{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HQXDLRCUCAFZBX32DJSRL6T3UM","short_pith_number":"pith:HQXDLRCU","schema_version":"1.0","canonical_sha256":"3c2e35c454100b90df7a1a6515fa7ba324e3fa2fe45b4b049cc4b16f14f89a4e","source":{"kind":"arxiv","id":"2208.11503","version":1},"attestation_state":"computed","paper":{"title":"DPTDR: Deep Prompt Tuning for Dense Passage Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Ting Yao, Zhengyang Tang","submitted_at":"2022-08-24T12:55:00Z","abstract_excerpt":"Deep prompt tuning (DPT) has gained great success in most natural language processing~(NLP) tasks. However, it is not well-investigated in dense retrieval where fine-tuning~(FT) still dominates. When deploying multiple retrieval tasks using the same backbone model~(e.g., RoBERTa), FT-based methods are unfriendly in terms of deployment cost: each new retrieval model needs to repeatedly deploy the backbone model without reuse. To reduce the deployment cost in such a scenario, this work investigates applying DPT in dense retrieval. The challenge is that directly applying DPT in dense retrieval la"},"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":"2208.11503","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-08-24T12:55:00Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"eef6d1f6042c748eb859f4f7b861c789c2614d060706592f95a5688b4c2fac7a","abstract_canon_sha256":"c4ad90ac393d05602c49f4fc30410f5d11f2b358e838d7c5f20ecae8a3737ef9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:51:15.855465Z","signature_b64":"+VVkidxuHTB+Ulqvt15aXPeJfe9feQf5zWIAmU6lCBZyQxOspR76xrXRBJZURuFx7X7+eE9q3qhgO8LUd77wAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c2e35c454100b90df7a1a6515fa7ba324e3fa2fe45b4b049cc4b16f14f89a4e","last_reissued_at":"2026-07-05T04:51:15.855045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:51:15.855045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DPTDR: Deep Prompt Tuning for Dense Passage Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Ting Yao, Zhengyang Tang","submitted_at":"2022-08-24T12:55:00Z","abstract_excerpt":"Deep prompt tuning (DPT) has gained great success in most natural language processing~(NLP) tasks. However, it is not well-investigated in dense retrieval where fine-tuning~(FT) still dominates. When deploying multiple retrieval tasks using the same backbone model~(e.g., RoBERTa), FT-based methods are unfriendly in terms of deployment cost: each new retrieval model needs to repeatedly deploy the backbone model without reuse. To reduce the deployment cost in such a scenario, this work investigates applying DPT in dense retrieval. The challenge is that directly applying DPT in dense retrieval la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11503","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/2208.11503/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":"2208.11503","created_at":"2026-07-05T04:51:15.855110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.11503v1","created_at":"2026-07-05T04:51:15.855110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11503","created_at":"2026-07-05T04:51:15.855110+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQXDLRCUCAFZ","created_at":"2026-07-05T04:51:15.855110+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQXDLRCUCAFZBX32","created_at":"2026-07-05T04:51:15.855110+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQXDLRCU","created_at":"2026-07-05T04:51:15.855110+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/HQXDLRCUCAFZBX32DJSRL6T3UM","json":"https://pith.science/pith/HQXDLRCUCAFZBX32DJSRL6T3UM.json","graph_json":"https://pith.science/api/pith-number/HQXDLRCUCAFZBX32DJSRL6T3UM/graph.json","events_json":"https://pith.science/api/pith-number/HQXDLRCUCAFZBX32DJSRL6T3UM/events.json","paper":"https://pith.science/paper/HQXDLRCU"},"agent_actions":{"view_html":"https://pith.science/pith/HQXDLRCUCAFZBX32DJSRL6T3UM","download_json":"https://pith.science/pith/HQXDLRCUCAFZBX32DJSRL6T3UM.json","view_paper":"https://pith.science/paper/HQXDLRCU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.11503&json=true","fetch_graph":"https://pith.science/api/pith-number/HQXDLRCUCAFZBX32DJSRL6T3UM/graph.json","fetch_events":"https://pith.science/api/pith-number/HQXDLRCUCAFZBX32DJSRL6T3UM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQXDLRCUCAFZBX32DJSRL6T3UM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQXDLRCUCAFZBX32DJSRL6T3UM/action/storage_attestation","attest_author":"https://pith.science/pith/HQXDLRCUCAFZBX32DJSRL6T3UM/action/author_attestation","sign_citation":"https://pith.science/pith/HQXDLRCUCAFZBX32DJSRL6T3UM/action/citation_signature","submit_replication":"https://pith.science/pith/HQXDLRCUCAFZBX32DJSRL6T3UM/action/replication_record"}},"created_at":"2026-07-05T04:51:15.855110+00:00","updated_at":"2026-07-05T04:51:15.855110+00:00"}