{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YSHUYZCMQKGYXMUHLDYMOLY2C4","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":"8800706c54980c16eac53f069894a7141e8f6365b1b8532880635c681735a422","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-05T17:59:18Z","title_canon_sha256":"642c2a71ec546ebe9d567287e9affdd7d3bf71008dd3a28e7af581c77e7b04ab"},"schema_version":"1.0","source":{"id":"2310.03739","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03739","created_at":"2026-07-05T09:32:03Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03739v5","created_at":"2026-07-05T09:32:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03739","created_at":"2026-07-05T09:32:03Z"},{"alias_kind":"pith_short_12","alias_value":"YSHUYZCMQKGY","created_at":"2026-07-05T09:32:03Z"},{"alias_kind":"pith_short_16","alias_value":"YSHUYZCMQKGYXMUH","created_at":"2026-07-05T09:32:03Z"},{"alias_kind":"pith_short_8","alias_value":"YSHUYZCM","created_at":"2026-07-05T09:32:03Z"}],"graph_snapshots":[{"event_id":"sha256:36f0fc976a4c4db4a62a90cebca9c383f39922d543abf3873ba1ded0fbfb5112","target":"graph","created_at":"2026-07-05T09:32:03Z","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/2310.03739/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-image diffusion models have recently emerged at the forefront of image generation, powered by very large-scale unsupervised or weakly supervised text-to-image training datasets. Due to their unsupervised training, controlling their behavior in downstream tasks, such as maximizing human-perceived image quality, image-text alignment, or ethical image generation, is difficult. Recent works finetune diffusion models to downstream reward functions using vanilla reinforcement learning, notorious for the high variance of the gradient estimators. In this paper, we propose AlignProp, a method t","authors_text":"Anirudh Goyal, Deepak Pathak, Katerina Fragkiadaki, Mihir Prabhudesai","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-05T17:59:18Z","title":"Aligning Text-to-Image Diffusion Models with Reward Backpropagation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03739","kind":"arxiv","version":5},"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:cb3b6b6d54a6c1cf53f9923da0e79a040482e7cdac60c106053153fc4b306712","target":"record","created_at":"2026-07-05T09:32:03Z","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":"8800706c54980c16eac53f069894a7141e8f6365b1b8532880635c681735a422","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-05T17:59:18Z","title_canon_sha256":"642c2a71ec546ebe9d567287e9affdd7d3bf71008dd3a28e7af581c77e7b04ab"},"schema_version":"1.0","source":{"id":"2310.03739","kind":"arxiv","version":5}},"canonical_sha256":"c48f4c644c828d8bb28758f0c72f1a172b9412a0739989fdd53f5eb4de9e88e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c48f4c644c828d8bb28758f0c72f1a172b9412a0739989fdd53f5eb4de9e88e9","first_computed_at":"2026-07-05T09:32:03.745344Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:32:03.745344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mO2G9/XmzLGbfXEkGZtex++zY3cbNfLcR0yeGkqMrmyeiuF9+WhHfD43cDl0atmq2WvNyNZur/QvhzUT/O1+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:32:03.745919Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.03739","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb3b6b6d54a6c1cf53f9923da0e79a040482e7cdac60c106053153fc4b306712","sha256:36f0fc976a4c4db4a62a90cebca9c383f39922d543abf3873ba1ded0fbfb5112"],"state_sha256":"9362bf1e116f5cd7dc98626fcb29e928475ae561fc338dfc7c7012ab131d686b"}