{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IKW6633J6EHB7FYRWS2X2XSZXQ","short_pith_number":"pith:IKW6633J","schema_version":"1.0","canonical_sha256":"42adef6f69f10e1f9711b4b57d5e59bc0a0bed9e54a46ce304e1ae62c9508aa1","source":{"kind":"arxiv","id":"2205.11024","version":2},"attestation_state":"computed","paper":{"title":"Vector-Quantized Input-Contextualized Soft Prompts for Natural Language Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amrita Saha, Rishabh Bhardwaj, Soujanya Poria, Steven C.H. Hoi","submitted_at":"2022-05-23T03:51:27Z","abstract_excerpt":"Prompt Tuning has been largely successful as a parameter-efficient method of conditioning large-scale pre-trained language models to perform downstream tasks. Thus far, soft prompt tuning learns a fixed set of task-specific continuous vectors, i.e., soft tokens that remain static across the task samples. A fixed prompt, however, may not generalize well to the diverse kinds of inputs the task comprises. In order to address this, we propose Vector-quantized Input-contextualized Prompts (VIP) as an extension to the soft prompt tuning framework. VIP particularly focuses on two aspects -- contextua"},"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":"2205.11024","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-23T03:51:27Z","cross_cats_sorted":[],"title_canon_sha256":"ded2ae96ea1d1bd67ca8b791790b39af287cb0299c3fcb007b09913c35a607c3","abstract_canon_sha256":"d3d3fce599403a4659695385e1cd323b5b92a4ae0ddb5a409e6a258bf31cbb39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:18.282598Z","signature_b64":"n33BurW+c7CXX2HRXqe/p7zSzeJ5TXEyD4mYhlUDdHy56jDFBJ+ihBDHs8hMwg2CA0De8L8cBFd+d46r/5HsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42adef6f69f10e1f9711b4b57d5e59bc0a0bed9e54a46ce304e1ae62c9508aa1","last_reissued_at":"2026-07-05T05:09:18.282265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:18.282265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vector-Quantized Input-Contextualized Soft Prompts for Natural Language Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amrita Saha, Rishabh Bhardwaj, Soujanya Poria, Steven C.H. Hoi","submitted_at":"2022-05-23T03:51:27Z","abstract_excerpt":"Prompt Tuning has been largely successful as a parameter-efficient method of conditioning large-scale pre-trained language models to perform downstream tasks. Thus far, soft prompt tuning learns a fixed set of task-specific continuous vectors, i.e., soft tokens that remain static across the task samples. A fixed prompt, however, may not generalize well to the diverse kinds of inputs the task comprises. In order to address this, we propose Vector-quantized Input-contextualized Prompts (VIP) as an extension to the soft prompt tuning framework. VIP particularly focuses on two aspects -- contextua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11024","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/2205.11024/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":"2205.11024","created_at":"2026-07-05T05:09:18.282322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.11024v2","created_at":"2026-07-05T05:09:18.282322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11024","created_at":"2026-07-05T05:09:18.282322+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKW6633J6EHB","created_at":"2026-07-05T05:09:18.282322+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKW6633J6EHB7FYR","created_at":"2026-07-05T05:09:18.282322+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKW6633J","created_at":"2026-07-05T05:09:18.282322+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/IKW6633J6EHB7FYRWS2X2XSZXQ","json":"https://pith.science/pith/IKW6633J6EHB7FYRWS2X2XSZXQ.json","graph_json":"https://pith.science/api/pith-number/IKW6633J6EHB7FYRWS2X2XSZXQ/graph.json","events_json":"https://pith.science/api/pith-number/IKW6633J6EHB7FYRWS2X2XSZXQ/events.json","paper":"https://pith.science/paper/IKW6633J"},"agent_actions":{"view_html":"https://pith.science/pith/IKW6633J6EHB7FYRWS2X2XSZXQ","download_json":"https://pith.science/pith/IKW6633J6EHB7FYRWS2X2XSZXQ.json","view_paper":"https://pith.science/paper/IKW6633J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.11024&json=true","fetch_graph":"https://pith.science/api/pith-number/IKW6633J6EHB7FYRWS2X2XSZXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/IKW6633J6EHB7FYRWS2X2XSZXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKW6633J6EHB7FYRWS2X2XSZXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKW6633J6EHB7FYRWS2X2XSZXQ/action/storage_attestation","attest_author":"https://pith.science/pith/IKW6633J6EHB7FYRWS2X2XSZXQ/action/author_attestation","sign_citation":"https://pith.science/pith/IKW6633J6EHB7FYRWS2X2XSZXQ/action/citation_signature","submit_replication":"https://pith.science/pith/IKW6633J6EHB7FYRWS2X2XSZXQ/action/replication_record"}},"created_at":"2026-07-05T05:09:18.282322+00:00","updated_at":"2026-07-05T05:09:18.282322+00:00"}