{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:STGYJY6Q64JTY2P4YX2TAI6V5C","short_pith_number":"pith:STGYJY6Q","schema_version":"1.0","canonical_sha256":"94cd84e3d0f7133c69fcc5f53023d5e89f3bdcfc26ca711cedcc711688eb23dc","source":{"kind":"arxiv","id":"2210.02952","version":2},"attestation_state":"computed","paper":{"title":"Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boyang Li, Han Yu, Xu Guo","submitted_at":"2022-10-06T14:44:21Z","abstract_excerpt":"Prompt tuning, or the conditioning of a frozen pretrained language model (PLM) with soft prompts learned from data, has demonstrated impressive performance on a wide range of NLP tasks. However, prompt tuning requires a large training dataset to be effective and is outperformed by finetuning the entire PLM in data-scarce regimes. Previous work (Gu et al., 2022, Vu et al., 2022) proposed to transfer soft prompts pretrained on the source domain to the target domain. In this paper, we explore domain adaptation for prompt tuning, a problem setting where unlabeled data from the target domain are av"},"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":"2210.02952","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-06T14:44:21Z","cross_cats_sorted":[],"title_canon_sha256":"4e34ffec0e13c5907969fcce09dfe2ee200d8e0d259c418a068f3699c3d8b70a","abstract_canon_sha256":"4864ccfd1be5f24bbe748a52dd560d20cbec2d4d032a61f0b8228eb451bb2142"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:52.973470Z","signature_b64":"O0sSuvR2IFEXUur3P/Z6ccpHkNzDt02c6bNYcBzhELLCgaKbfkHs4v9hgex18o9EEGONOz303gwFJgPhDu4FBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94cd84e3d0f7133c69fcc5f53023d5e89f3bdcfc26ca711cedcc711688eb23dc","last_reissued_at":"2026-07-05T05:08:52.973043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:52.973043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boyang Li, Han Yu, Xu Guo","submitted_at":"2022-10-06T14:44:21Z","abstract_excerpt":"Prompt tuning, or the conditioning of a frozen pretrained language model (PLM) with soft prompts learned from data, has demonstrated impressive performance on a wide range of NLP tasks. However, prompt tuning requires a large training dataset to be effective and is outperformed by finetuning the entire PLM in data-scarce regimes. Previous work (Gu et al., 2022, Vu et al., 2022) proposed to transfer soft prompts pretrained on the source domain to the target domain. In this paper, we explore domain adaptation for prompt tuning, a problem setting where unlabeled data from the target domain are av"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02952","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/2210.02952/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":"2210.02952","created_at":"2026-07-05T05:08:52.973105+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.02952v2","created_at":"2026-07-05T05:08:52.973105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02952","created_at":"2026-07-05T05:08:52.973105+00:00"},{"alias_kind":"pith_short_12","alias_value":"STGYJY6Q64JT","created_at":"2026-07-05T05:08:52.973105+00:00"},{"alias_kind":"pith_short_16","alias_value":"STGYJY6Q64JTY2P4","created_at":"2026-07-05T05:08:52.973105+00:00"},{"alias_kind":"pith_short_8","alias_value":"STGYJY6Q","created_at":"2026-07-05T05:08:52.973105+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17615","citing_title":"Large language model as user daily behavior data generator: balancing population diversity and individual personality","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/STGYJY6Q64JTY2P4YX2TAI6V5C","json":"https://pith.science/pith/STGYJY6Q64JTY2P4YX2TAI6V5C.json","graph_json":"https://pith.science/api/pith-number/STGYJY6Q64JTY2P4YX2TAI6V5C/graph.json","events_json":"https://pith.science/api/pith-number/STGYJY6Q64JTY2P4YX2TAI6V5C/events.json","paper":"https://pith.science/paper/STGYJY6Q"},"agent_actions":{"view_html":"https://pith.science/pith/STGYJY6Q64JTY2P4YX2TAI6V5C","download_json":"https://pith.science/pith/STGYJY6Q64JTY2P4YX2TAI6V5C.json","view_paper":"https://pith.science/paper/STGYJY6Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.02952&json=true","fetch_graph":"https://pith.science/api/pith-number/STGYJY6Q64JTY2P4YX2TAI6V5C/graph.json","fetch_events":"https://pith.science/api/pith-number/STGYJY6Q64JTY2P4YX2TAI6V5C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STGYJY6Q64JTY2P4YX2TAI6V5C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STGYJY6Q64JTY2P4YX2TAI6V5C/action/storage_attestation","attest_author":"https://pith.science/pith/STGYJY6Q64JTY2P4YX2TAI6V5C/action/author_attestation","sign_citation":"https://pith.science/pith/STGYJY6Q64JTY2P4YX2TAI6V5C/action/citation_signature","submit_replication":"https://pith.science/pith/STGYJY6Q64JTY2P4YX2TAI6V5C/action/replication_record"}},"created_at":"2026-07-05T05:08:52.973105+00:00","updated_at":"2026-07-05T05:08:52.973105+00:00"}