{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KLEEZOUVWP3BMHPPJFMZZWYVYV","short_pith_number":"pith:KLEEZOUV","canonical_record":{"source":{"id":"2206.03931","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-08T14:48:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6daf359980b52d69cf5a7725a1984420f381220ddd2610658e66346f83052fcd","abstract_canon_sha256":"928a671ee70af7a2d839b347736236712bb948b0fc5a3ca7239a88e39ce44596"},"schema_version":"1.0"},"canonical_sha256":"52c84cba95b3f6161def49599cdb15c554c6764a475346dff619d3b20819a9c7","source":{"kind":"arxiv","id":"2206.03931","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.03931","created_at":"2026-07-05T05:06:12Z"},{"alias_kind":"arxiv_version","alias_value":"2206.03931v3","created_at":"2026-07-05T05:06:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03931","created_at":"2026-07-05T05:06:12Z"},{"alias_kind":"pith_short_12","alias_value":"KLEEZOUVWP3B","created_at":"2026-07-05T05:06:12Z"},{"alias_kind":"pith_short_16","alias_value":"KLEEZOUVWP3BMHPP","created_at":"2026-07-05T05:06:12Z"},{"alias_kind":"pith_short_8","alias_value":"KLEEZOUV","created_at":"2026-07-05T05:06:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KLEEZOUVWP3BMHPPJFMZZWYVYV","target":"record","payload":{"canonical_record":{"source":{"id":"2206.03931","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-08T14:48:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6daf359980b52d69cf5a7725a1984420f381220ddd2610658e66346f83052fcd","abstract_canon_sha256":"928a671ee70af7a2d839b347736236712bb948b0fc5a3ca7239a88e39ce44596"},"schema_version":"1.0"},"canonical_sha256":"52c84cba95b3f6161def49599cdb15c554c6764a475346dff619d3b20819a9c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:12.809727Z","signature_b64":"ehFgMHyU+Wxral70IFYkLrsKijXD4PnRt9AXcv8EC7OHub6VJcsge/ShSdw0bU6+edsarj/PNhUq4uQgohVWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52c84cba95b3f6161def49599cdb15c554c6764a475346dff619d3b20819a9c7","last_reissued_at":"2026-07-05T05:06:12.809222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:12.809222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.03931","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:06:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IPEidwVTTzxdnkgmI5B2Une1Slw2qcThIpqDiagqt5QEjdeg8YsERFqJ/EUgv1uLY5EVZvFZKm4mjyGIFAjzCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:41:39.881434Z"},"content_sha256":"53e451c1b0b1ef97e2e114c47b443c221dcf2d3bd6232971ba1965dd50705b69","schema_version":"1.0","event_id":"sha256:53e451c1b0b1ef97e2e114c47b443c221dcf2d3bd6232971ba1965dd50705b69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KLEEZOUVWP3BMHPPJFMZZWYVYV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Generate Prompts for Dialogue Generation through Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chung Ho Lam, Hsuan Su, Hung-yi Lee, Pohan Chi, Saurav Sahay, Shang-Tse Chen, Shih-Cheng Huang","submitted_at":"2022-06-08T14:48:06Z","abstract_excerpt":"Much literature has shown that prompt-based learning is an efficient method to make use of the large pre-trained language model. Recent works also exhibit the possibility of steering a chatbot's output by plugging in an appropriate prompt. Gradient-based methods are often used to perturb the prompts. However, some language models are not even available to the public. In this work, we first explored the combination of prompting and reinforcement learning (RL) to steer models' generation without accessing any of the models' parameters. Second, to reduce the training effort and enhance the genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03931","kind":"arxiv","version":3},"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/2206.03931/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":"2026-07-05T05:06:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vz2TiDTy1podtm7Pn5E5V4pQfKvyG20l51gaT5SEDVzrlQypj1Igdck7tuyAWlP99Vi4B/uscefs5I+8OFapBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:41:39.882832Z"},"content_sha256":"976ca9eea02b28a3bb300b77964ae07b3ba5971f00f68d7ea502539020a76a19","schema_version":"1.0","event_id":"sha256:976ca9eea02b28a3bb300b77964ae07b3ba5971f00f68d7ea502539020a76a19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KLEEZOUVWP3BMHPPJFMZZWYVYV/bundle.json","state_url":"https://pith.science/pith/KLEEZOUVWP3BMHPPJFMZZWYVYV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KLEEZOUVWP3BMHPPJFMZZWYVYV/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":"2026-07-07T14:41:39Z","links":{"resolver":"https://pith.science/pith/KLEEZOUVWP3BMHPPJFMZZWYVYV","bundle":"https://pith.science/pith/KLEEZOUVWP3BMHPPJFMZZWYVYV/bundle.json","state":"https://pith.science/pith/KLEEZOUVWP3BMHPPJFMZZWYVYV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KLEEZOUVWP3BMHPPJFMZZWYVYV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KLEEZOUVWP3BMHPPJFMZZWYVYV","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":"928a671ee70af7a2d839b347736236712bb948b0fc5a3ca7239a88e39ce44596","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-08T14:48:06Z","title_canon_sha256":"6daf359980b52d69cf5a7725a1984420f381220ddd2610658e66346f83052fcd"},"schema_version":"1.0","source":{"id":"2206.03931","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.03931","created_at":"2026-07-05T05:06:12Z"},{"alias_kind":"arxiv_version","alias_value":"2206.03931v3","created_at":"2026-07-05T05:06:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03931","created_at":"2026-07-05T05:06:12Z"},{"alias_kind":"pith_short_12","alias_value":"KLEEZOUVWP3B","created_at":"2026-07-05T05:06:12Z"},{"alias_kind":"pith_short_16","alias_value":"KLEEZOUVWP3BMHPP","created_at":"2026-07-05T05:06:12Z"},{"alias_kind":"pith_short_8","alias_value":"KLEEZOUV","created_at":"2026-07-05T05:06:12Z"}],"graph_snapshots":[{"event_id":"sha256:976ca9eea02b28a3bb300b77964ae07b3ba5971f00f68d7ea502539020a76a19","target":"graph","created_at":"2026-07-05T05:06:12Z","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/2206.03931/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Much literature has shown that prompt-based learning is an efficient method to make use of the large pre-trained language model. Recent works also exhibit the possibility of steering a chatbot's output by plugging in an appropriate prompt. Gradient-based methods are often used to perturb the prompts. However, some language models are not even available to the public. In this work, we first explored the combination of prompting and reinforcement learning (RL) to steer models' generation without accessing any of the models' parameters. Second, to reduce the training effort and enhance the genera","authors_text":"Chung Ho Lam, Hsuan Su, Hung-yi Lee, Pohan Chi, Saurav Sahay, Shang-Tse Chen, Shih-Cheng Huang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-08T14:48:06Z","title":"Learning to Generate Prompts for Dialogue Generation through Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03931","kind":"arxiv","version":3},"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":"sha256:53e451c1b0b1ef97e2e114c47b443c221dcf2d3bd6232971ba1965dd50705b69","target":"record","created_at":"2026-07-05T05:06:12Z","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":"928a671ee70af7a2d839b347736236712bb948b0fc5a3ca7239a88e39ce44596","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-08T14:48:06Z","title_canon_sha256":"6daf359980b52d69cf5a7725a1984420f381220ddd2610658e66346f83052fcd"},"schema_version":"1.0","source":{"id":"2206.03931","kind":"arxiv","version":3}},"canonical_sha256":"52c84cba95b3f6161def49599cdb15c554c6764a475346dff619d3b20819a9c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52c84cba95b3f6161def49599cdb15c554c6764a475346dff619d3b20819a9c7","first_computed_at":"2026-07-05T05:06:12.809222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:12.809222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ehFgMHyU+Wxral70IFYkLrsKijXD4PnRt9AXcv8EC7OHub6VJcsge/ShSdw0bU6+edsarj/PNhUq4uQgohVWAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:12.809727Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.03931","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53e451c1b0b1ef97e2e114c47b443c221dcf2d3bd6232971ba1965dd50705b69","sha256:976ca9eea02b28a3bb300b77964ae07b3ba5971f00f68d7ea502539020a76a19"],"state_sha256":"6255d762e02354e6bb8f962818c93be0155a2ca8f8b5b278a747d7408238a779"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"42Eta3Ci4vF2OhpTHjpn5+wRD+LRurVcRt4qeq3FC7m04GgUlT7J+doh7Up1QtozDL9S3KXHGQ1PDf0mmub6Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:41:39.884787Z","bundle_sha256":"6945237f674f38ccd7ee514370e536d725c84b470981a8252c96e4e94d1ff5f3"}}