{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KAIY6OKUNU7VHG5DKAKVHBLLTO","short_pith_number":"pith:KAIY6OKU","schema_version":"1.0","canonical_sha256":"50118f39546d3f539ba3501553856b9bb8eb79d31bb002daec5a85f3b7671cb1","source":{"kind":"arxiv","id":"2209.11486","version":4},"attestation_state":"computed","paper":{"title":"MetaPrompting: Learning to Learn Better Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bohan Li, Hongyuan Dong, Wanxiang Che, Xinghao Wang, Yutai Hou","submitted_at":"2022-09-23T09:01:05Z","abstract_excerpt":"Prompting method is regarded as one of the crucial progress for few-shot nature language processing. Recent research on prompting moves from discrete tokens based ``hard prompts'' to continuous ``soft prompts'', which employ learnable vectors as pseudo prompt tokens and achieve better performance. Though showing promising prospects, these soft-prompting methods are observed to rely heavily on good initialization to take effect. Unfortunately, obtaining a perfect initialization for soft prompts requires understanding of inner language models working and elaborate design, which is no easy task a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2209.11486","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-23T09:01:05Z","cross_cats_sorted":[],"title_canon_sha256":"2b7b9cfcaf95e8ae897741eb7cbe03e35d9ef4908ef3f2f856d5c7dab7608bb3","abstract_canon_sha256":"5c25cf34e3617a02cec4bc89940e67ca1fc6b1339c945d1d2b02b5611f7036e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:28.982121Z","signature_b64":"OhA6m2WgooV0gp3IGKqFpNS8Lt/oZXHvPalvSlO8zKu67rIrH+uSMJd6dSUct+o0i755XiPvdFriVtuYliikAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50118f39546d3f539ba3501553856b9bb8eb79d31bb002daec5a85f3b7671cb1","last_reissued_at":"2026-07-05T05:38:28.981677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:28.981677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MetaPrompting: Learning to Learn Better Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bohan Li, Hongyuan Dong, Wanxiang Che, Xinghao Wang, Yutai Hou","submitted_at":"2022-09-23T09:01:05Z","abstract_excerpt":"Prompting method is regarded as one of the crucial progress for few-shot nature language processing. Recent research on prompting moves from discrete tokens based ``hard prompts'' to continuous ``soft prompts'', which employ learnable vectors as pseudo prompt tokens and achieve better performance. Though showing promising prospects, these soft-prompting methods are observed to rely heavily on good initialization to take effect. Unfortunately, obtaining a perfect initialization for soft prompts requires understanding of inner language models working and elaborate design, which is no easy task a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.11486","kind":"arxiv","version":4},"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/2209.11486/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2209.11486","created_at":"2026-07-05T05:38:28.981736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.11486v4","created_at":"2026-07-05T05:38:28.981736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.11486","created_at":"2026-07-05T05:38:28.981736+00:00"},{"alias_kind":"pith_short_12","alias_value":"KAIY6OKUNU7V","created_at":"2026-07-05T05:38:28.981736+00:00"},{"alias_kind":"pith_short_16","alias_value":"KAIY6OKUNU7VHG5D","created_at":"2026-07-05T05:38:28.981736+00:00"},{"alias_kind":"pith_short_8","alias_value":"KAIY6OKU","created_at":"2026-07-05T05:38:28.981736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02096","citing_title":"Foundation Models as Oracles for Refactoring Correctness Detection","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20728","citing_title":"VTOS: Learning to Orchestrate Vision Tools by Co-Searching Solutions and Observers","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02096","citing_title":"Foundation Models as Oracles for Refactoring Correctness Detection","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KAIY6OKUNU7VHG5DKAKVHBLLTO","json":"https://pith.science/pith/KAIY6OKUNU7VHG5DKAKVHBLLTO.json","graph_json":"https://pith.science/api/pith-number/KAIY6OKUNU7VHG5DKAKVHBLLTO/graph.json","events_json":"https://pith.science/api/pith-number/KAIY6OKUNU7VHG5DKAKVHBLLTO/events.json","paper":"https://pith.science/paper/KAIY6OKU"},"agent_actions":{"view_html":"https://pith.science/pith/KAIY6OKUNU7VHG5DKAKVHBLLTO","download_json":"https://pith.science/pith/KAIY6OKUNU7VHG5DKAKVHBLLTO.json","view_paper":"https://pith.science/paper/KAIY6OKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.11486&json=true","fetch_graph":"https://pith.science/api/pith-number/KAIY6OKUNU7VHG5DKAKVHBLLTO/graph.json","fetch_events":"https://pith.science/api/pith-number/KAIY6OKUNU7VHG5DKAKVHBLLTO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KAIY6OKUNU7VHG5DKAKVHBLLTO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KAIY6OKUNU7VHG5DKAKVHBLLTO/action/storage_attestation","attest_author":"https://pith.science/pith/KAIY6OKUNU7VHG5DKAKVHBLLTO/action/author_attestation","sign_citation":"https://pith.science/pith/KAIY6OKUNU7VHG5DKAKVHBLLTO/action/citation_signature","submit_replication":"https://pith.science/pith/KAIY6OKUNU7VHG5DKAKVHBLLTO/action/replication_record"}},"created_at":"2026-07-05T05:38:28.981736+00:00","updated_at":"2026-07-05T05:38:28.981736+00:00"}