{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DOOWQ4BPSQTPX2HQH36B5NR2N3","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":"822cdc021426df8a23d2928052bab6f7262bb89c01130266cff405920ce49922","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T00:08:49Z","title_canon_sha256":"5b5f8311475828b31c6cd9880bfe01d5f5011f460938092523be5a25f369e79e"},"schema_version":"1.0","source":{"id":"2505.17352","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17352","created_at":"2026-05-20T00:02:05Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17352v2","created_at":"2026-05-20T00:02:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17352","created_at":"2026-05-20T00:02:05Z"},{"alias_kind":"pith_short_12","alias_value":"DOOWQ4BPSQTP","created_at":"2026-05-20T00:02:05Z"},{"alias_kind":"pith_short_16","alias_value":"DOOWQ4BPSQTPX2HQ","created_at":"2026-05-20T00:02:05Z"},{"alias_kind":"pith_short_8","alias_value":"DOOWQ4BP","created_at":"2026-05-20T00:02:05Z"}],"graph_snapshots":[{"event_id":"sha256:586227c861847948886d333a9547ab786fdbcdcade640e63499535d5eb6c310c","target":"graph","created_at":"2026-05-20T00:02:05Z","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/2505.17352/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have become a central paradigm for image and multimodal generation, yet their deployment raises persistent questions about alignment, safety, preference satisfaction, and robustness to misuse. This survey reviews recent progress on aligning text-to-image diffusion models through reinforcement learning, reward modeling, preference optimization, and safety-specific fine-tuning. We organize the literature along five axes: the source of feedback, the form of the reward or preference signal, the optimization mechanism, the treatment of distribution shift and reward overoptimization","authors_text":"Ankita Kushwaha, Kiran Ravish, Pawan Kumar, Preeti Lamba","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T00:08:49Z","title":"Alignment and Safety of Diffusion Models via Reinforcement Learning and Reward Modeling: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17352","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:e880dfc933b9c32468f51406fcc4e953dad201e99fe20e1e4a1dfc9a8f9a6f2b","target":"record","created_at":"2026-05-20T00:02:05Z","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":"822cdc021426df8a23d2928052bab6f7262bb89c01130266cff405920ce49922","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T00:08:49Z","title_canon_sha256":"5b5f8311475828b31c6cd9880bfe01d5f5011f460938092523be5a25f369e79e"},"schema_version":"1.0","source":{"id":"2505.17352","kind":"arxiv","version":2}},"canonical_sha256":"1b9d68702f9426fbe8f03efc1eb63a6ed2505055652cea467c9f68068b57260f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b9d68702f9426fbe8f03efc1eb63a6ed2505055652cea467c9f68068b57260f","first_computed_at":"2026-05-20T00:02:05.164986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:05.164986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X79/oDXPzmG4aidx6Iy+U1ZwgwEiFSI5xq/+Q48bt7gF4emRjAvHuYmtuhX4jbHx0/MD4wWD/Au1PRXkVdx+Dw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:05.165715Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17352","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e880dfc933b9c32468f51406fcc4e953dad201e99fe20e1e4a1dfc9a8f9a6f2b","sha256:586227c861847948886d333a9547ab786fdbcdcade640e63499535d5eb6c310c"],"state_sha256":"c6dad12e917b32387a7aaec11a7d14734978af3d632b02fd3b8d59f939a58759"}