{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DOOWQ4BPSQTPX2HQH36B5NR2N3","short_pith_number":"pith:DOOWQ4BP","canonical_record":{"source":{"id":"2505.17352","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T00:08:49Z","cross_cats_sorted":[],"title_canon_sha256":"5b5f8311475828b31c6cd9880bfe01d5f5011f460938092523be5a25f369e79e","abstract_canon_sha256":"822cdc021426df8a23d2928052bab6f7262bb89c01130266cff405920ce49922"},"schema_version":"1.0"},"canonical_sha256":"1b9d68702f9426fbe8f03efc1eb63a6ed2505055652cea467c9f68068b57260f","source":{"kind":"arxiv","id":"2505.17352","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DOOWQ4BPSQTPX2HQH36B5NR2N3","target":"record","payload":{"canonical_record":{"source":{"id":"2505.17352","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T00:08:49Z","cross_cats_sorted":[],"title_canon_sha256":"5b5f8311475828b31c6cd9880bfe01d5f5011f460938092523be5a25f369e79e","abstract_canon_sha256":"822cdc021426df8a23d2928052bab6f7262bb89c01130266cff405920ce49922"},"schema_version":"1.0"},"canonical_sha256":"1b9d68702f9426fbe8f03efc1eb63a6ed2505055652cea467c9f68068b57260f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:05.165715Z","signature_b64":"X79/oDXPzmG4aidx6Iy+U1ZwgwEiFSI5xq/+Q48bt7gF4emRjAvHuYmtuhX4jbHx0/MD4wWD/Au1PRXkVdx+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b9d68702f9426fbe8f03efc1eb63a6ed2505055652cea467c9f68068b57260f","last_reissued_at":"2026-05-20T00:02:05.164986Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:05.164986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.17352","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8tZodxYU6X99zpdt0vWCHVdboHdsUKnn3MgskrPlcDzZ91AHIhkGxY5k6JgKSSm1z2LGuNHG8cK0QZpLun1PAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:35:13.872862Z"},"content_sha256":"e880dfc933b9c32468f51406fcc4e953dad201e99fe20e1e4a1dfc9a8f9a6f2b","schema_version":"1.0","event_id":"sha256:e880dfc933b9c32468f51406fcc4e953dad201e99fe20e1e4a1dfc9a8f9a6f2b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DOOWQ4BPSQTPX2HQH36B5NR2N3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Alignment and Safety of Diffusion Models via Reinforcement Learning and Reward Modeling: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ankita Kushwaha, Kiran Ravish, Pawan Kumar, Preeti Lamba","submitted_at":"2025-05-23T00:08:49Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17352","kind":"arxiv","version":2},"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/2505.17352/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":"2026-05-20T00:02:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sBzp3gFNiZvn2OozkReRhPyERmanurUw2G5fGKd7mbeUJdL9PE3CF7oJ5/YHmcK4yINZV2avUBTvHcHDch2KDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:35:13.873500Z"},"content_sha256":"586227c861847948886d333a9547ab786fdbcdcade640e63499535d5eb6c310c","schema_version":"1.0","event_id":"sha256:586227c861847948886d333a9547ab786fdbcdcade640e63499535d5eb6c310c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DOOWQ4BPSQTPX2HQH36B5NR2N3/bundle.json","state_url":"https://pith.science/pith/DOOWQ4BPSQTPX2HQH36B5NR2N3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DOOWQ4BPSQTPX2HQH36B5NR2N3/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":"2026-05-27T02:35:13Z","links":{"resolver":"https://pith.science/pith/DOOWQ4BPSQTPX2HQH36B5NR2N3","bundle":"https://pith.science/pith/DOOWQ4BPSQTPX2HQH36B5NR2N3/bundle.json","state":"https://pith.science/pith/DOOWQ4BPSQTPX2HQH36B5NR2N3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DOOWQ4BPSQTPX2HQH36B5NR2N3/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YN1z3ojmUd0RIX0KiyxLsOonkEN0p814AtD5V9vYY+WFaTYnfegjt9FV4QdXEMv0p3PvglkIuikp6jKOPg3nDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T02:35:13.876771Z","bundle_sha256":"60c8b3746ba2caa8fe38b2497325e7285bf5758a1362ee3faa8d880dcf34ad31"}}