{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:S3J247GBR2SL62IOXLVPXXIQWX","short_pith_number":"pith:S3J247GB","schema_version":"1.0","canonical_sha256":"96d3ae7cc18ea4bf690ebaeafbdd10b5c1b94ba2694bc75e7168b814a8a3ce70","source":{"kind":"arxiv","id":"2212.10929","version":1},"attestation_state":"computed","paper":{"title":"SPT: Semi-Parametric Prompt Tuning for Multitask Prompted Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aston Zhang, M Saiful Bari, Mu Li, Shafiq Joty, Shuai Zheng, Xingjian Shi, Yi Zhu","submitted_at":"2022-12-21T11:18:09Z","abstract_excerpt":"Pre-trained large language models can efficiently interpolate human-written prompts in a natural way. Multitask prompted learning can help generalization through a diverse set of tasks at once, thus enhancing the potential for more effective downstream fine-tuning. To perform efficient multitask-inference in the same batch, parameter-efficient fine-tuning methods such as prompt tuning have been proposed. However, the existing prompt tuning methods may lack generalization. We propose SPT, a semi-parametric prompt tuning method for multitask prompted learning. The novel component of SPT is a mem"},"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":"2212.10929","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-21T11:18:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"25ba60e49f5605d1305bce9a116bee76369682f24c99d031698b56377bc0ee27","abstract_canon_sha256":"df7f2cbdaa4256601b27a3a7b0275d8cf7175bb4b8434e570a87d8ebc8919e62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:24.527939Z","signature_b64":"wG5UD47U4btnL3CZXO7yc+hn2o+zU6RaujPfSNtqq7I8gdZy1MU1v+R0hhPVefOHAfpuvJOsp7kjSZD315SqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96d3ae7cc18ea4bf690ebaeafbdd10b5c1b94ba2694bc75e7168b814a8a3ce70","last_reissued_at":"2026-07-05T05:27:24.527501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:24.527501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPT: Semi-Parametric Prompt Tuning for Multitask Prompted Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aston Zhang, M Saiful Bari, Mu Li, Shafiq Joty, Shuai Zheng, Xingjian Shi, Yi Zhu","submitted_at":"2022-12-21T11:18:09Z","abstract_excerpt":"Pre-trained large language models can efficiently interpolate human-written prompts in a natural way. Multitask prompted learning can help generalization through a diverse set of tasks at once, thus enhancing the potential for more effective downstream fine-tuning. To perform efficient multitask-inference in the same batch, parameter-efficient fine-tuning methods such as prompt tuning have been proposed. However, the existing prompt tuning methods may lack generalization. We propose SPT, a semi-parametric prompt tuning method for multitask prompted learning. The novel component of SPT is a mem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10929","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/2212.10929/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":"2212.10929","created_at":"2026-07-05T05:27:24.527559+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10929v1","created_at":"2026-07-05T05:27:24.527559+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10929","created_at":"2026-07-05T05:27:24.527559+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3J247GBR2SL","created_at":"2026-07-05T05:27:24.527559+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3J247GBR2SL62IO","created_at":"2026-07-05T05:27:24.527559+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3J247GB","created_at":"2026-07-05T05:27:24.527559+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/S3J247GBR2SL62IOXLVPXXIQWX","json":"https://pith.science/pith/S3J247GBR2SL62IOXLVPXXIQWX.json","graph_json":"https://pith.science/api/pith-number/S3J247GBR2SL62IOXLVPXXIQWX/graph.json","events_json":"https://pith.science/api/pith-number/S3J247GBR2SL62IOXLVPXXIQWX/events.json","paper":"https://pith.science/paper/S3J247GB"},"agent_actions":{"view_html":"https://pith.science/pith/S3J247GBR2SL62IOXLVPXXIQWX","download_json":"https://pith.science/pith/S3J247GBR2SL62IOXLVPXXIQWX.json","view_paper":"https://pith.science/paper/S3J247GB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10929&json=true","fetch_graph":"https://pith.science/api/pith-number/S3J247GBR2SL62IOXLVPXXIQWX/graph.json","fetch_events":"https://pith.science/api/pith-number/S3J247GBR2SL62IOXLVPXXIQWX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3J247GBR2SL62IOXLVPXXIQWX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3J247GBR2SL62IOXLVPXXIQWX/action/storage_attestation","attest_author":"https://pith.science/pith/S3J247GBR2SL62IOXLVPXXIQWX/action/author_attestation","sign_citation":"https://pith.science/pith/S3J247GBR2SL62IOXLVPXXIQWX/action/citation_signature","submit_replication":"https://pith.science/pith/S3J247GBR2SL62IOXLVPXXIQWX/action/replication_record"}},"created_at":"2026-07-05T05:27:24.527559+00:00","updated_at":"2026-07-05T05:27:24.527559+00:00"}