{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:THXIK43R2LU2YHL2OF33EEQ4AG","short_pith_number":"pith:THXIK43R","schema_version":"1.0","canonical_sha256":"99ee857371d2e9ac1d7a7177b2121c01b9b28cc3a568550a5abc0e2d0710568d","source":{"kind":"arxiv","id":"2210.01253","version":2},"attestation_state":"computed","paper":{"title":"PLOT: Prompt Learning with Optimal Transport for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Guangyi Chen, Kun Zhang, Weiran Yao, Xiangchen Song, Xinyue Li, Yongming Rao","submitted_at":"2022-10-03T22:21:07Z","abstract_excerpt":"With the increasing attention to large vision-language models such as CLIP, there has been a significant amount of effort dedicated to building efficient prompts. Unlike conventional methods of only learning one single prompt, we propose to learn multiple comprehensive prompts to describe diverse characteristics of categories such as intrinsic attributes or extrinsic contexts. However, directly matching each prompt to the same visual feature is problematic, as it pushes the prompts to converge to one point. To solve this problem, we propose to apply optimal transport to match the vision and te"},"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":"2210.01253","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-03T22:21:07Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"87563f326b5414e6ad075473cd0081906e93715de86997f5514bbcb05684eb08","abstract_canon_sha256":"7e3442c1111f13b262c771fe69a012e8d151c2bc3d1b07625bca3b3d47e7e1da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:21.034449Z","signature_b64":"gEP3hdP/w51PaW00TcsZQqbsIcOlmxDB+nhXTe25iwXsGl70Rm5HmO4+3PQVuJgfByqlDliLGOXpqWwu1JJhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99ee857371d2e9ac1d7a7177b2121c01b9b28cc3a568550a5abc0e2d0710568d","last_reissued_at":"2026-07-05T05:40:21.033965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:21.033965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PLOT: Prompt Learning with Optimal Transport for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Guangyi Chen, Kun Zhang, Weiran Yao, Xiangchen Song, Xinyue Li, Yongming Rao","submitted_at":"2022-10-03T22:21:07Z","abstract_excerpt":"With the increasing attention to large vision-language models such as CLIP, there has been a significant amount of effort dedicated to building efficient prompts. Unlike conventional methods of only learning one single prompt, we propose to learn multiple comprehensive prompts to describe diverse characteristics of categories such as intrinsic attributes or extrinsic contexts. However, directly matching each prompt to the same visual feature is problematic, as it pushes the prompts to converge to one point. To solve this problem, we propose to apply optimal transport to match the vision and te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01253","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/2210.01253/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":"2210.01253","created_at":"2026-07-05T05:40:21.034022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.01253v2","created_at":"2026-07-05T05:40:21.034022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01253","created_at":"2026-07-05T05:40:21.034022+00:00"},{"alias_kind":"pith_short_12","alias_value":"THXIK43R2LU2","created_at":"2026-07-05T05:40:21.034022+00:00"},{"alias_kind":"pith_short_16","alias_value":"THXIK43R2LU2YHL2","created_at":"2026-07-05T05:40:21.034022+00:00"},{"alias_kind":"pith_short_8","alias_value":"THXIK43R","created_at":"2026-07-05T05:40:21.034022+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.18816","citing_title":"Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17577","citing_title":"TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2510.14543","citing_title":"Exploring Cross-Modal Flows for Few-Shot Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13835","citing_title":"Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05910","citing_title":"Plug-and-play Class-aware Knowledge Injection for Prompt Learning with Visual-Language Model","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04058","citing_title":"MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning","ref_index":129,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/THXIK43R2LU2YHL2OF33EEQ4AG","json":"https://pith.science/pith/THXIK43R2LU2YHL2OF33EEQ4AG.json","graph_json":"https://pith.science/api/pith-number/THXIK43R2LU2YHL2OF33EEQ4AG/graph.json","events_json":"https://pith.science/api/pith-number/THXIK43R2LU2YHL2OF33EEQ4AG/events.json","paper":"https://pith.science/paper/THXIK43R"},"agent_actions":{"view_html":"https://pith.science/pith/THXIK43R2LU2YHL2OF33EEQ4AG","download_json":"https://pith.science/pith/THXIK43R2LU2YHL2OF33EEQ4AG.json","view_paper":"https://pith.science/paper/THXIK43R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.01253&json=true","fetch_graph":"https://pith.science/api/pith-number/THXIK43R2LU2YHL2OF33EEQ4AG/graph.json","fetch_events":"https://pith.science/api/pith-number/THXIK43R2LU2YHL2OF33EEQ4AG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/THXIK43R2LU2YHL2OF33EEQ4AG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/THXIK43R2LU2YHL2OF33EEQ4AG/action/storage_attestation","attest_author":"https://pith.science/pith/THXIK43R2LU2YHL2OF33EEQ4AG/action/author_attestation","sign_citation":"https://pith.science/pith/THXIK43R2LU2YHL2OF33EEQ4AG/action/citation_signature","submit_replication":"https://pith.science/pith/THXIK43R2LU2YHL2OF33EEQ4AG/action/replication_record"}},"created_at":"2026-07-05T05:40:21.034022+00:00","updated_at":"2026-07-05T05:40:21.034022+00:00"}