{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QIOXRJZ7P5SLFAMDVRIJKITCSX","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":"94175793a626b224af49a46e7db6636b33f82e1440314cb0292d22372571b564","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T22:00:26Z","title_canon_sha256":"7cc39869bfc1d25e081afa9bf8fa206a1aba42846924f05f32f076e381d3c01f"},"schema_version":"1.0","source":{"id":"2406.12120","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12120","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12120v3","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12120","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"pith_short_12","alias_value":"QIOXRJZ7P5SL","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"pith_short_16","alias_value":"QIOXRJZ7P5SLFAMD","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"pith_short_8","alias_value":"QIOXRJZ7","created_at":"2026-07-05T10:18:38Z"}],"graph_snapshots":[{"event_id":"sha256:4e08206a6fb2295765623bdd3a82bb51df8aa482d92d1f9fb807e9920a216c3f","target":"graph","created_at":"2026-07-05T10:18:38Z","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/2406.12120/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models are powerful generative models that allow for precise control over the characteristics of the generated samples. While these diffusion models trained on large datasets have achieved success, there is often a need to introduce additional controls in downstream fine-tuning processes, treating these powerful models as pre-trained diffusion models. This work presents a novel method based on reinforcement learning (RL) to add such controls using an offline dataset comprising inputs and labels. We formulate this task as an RL problem, with the classifier learned from the offline dat","authors_text":"Ehsan Hajiramezanali, Gabriele Scalia, Masatoshi Uehara, Sergey Levine, Sunyuan Kung, Tommaso Biancalani, Yulai Zhao","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T22:00:26Z","title":"Adding Conditional Control to Diffusion Models with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12120","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":"sha256:94d3e049f8144a86d9f2f13f83114246600fc02947e7777dd7e00ea72611f4b6","target":"record","created_at":"2026-07-05T10:18:38Z","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":"94175793a626b224af49a46e7db6636b33f82e1440314cb0292d22372571b564","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T22:00:26Z","title_canon_sha256":"7cc39869bfc1d25e081afa9bf8fa206a1aba42846924f05f32f076e381d3c01f"},"schema_version":"1.0","source":{"id":"2406.12120","kind":"arxiv","version":3}},"canonical_sha256":"821d78a73f7f64b28183ac5095226295f7c36a304fa3b07d0b0480306586e233","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"821d78a73f7f64b28183ac5095226295f7c36a304fa3b07d0b0480306586e233","first_computed_at":"2026-07-05T10:18:38.342979Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:38.342979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CYQCK/bmvsIvEdVyZa0rZHEe2kd/NxxY/ZQ4cbmvhfMOv0NKQ68J4kEQFE5mSMsTAa/WvQlRAHsg4Scm1LXjBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:38.343493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12120","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94d3e049f8144a86d9f2f13f83114246600fc02947e7777dd7e00ea72611f4b6","sha256:4e08206a6fb2295765623bdd3a82bb51df8aa482d92d1f9fb807e9920a216c3f"],"state_sha256":"80810b92d3804542638f4409b8980b3c36130289ee050651e041f497e09a8d79"}