{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7PPA3CJLM5T66FLYKU3TN75MAF","short_pith_number":"pith:7PPA3CJL","schema_version":"1.0","canonical_sha256":"fbde0d892b6767ef1578553736ffac016c2dcbd60834fb8155fcef2d11808080","source":{"kind":"arxiv","id":"2208.10160","version":2},"attestation_state":"computed","paper":{"title":"PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Du, Dacheng Tao, Juhua Liu, Liang Ding, Qihuang Zhong","submitted_at":"2022-08-22T09:14:14Z","abstract_excerpt":"Prompt Transfer (PoT) is a recently-proposed approach to improve prompt-tuning, by initializing the target prompt with the existing prompt trained on similar source tasks. However, such a vanilla PoT approach usually achieves sub-optimal performance, as (i) the PoT is sensitive to the similarity of source-target pair and (ii) directly fine-tuning the prompt initialized with source prompt on target task might lead to forgetting of the useful general knowledge learned from source task. To tackle these issues, we propose a new metric to accurately predict the prompt transferability (regarding (i)"},"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":"2208.10160","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-08-22T09:14:14Z","cross_cats_sorted":[],"title_canon_sha256":"eba0ecf3e904fa9b851393d90eed65e2e990ac018ae16c61626639724d98f8b3","abstract_canon_sha256":"0d1962815315e431cf848186d5cc84abc69c5c035179e03aee849da972edafc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:04.925579Z","signature_b64":"ukxuotFWfKUdG8jYDIwYjNiM/hGtvDAJOuuvLWi+2YZ05lSZ18H7h0uwNftqop2wn0xauN6rMeoFzNhzLK3vBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbde0d892b6767ef1578553736ffac016c2dcbd60834fb8155fcef2d11808080","last_reissued_at":"2026-07-05T08:03:04.925186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:04.925186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Du, Dacheng Tao, Juhua Liu, Liang Ding, Qihuang Zhong","submitted_at":"2022-08-22T09:14:14Z","abstract_excerpt":"Prompt Transfer (PoT) is a recently-proposed approach to improve prompt-tuning, by initializing the target prompt with the existing prompt trained on similar source tasks. However, such a vanilla PoT approach usually achieves sub-optimal performance, as (i) the PoT is sensitive to the similarity of source-target pair and (ii) directly fine-tuning the prompt initialized with source prompt on target task might lead to forgetting of the useful general knowledge learned from source task. To tackle these issues, we propose a new metric to accurately predict the prompt transferability (regarding (i)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.10160","kind":"arxiv","version":2},"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/2208.10160/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":"2208.10160","created_at":"2026-07-05T08:03:04.925242+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.10160v2","created_at":"2026-07-05T08:03:04.925242+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.10160","created_at":"2026-07-05T08:03:04.925242+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PPA3CJLM5T6","created_at":"2026-07-05T08:03:04.925242+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PPA3CJLM5T66FLY","created_at":"2026-07-05T08:03:04.925242+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PPA3CJL","created_at":"2026-07-05T08:03:04.925242+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.01343","citing_title":"BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7PPA3CJLM5T66FLYKU3TN75MAF","json":"https://pith.science/pith/7PPA3CJLM5T66FLYKU3TN75MAF.json","graph_json":"https://pith.science/api/pith-number/7PPA3CJLM5T66FLYKU3TN75MAF/graph.json","events_json":"https://pith.science/api/pith-number/7PPA3CJLM5T66FLYKU3TN75MAF/events.json","paper":"https://pith.science/paper/7PPA3CJL"},"agent_actions":{"view_html":"https://pith.science/pith/7PPA3CJLM5T66FLYKU3TN75MAF","download_json":"https://pith.science/pith/7PPA3CJLM5T66FLYKU3TN75MAF.json","view_paper":"https://pith.science/paper/7PPA3CJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.10160&json=true","fetch_graph":"https://pith.science/api/pith-number/7PPA3CJLM5T66FLYKU3TN75MAF/graph.json","fetch_events":"https://pith.science/api/pith-number/7PPA3CJLM5T66FLYKU3TN75MAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PPA3CJLM5T66FLYKU3TN75MAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PPA3CJLM5T66FLYKU3TN75MAF/action/storage_attestation","attest_author":"https://pith.science/pith/7PPA3CJLM5T66FLYKU3TN75MAF/action/author_attestation","sign_citation":"https://pith.science/pith/7PPA3CJLM5T66FLYKU3TN75MAF/action/citation_signature","submit_replication":"https://pith.science/pith/7PPA3CJLM5T66FLYKU3TN75MAF/action/replication_record"}},"created_at":"2026-07-05T08:03:04.925242+00:00","updated_at":"2026-07-05T08:03:04.925242+00:00"}