixuan Huang, Mengdi Wang, Minshuo Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-13T20:20:40Z","title":"Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07055","kind":"arxiv","version":1},"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":"sha256:6d2343f845d154ace89a6f0dcc00abc97ecd78d2e2b503da3ecd4d271c2d31fb","target":"record","created_at":"2026-07-05T06:30:49Z","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":"027329fd7270f45aafcfc454d958f610b3b98f21298e3f6979a7d154c1da7dcf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-13T20:20:40Z","title_canon_sha256":"854d87b0818d84a9773b178e0d3441bb1179ac89e39b3568ba7734bab9f6148a"},"schema_version":"1.0","source":{"id":"2307.07055","kind":"arxiv","version":1}},"canonical_sha256":"d1b34467aced88931de472ad9c9ef326a1196f2821cfc6b71f685bb1ef245058","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1b34467aced88931de472ad9c9ef326a1196f2821cfc6b71f685bb1ef245058","first_computed_at":"2026-07-05T06:30:49.833605Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:30:49.833605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QK97HApsZ2NgoVlYMoBuf/CQ1+6GZHKjEi/t/IXf4a++o07BeWWoSr7iy/UYC1E4A+mPWJUfHivBM6aYeaHZBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:30:49.834053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.07055","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d2343f845d154ace89a6f0dcc00abc97ecd78d2e2b503da3ecd4d271c2d31fb","sha256:3c386929d9ba65a5871b5f147ceca5450e4b198d5b24b344100ba39f55247c32"],"state_sha256":"8f44ab7818d590f8ba5a9c42e62f325127861b122e7a9c50d24481388017f4d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JhYBSWUJFHNYoBiCSxQqgyltIaZWhk8Bq6fInaLFFcqWjxZ2prW8ljKd3MlcSkxeDIlvR/KkNgZPD4nyQiHuDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:28:45.641183Z","bundle_sha256":"e5ddbaaf54143f82975d8dbad34e5ce577463b191fa9702e1c0b79c6732b386c"}}