{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YNJDBD6KHLTKEKAD4EAXA2U534","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":"4d6ac18a42a9f52df356e2bad797ffdc385c74d450ac77bdbb3349569f14aa8c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T14:20:53Z","title_canon_sha256":"11e17bd4f3d94891c3d2f8ab346212e3e5bfe39cc05299b8281be77c13c5df2f"},"schema_version":"1.0","source":{"id":"2406.11581","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11581","created_at":"2026-07-05T08:49:35Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11581v2","created_at":"2026-07-05T08:49:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11581","created_at":"2026-07-05T08:49:35Z"},{"alias_kind":"pith_short_12","alias_value":"YNJDBD6KHLTK","created_at":"2026-07-05T08:49:35Z"},{"alias_kind":"pith_short_16","alias_value":"YNJDBD6KHLTKEKAD","created_at":"2026-07-05T08:49:35Z"},{"alias_kind":"pith_short_8","alias_value":"YNJDBD6K","created_at":"2026-07-05T08:49:35Z"}],"graph_snapshots":[{"event_id":"sha256:f92bfe22c105546f9e751abe7e655d2f9c874ad584e8777e5a23df5c34056aac","target":"graph","created_at":"2026-07-05T08:49:35Z","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/2406.11581/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Numerous recent techniques for text style transfer characterize their approaches as variants of reinforcement learning and preference optimization. In this work, we consider the relationship between these approaches and a class of optimization approaches developed primarily for (non-neural) statistical machine translation, formerly known as `tuning'. Inspired by these techniques from the past, we improve upon established preference optimization approaches, incorporating multiple iterations of exploration and optimization, and choosing contrastive examples by following a `hope' vs `fear' sampli","authors_text":"Jonathan May, Shuai Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T14:20:53Z","title":"Style Transfer with Multi-iteration Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11581","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:d4e7ac101361708d0e4a1dde4e69a3b2a7395b040e1c96a94fb8d1face183890","target":"record","created_at":"2026-07-05T08:49:35Z","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":"4d6ac18a42a9f52df356e2bad797ffdc385c74d450ac77bdbb3349569f14aa8c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T14:20:53Z","title_canon_sha256":"11e17bd4f3d94891c3d2f8ab346212e3e5bfe39cc05299b8281be77c13c5df2f"},"schema_version":"1.0","source":{"id":"2406.11581","kind":"arxiv","version":2}},"canonical_sha256":"c352308fca3ae6a22803e101706a9ddf224c219d7f87b62f9941d7a9daf34044","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c352308fca3ae6a22803e101706a9ddf224c219d7f87b62f9941d7a9daf34044","first_computed_at":"2026-07-05T08:49:35.637436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:49:35.637436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JPJ4p0K8oguCPgY2by6lnDKgH2RYwdl8HLYRywwAZggOOmncmb6ishhwArTlJgrD6hjIGJBAnUrnfediCBa/CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:49:35.637886Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11581","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4e7ac101361708d0e4a1dde4e69a3b2a7395b040e1c96a94fb8d1face183890","sha256:f92bfe22c105546f9e751abe7e655d2f9c874ad584e8777e5a23df5c34056aac"],"state_sha256":"fb889934c515e7d3bb63b187ac4cca4a08130ce95e382ce171067c09ec187b83"}