{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6SQSOI7N4YL2J5LV2UP4LD4LJ2","short_pith_number":"pith:6SQSOI7N","canonical_record":{"source":{"id":"2410.07652","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T06:35:51Z","cross_cats_sorted":[],"title_canon_sha256":"82f178e51e1c9b79b09165fda6de28d3609a764e295e670d4d7483a5840269ff","abstract_canon_sha256":"377ee89eee027520f6757a527069e2d1814ad9af171b54765d21f54417ee7290"},"schema_version":"1.0"},"canonical_sha256":"f4a12723ede617a4f575d51fc58f8b4eb97a349b76b1852cb8c7f0fd900915f9","source":{"kind":"arxiv","id":"2410.07652","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07652","created_at":"2026-07-05T09:18:41Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07652v1","created_at":"2026-07-05T09:18:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07652","created_at":"2026-07-05T09:18:41Z"},{"alias_kind":"pith_short_12","alias_value":"6SQSOI7N4YL2","created_at":"2026-07-05T09:18:41Z"},{"alias_kind":"pith_short_16","alias_value":"6SQSOI7N4YL2J5LV","created_at":"2026-07-05T09:18:41Z"},{"alias_kind":"pith_short_8","alias_value":"6SQSOI7N","created_at":"2026-07-05T09:18:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6SQSOI7N4YL2J5LV2UP4LD4LJ2","target":"record","payload":{"canonical_record":{"source":{"id":"2410.07652","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T06:35:51Z","cross_cats_sorted":[],"title_canon_sha256":"82f178e51e1c9b79b09165fda6de28d3609a764e295e670d4d7483a5840269ff","abstract_canon_sha256":"377ee89eee027520f6757a527069e2d1814ad9af171b54765d21f54417ee7290"},"schema_version":"1.0"},"canonical_sha256":"f4a12723ede617a4f575d51fc58f8b4eb97a349b76b1852cb8c7f0fd900915f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:41.363532Z","signature_b64":"VBFbiZlC532HtlMV7lEuhO7EIhGQRTCz28ozlEoa1RtB1NlM2Kd6O910m56m91vhkLchs2pjsj9VsKcRrUipAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4a12723ede617a4f575d51fc58f8b4eb97a349b76b1852cb8c7f0fd900915f9","last_reissued_at":"2026-07-05T09:18:41.363001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:41.363001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.07652","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:18:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qpcLE+q4n7+rqvas6SuvSHGMno6WEgeNew0aeBGLVH1vFZRnCUWxxRPZVz187QQB9RsiRbquR6Qz5CgXSbeaCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T12:54:07.391946Z"},"content_sha256":"d13e7d7319d4fa60a6d4ddcb5555ed67135c7074561a04a9e460a47aba8eebc9","schema_version":"1.0","event_id":"sha256:d13e7d7319d4fa60a6d4ddcb5555ed67135c7074561a04a9e460a47aba8eebc9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6SQSOI7N4YL2J5LV2UP4LD4LJ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StablePrompt: Automatic Prompt Tuning using Reinforcement Learning for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gaeun Kim, Haeil Lee, Jongsuk Kim, Junmo Kim, Minchan Kwon","submitted_at":"2024-10-10T06:35:51Z","abstract_excerpt":"Finding appropriate prompts for the specific task has become an important issue as the usage of Large Language Models (LLM) has expanded. Reinforcement Learning (RL) is widely used for prompt tuning, but its inherent instability and environmental dependency make it difficult to use in practice. In this paper, we propose StablePrompt, which strikes a balance between training stability and search space, mitigating the instability of RL and producing high-performance prompts. We formulate prompt tuning as an online RL problem between the agent and target LLM and introduce Adaptive Proximal Policy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07652","kind":"arxiv","version":1},"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/2410.07652/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":"2026-07-05T09:18:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tVQ+7VR+r8zOu6FpZ7hjT2eqxx1FOFbtbarnb/B4vQYtFBebL+W20Rk9yuiLMqQqCvNam4vShHLKM79/k5KoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T12:54:07.394157Z"},"content_sha256":"d61c07488746b2679e672bb01c066a464af221619176c06bfa7ff5cfb2e9495d","schema_version":"1.0","event_id":"sha256:d61c07488746b2679e672bb01c066a464af221619176c06bfa7ff5cfb2e9495d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6SQSOI7N4YL2J5LV2UP4LD4LJ2/bundle.json","state_url":"https