{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YBZFXSDFWY2RR35LZQWL62VY7K","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":"7907426d61a3f8eaa7ddbef8247bc28aa49f101f774d05aa54d8aea808886b16","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T20:03:08Z","title_canon_sha256":"10dbfe9327b89fef861c2569f0a0467c19bbf6fe063adfa34f2f2d8cea03243c"},"schema_version":"1.0","source":{"id":"2605.27642","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27642","created_at":"2026-05-28T01:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27642v1","created_at":"2026-05-28T01:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27642","created_at":"2026-05-28T01:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"YBZFXSDFWY2R","created_at":"2026-05-28T01:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"YBZFXSDFWY2RR35L","created_at":"2026-05-28T01:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"YBZFXSDF","created_at":"2026-05-28T01:04:45Z"}],"graph_snapshots":[{"event_id":"sha256:7875b7e32797fb0081faf80e6bb880715be529cbd8c80554e974f62584979648","target":"graph","created_at":"2026-05-28T01:04:45Z","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/2605.27642/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Soft prompt tuning is a parameter-efficient method for adapting LLMs to specific tasks, but suffers from a lack of interpretability. Building on recent work on interpreting soft prompts (Ramati et al., 2024), we explore how training a dedicated soft prompt to natural language translation model can yield higher translation quality. In particular, in both quantitative and qualitative comparisons on multiple Datasets of Datasets (DoDs), we demonstrate that our translator produces fluent, accurate verbalizations that outperforms existing training-free methods like InSPEcT. In addition to advancing","authors_text":"Jacob Whitehill, Pitipat Kongsomjit, Suryansh Goyal","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T20:03:08Z","title":"Learning to Translate from Soft to Hard LLM Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27642","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:cfe84d37953e6377d48977e91fed2f47c730aeb0e2eb7f251dcb16ee8ef0d1cf","target":"record","created_at":"2026-05-28T01:04:45Z","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":"7907426d61a3f8eaa7ddbef8247bc28aa49f101f774d05aa54d8aea808886b16","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T20:03:08Z","title_canon_sha256":"10dbfe9327b89fef861c2569f0a0467c19bbf6fe063adfa34f2f2d8cea03243c"},"schema_version":"1.0","source":{"id":"2605.27642","kind":"arxiv","version":1}},"canonical_sha256":"c0725bc865b63518efabcc2cbf6ab8fab75797e6b8ed35a56a6e0fa82a9fa270","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0725bc865b63518efabcc2cbf6ab8fab75797e6b8ed35a56a6e0fa82a9fa270","first_computed_at":"2026-05-28T01:04:45.116018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:45.116018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7e0DGgfHB8OAFMpiJUHBSvFBvenbxsgHT4vXnObWipggTInNMW5c9fPydWO7ZCBdYB2IxDf8jbolw85zm7tvDg==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:45.116435Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27642","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfe84d37953e6377d48977e91fed2f47c730aeb0e2eb7f251dcb16ee8ef0d1cf","sha256:7875b7e32797fb0081faf80e6bb880715be529cbd8c80554e974f62584979648"],"state_sha256":"3f8fe650af77f78de5dc4ade351a0d42cf999426249a61ad94b66741340cd215"}