{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P3NLHCPLSMBGXDEXVJW5YPQR73","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":"e43703cab0667fc83aff2277cada747c8e5ab5e24900626fe5e3899ad686cf61","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T18:59:18Z","title_canon_sha256":"29bca147e3148d6c64be03e493a220f0d5f7080757c1f704fce30d683708c436"},"schema_version":"1.0","source":{"id":"2402.10210","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10210","created_at":"2026-07-05T07:45:42Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10210v1","created_at":"2026-07-05T07:45:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10210","created_at":"2026-07-05T07:45:42Z"},{"alias_kind":"pith_short_12","alias_value":"P3NLHCPLSMBG","created_at":"2026-07-05T07:45:42Z"},{"alias_kind":"pith_short_16","alias_value":"P3NLHCPLSMBGXDEX","created_at":"2026-07-05T07:45:42Z"},{"alias_kind":"pith_short_8","alias_value":"P3NLHCPL","created_at":"2026-07-05T07:45:42Z"}],"graph_snapshots":[{"event_id":"sha256:1cf51a93bf75ca2bfd106f5044be1054bcaec30a1d570244e101a4b1ba9a0062","target":"graph","created_at":"2026-07-05T07:45:42Z","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/2402.10210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning Diffusion Models remains an underexplored frontier in generative artificial intelligence (GenAI), especially when compared with the remarkable progress made in fine-tuning Large Language Models (LLMs). While cutting-edge diffusion models such as Stable Diffusion (SD) and SDXL rely on supervised fine-tuning, their performance inevitably plateaus after seeing a certain volume of data. Recently, reinforcement learning (RL) has been employed to fine-tune diffusion models with human preference data, but it requires at least two images (\"winner\" and \"loser\" images) for each text prompt. ","authors_text":"Huizhuo Yuan, Kaixuan Ji, Quanquan Gu, Zixiang Chen","cross_cats":["cs.AI","cs.CL","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T18:59:18Z","title":"Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10210","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:e32c85e87e21bfd98b9a4cde5502fa513d6a5baa5650a280c6899fab225afd7d","target":"record","created_at":"2026-07-05T07:45:42Z","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":"e43703cab0667fc83aff2277cada747c8e5ab5e24900626fe5e3899ad686cf61","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T18:59:18Z","title_canon_sha256":"29bca147e3148d6c64be03e493a220f0d5f7080757c1f704fce30d683708c436"},"schema_version":"1.0","source":{"id":"2402.10210","kind":"arxiv","version":1}},"canonical_sha256":"7edab389eb93026b8c97aa6ddc3e11fedc5a156441e5fcc7fc29dfe54b7ceb26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7edab389eb93026b8c97aa6ddc3e11fedc5a156441e5fcc7fc29dfe54b7ceb26","first_computed_at":"2026-07-05T07:45:42.698930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:45:42.698930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KKe8Sky9UXAjvOP/xaLKXUtPCre0Zef4KCZ/vemxv24CkZ9GGbl6N6hEdWnxlzUQq/0tta2WBvJh5ZZSOJjsCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:45:42.699399Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.10210","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e32c85e87e21bfd98b9a4cde5502fa513d6a5baa5650a280c6899fab225afd7d","sha256:1cf51a93bf75ca2bfd106f5044be1054bcaec30a1d570244e101a4b1ba9a0062"],"state_sha256":"6b590d86a68de1e6b7cf05278a0b1981561a899c83f86da370e0ab67a08a4832"}