{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2VLUCZADED3DPSXCTNLVU5ZBDR","short_pith_number":"pith:2VLUCZAD","schema_version":"1.0","canonical_sha256":"d55741640320f637cae29b575a77211c40ffd09628d9d1dbb9e86a91cc220b41","source":{"kind":"arxiv","id":"2305.03518","version":2},"attestation_state":"computed","paper":{"title":"Black-box Prompt Tuning with Subspace Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Peng Li, Yang Liu, Yuanhang Zheng, Zhixing Tan","submitted_at":"2023-05-04T01:04:25Z","abstract_excerpt":"Black-box prompt tuning employs derivative-free optimization algorithms to learn prompts within low-dimensional subspaces rather than back-propagating through the network of Large Language Models (LLMs). Recent studies reveal that black-box prompt tuning lacks versatility across tasks and LLMs, which we believe is related to the suboptimal choice of subspaces. In this paper, we introduce Black-box prompt tuning with Subspace Learning (BSL) to enhance the versatility of black-box prompt tuning. Based on the assumption that nearly optimal prompts for similar tasks reside in a common subspace, we"},"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":"2305.03518","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-04T01:04:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"56ce82a12d570875470ed133798e971b37f39f3d2e9e254ac78151a1386208a4","abstract_canon_sha256":"89ab2a3124f44feede20a290297b841dae0856e6b6744a58150ec6564d4fac4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:29.432174Z","signature_b64":"nw6RYUb/LTXcZsvvOxVKLR23UxCqRken+jFDYMoQCaVowDpzt8k6ZEe4d4nisZ0w/ehNFyZHpUTviIH1gQH/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d55741640320f637cae29b575a77211c40ffd09628d9d1dbb9e86a91cc220b41","last_reissued_at":"2026-07-05T08:32:29.431689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:29.431689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Black-box Prompt Tuning with Subspace Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Peng Li, Yang Liu, Yuanhang Zheng, Zhixing Tan","submitted_at":"2023-05-04T01:04:25Z","abstract_excerpt":"Black-box prompt tuning employs derivative-free optimization algorithms to learn prompts within low-dimensional subspaces rather than back-propagating through the network of Large Language Models (LLMs). Recent studies reveal that black-box prompt tuning lacks versatility across tasks and LLMs, which we believe is related to the suboptimal choice of subspaces. In this paper, we introduce Black-box prompt tuning with Subspace Learning (BSL) to enhance the versatility of black-box prompt tuning. Based on the assumption that nearly optimal prompts for similar tasks reside in a common subspace, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03518","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/2305.03518/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":"2305.03518","created_at":"2026-07-05T08:32:29.431747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.03518v2","created_at":"2026-07-05T08:32:29.431747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03518","created_at":"2026-07-05T08:32:29.431747+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VLUCZADED3D","created_at":"2026-07-05T08:32:29.431747+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VLUCZADED3DPSXC","created_at":"2026-07-05T08:32:29.431747+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VLUCZAD","created_at":"2026-07-05T08:32:29.431747+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/2VLUCZADED3DPSXCTNLVU5ZBDR","json":"https://pith.science/pith/2VLUCZADED3DPSXCTNLVU5ZBDR.json","graph_json":"https://pith.science/api/pith-number/2VLUCZADED3DPSXCTNLVU5ZBDR/graph.json","events_json":"https://pith.science/api/pith-number/2VLUCZADED3DPSXCTNLVU5ZBDR/events.json","paper":"https://pith.science/paper/2VLUCZAD"},"agent_actions":{"view_html":"https://pith.science/pith/2VLUCZADED3DPSXCTNLVU5ZBDR","download_json":"https://pith.science/pith/2VLUCZADED3DPSXCTNLVU5ZBDR.json","view_paper":"https://pith.science/paper/2VLUCZAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.03518&json=true","fetch_graph":"https://pith.science/api/pith-number/2VLUCZADED3DPSXCTNLVU5ZBDR/graph.json","fetch_events":"https://pith.science/api/pith-number/2VLUCZADED3DPSXCTNLVU5ZBDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VLUCZADED3DPSXCTNLVU5ZBDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VLUCZADED3DPSXCTNLVU5ZBDR/action/storage_attestation","attest_author":"https://pith.science/pith/2VLUCZADED3DPSXCTNLVU5ZBDR/action/author_attestation","sign_citation":"https://pith.science/pith/2VLUCZADED3DPSXCTNLVU5ZBDR/action/citation_signature","submit_replication":"https://pith.science/pith/2VLUCZADED3DPSXCTNLVU5ZBDR/action/replication_record"}},"created_at":"2026-07-05T08:32:29.431747+00:00","updated_at":"2026-07-05T08:32:29.431747+00:00"}