{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZJKPPAPLJDL4O773IV7KQYHNHE","short_pith_number":"pith:ZJKPPAPL","schema_version":"1.0","canonical_sha256":"ca54f781eb48d7c77ffb457ea860ed3901e5e5dfdf220e0e709ec4134a406d19","source":{"kind":"arxiv","id":"2205.11166","version":1},"attestation_state":"computed","paper":{"title":"Prompt Tuning for Discriminative Pre-trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ao Zhang, Bowen Dong, Jianyong Wang, Leyu Lin, Maosong Sun, Ruobing Xie, Yuan Yao, Zhengyan Zhang, Zhiyuan Liu","submitted_at":"2022-05-23T10:11:50Z","abstract_excerpt":"Recent works have shown promising results of prompt tuning in stimulating pre-trained language models (PLMs) for natural language processing (NLP) tasks. However, to the best of our knowledge, existing works focus on prompt-tuning generative PLMs that are pre-trained to generate target tokens, such as BERT. It is still unknown whether and how discriminative PLMs, e.g., ELECTRA, can be effectively prompt-tuned. In this work, we present DPT, the first prompt tuning framework for discriminative PLMs, which reformulates NLP tasks into a discriminative language modeling problem. Comprehensive exper"},"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":"2205.11166","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-23T10:11:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"01dd6a1e6e44a62b5e4d215aea995326db8e907f33b1e34f0bbe533c0e4ce3c8","abstract_canon_sha256":"8300368db110c7c17f3ac26e3690d808b7429f4257ae18570f3526618034ba35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:27.976407Z","signature_b64":"8i2rd72zR1ZWmMD+IFQV5oJ2w3685G16AGiIKkVMxHCz+GMECjL0iTnYWcoQ7asVb1Y7qhZ3W7p4pqAIUE7vDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca54f781eb48d7c77ffb457ea860ed3901e5e5dfdf220e0e709ec4134a406d19","last_reissued_at":"2026-07-05T04:25:27.975982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:27.975982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt Tuning for Discriminative Pre-trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ao Zhang, Bowen Dong, Jianyong Wang, Leyu Lin, Maosong Sun, Ruobing Xie, Yuan Yao, Zhengyan Zhang, Zhiyuan Liu","submitted_at":"2022-05-23T10:11:50Z","abstract_excerpt":"Recent works have shown promising results of prompt tuning in stimulating pre-trained language models (PLMs) for natural language processing (NLP) tasks. However, to the best of our knowledge, existing works focus on prompt-tuning generative PLMs that are pre-trained to generate target tokens, such as BERT. It is still unknown whether and how discriminative PLMs, e.g., ELECTRA, can be effectively prompt-tuned. In this work, we present DPT, the first prompt tuning framework for discriminative PLMs, which reformulates NLP tasks into a discriminative language modeling problem. Comprehensive exper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11166","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/2205.11166/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":"2205.11166","created_at":"2026-07-05T04:25:27.976040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.11166v1","created_at":"2026-07-05T04:25:27.976040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11166","created_at":"2026-07-05T04:25:27.976040+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJKPPAPLJDL4","created_at":"2026-07-05T04:25:27.976040+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJKPPAPLJDL4O773","created_at":"2026-07-05T04:25:27.976040+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJKPPAPL","created_at":"2026-07-05T04:25:27.976040+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJKPPAPLJDL4O773IV7KQYHNHE","json":"https://pith.science/pith/ZJKPPAPLJDL4O773IV7KQYHNHE.json","graph_json":"https://pith.science/api/pith-number/ZJKPPAPLJDL4O773IV7KQYHNHE/graph.json","events_json":"https://pith.science/api/pith-number/ZJKPPAPLJDL4O773IV7KQYHNHE/events.json","paper":"https://pith.science/paper/ZJKPPAPL"},"agent_actions":{"view_html":"https://pith.science/pith/ZJKPPAPLJDL4O773IV7KQYHNHE","download_json":"https://pith.science/pith/ZJKPPAPLJDL4O773IV7KQYHNHE.json","view_paper":"https://pith.science/paper/ZJKPPAPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.11166&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJKPPAPLJDL4O773IV7KQYHNHE/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJKPPAPLJDL4O773IV7KQYHNHE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJKPPAPLJDL4O773IV7KQYHNHE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJKPPAPLJDL4O773IV7KQYHNHE/action/storage_attestation","attest_author":"https://pith.science/pith/ZJKPPAPLJDL4O773IV7KQYHNHE/action/author_attestation","sign_citation":"https://pith.science/pith/ZJKPPAPLJDL4O773IV7KQYHNHE/action/citation_signature","submit_replication":"https://pith.science/pith/ZJKPPAPLJDL4O773IV7KQYHNHE/action/replication_record"}},"created_at":"2026-07-05T04:25:27.976040+00:00","updated_at":"2026-07-05T04:25:27.976040+00:00"}