://pith.science/pith/6SQSOI7N4YL2J5LV2UP4LD4LJ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6SQSOI7N4YL2J5LV2UP4LD4LJ2/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":"2026-08-13T12:54:07Z","links":{"resolver":"https://pith.science/pith/6SQSOI7N4YL2J5LV2UP4LD4LJ2","bundle":"https://pith.science/pith/6SQSOI7N4YL2J5LV2UP4LD4LJ2/bundle.json","state":"https://pith.science/pith/6SQSOI7N4YL2J5LV2UP4LD4LJ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6SQSOI7N4YL2J5LV2UP4LD4LJ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6SQSOI7N4YL2J5LV2UP4LD4LJ2","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":"377ee89eee027520f6757a527069e2d1814ad9af171b54765d21f54417ee7290","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T06:35:51Z","title_canon_sha256":"82f178e51e1c9b79b09165fda6de28d3609a764e295e670d4d7483a5840269ff"},"schema_version":"1.0","source":{"id":"2410.07652","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07652","created_at":"2026-07-05T09:18:41Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07652v1","created_at":"2026-07-05T09:18:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07652","created_at":"2026-07-05T09:18:41Z"},{"alias_kind":"pith_short_12","alias_value":"6SQSOI7N4YL2","created_at":"2026-07-05T09:18:41Z"},{"alias_kind":"pith_short_16","alias_value":"6SQSOI7N4YL2J5LV","created_at":"2026-07-05T09:18:41Z"},{"alias_kind":"pith_short_8","alias_value":"6SQSOI7N","created_at":"2026-07-05T09:18:41Z"}],"graph_snapshots":[{"event_id":"sha256:d61c07488746b2679e672bb01c066a464af221619176c06bfa7ff5cfb2e9495d","target":"graph","created_at":"2026-07-05T09:18:41Z","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/2410.07652/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Finding appropriate prompts for the specific task has become an important issue as the usage of Large Language Models (LLM) has expanded. Reinforcement Learning (RL) is widely used for prompt tuning, but its inherent instability and environmental dependency make it difficult to use in practice. In this paper, we propose StablePrompt, which strikes a balance between training stability and search space, mitigating the instability of RL and producing high-performance prompts. We formulate prompt tuning as an online RL problem between the agent and target LLM and introduce Adaptive Proximal Policy","authors_text":"Gaeun Kim, Haeil Lee, Jongsuk Kim, Junmo Kim, Minchan Kwon","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T06:35:51Z","title":"StablePrompt: Automatic Prompt Tuning using Reinforcement Learning for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07652","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:d13e7d7319d4fa60a6d4ddcb5555ed67135c7074561a04a9e460a47aba8eebc9","target":"record","created_at":"2026-07-05T09:18:41Z","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":"377ee89eee027520f6757a527069e2d1814ad9af171b54765d21f54417ee7290","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T06:35:51Z","title_canon_sha256":"82f178e51e1c9b79b09165fda6de28d3609a764e295e670d4d7483a5840269ff"},"schema_version":"1.0","source":{"id":"2410.07652","kind":"arxiv","version":1}},"canonical_sha256":"f4a12723ede617a4f575d51fc58f8b4eb97a349b76b1852cb8c7f0fd900915f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4a12723ede617a4f575d51fc58f8b4eb97a349b76b1852cb8c7f0fd900915f9","first_computed_at":"2026-07-05T09:18:41.363001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:41.363001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VBFbiZlC532HtlMV7lEuhO7EIhGQRTCz28ozlEoa1RtB1NlM2Kd6O910m56m91vhkLchs2pjsj9VsKcRrUipAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:41.363532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.07652","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d13e7d7319d4fa60a6d4ddcb5555ed67135c7074561a04a9e460a47aba8eebc9","sha256:d61c07488746b2679e672bb01c066a464af221619176c06bfa7ff5cfb2e9495d"],"state_sha256":"7ef9578a56db63b43343d5163006c6349ab48645a97df2c0857ad0d943b8386e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wpn65VB7P4tLazlg39aSBCUmK+wsW1pdiFSJ3D4I+i80bFc81XK3nBxhWcEvMPQ+nDFFBiO9IZcgIno03BKUAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T12:54:07.401962Z","bundle_sha256":"159e04f7908140e2a1a50fe7ce161ccd7c59bb756b403ec4b93e54634ef88df9"}}