{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:276XKXCO3IXGLVC7CIDS64DOKR","short_pith_number":"pith:276XKXCO","schema_version":"1.0","canonical_sha256":"d7fd755c4eda2e65d45f12072f706e54453aea929a41de177539fc36f85d8ff7","source":{"kind":"arxiv","id":"2405.11464","version":3},"attestation_state":"computed","paper":{"title":"Efficient Prompt Tuning by Multi-Space Projection and Prompt Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Enneng Yang, Guibing Guo, Jianzhe Zhao, Pengxiang Lan, Xingwei Wang, Yuting Liu","submitted_at":"2024-05-19T06:43:12Z","abstract_excerpt":"Prompt tuning is a promising method to fine-tune a pre-trained language model without retraining its large-scale parameters. Instead, it attaches a soft prompt to the input text, whereby downstream tasks can be well adapted by merely learning the embeddings of prompt tokens. Nevertheless, existing methods still suffer from two challenges: (i) they are hard to balance accuracy and efficiency. A longer (shorter) soft prompt generally leads to a better(worse) accuracy but at the cost of more (less) training time. (ii)The performance may not be consistent when adapting to different downstream task"},"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":"2405.11464","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-19T06:43:12Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"64dd2905a556be50fbfcac200088307f9972c6eb66fb179ad5741b4f9d7bc770","abstract_canon_sha256":"955b6d8a9afa6bf843e674fa9776ce076731d33524ad31c6441f1c3d66c3f241"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:30.270617Z","signature_b64":"PIkOt8g5kr2y3FPHKR+5XE+8XHUChg93SMcjF078pajYIbeztFoJxXSlpSFb7aZ0ecz6S37R3YBCJj79DoT5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7fd755c4eda2e65d45f12072f706e54453aea929a41de177539fc36f85d8ff7","last_reissued_at":"2026-07-05T09:47:30.270137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:30.270137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Prompt Tuning by Multi-Space Projection and Prompt Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Enneng Yang, Guibing Guo, Jianzhe Zhao, Pengxiang Lan, Xingwei Wang, Yuting Liu","submitted_at":"2024-05-19T06:43:12Z","abstract_excerpt":"Prompt tuning is a promising method to fine-tune a pre-trained language model without retraining its large-scale parameters. Instead, it attaches a soft prompt to the input text, whereby downstream tasks can be well adapted by merely learning the embeddings of prompt tokens. Nevertheless, existing methods still suffer from two challenges: (i) they are hard to balance accuracy and efficiency. A longer (shorter) soft prompt generally leads to a better(worse) accuracy but at the cost of more (less) training time. (ii)The performance may not be consistent when adapting to different downstream task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11464","kind":"arxiv","version":3},"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/2405.11464/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":"2405.11464","created_at":"2026-07-05T09:47:30.270197+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11464v3","created_at":"2026-07-05T09:47:30.270197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11464","created_at":"2026-07-05T09:47:30.270197+00:00"},{"alias_kind":"pith_short_12","alias_value":"276XKXCO3IXG","created_at":"2026-07-05T09:47:30.270197+00:00"},{"alias_kind":"pith_short_16","alias_value":"276XKXCO3IXGLVC7","created_at":"2026-07-05T09:47:30.270197+00:00"},{"alias_kind":"pith_short_8","alias_value":"276XKXCO","created_at":"2026-07-05T09:47:30.270197+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/276XKXCO3IXGLVC7CIDS64DOKR","json":"https://pith.science/pith/276XKXCO3IXGLVC7CIDS64DOKR.json","graph_json":"https://pith.science/api/pith-number/276XKXCO3IXGLVC7CIDS64DOKR/graph.json","events_json":"https://pith.science/api/pith-number/276XKXCO3IXGLVC7CIDS64DOKR/events.json","paper":"https://pith.science/paper/276XKXCO"},"agent_actions":{"view_html":"https://pith.science/pith/276XKXCO3IXGLVC7CIDS64DOKR","download_json":"https://pith.science/pith/276XKXCO3IXGLVC7CIDS64DOKR.json","view_paper":"https://pith.science/paper/276XKXCO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11464&json=true","fetch_graph":"https://pith.science/api/pith-number/276XKXCO3IXGLVC7CIDS64DOKR/graph.json","fetch_events":"https://pith.science/api/pith-number/276XKXCO3IXGLVC7CIDS64DOKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/276XKXCO3IXGLVC7CIDS64DOKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/276XKXCO3IXGLVC7CIDS64DOKR/action/storage_attestation","attest_author":"https://pith.science/pith/276XKXCO3IXGLVC7CIDS64DOKR/action/author_attestation","sign_citation":"https://pith.science/pith/276XKXCO3IXGLVC7CIDS64DOKR/action/citation_signature","submit_replication":"https://pith.science/pith/276XKXCO3IXGLVC7CIDS64DOKR/action/replication_record"}},"created_at":"2026-07-05T09:47:30.270197+00:00","updated_at":"2026-07-05T09:47:30.270197+00:00"}