{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LRLZB33MFJ5BSUQW2U34D7EBRD","short_pith_number":"pith:LRLZB33M","schema_version":"1.0","canonical_sha256":"5c5790ef6c2a7a195216d537c1fc8188ec41d17c83685436ec70cd58c11df1ea","source":{"kind":"arxiv","id":"2307.00910","version":2},"attestation_state":"computed","paper":{"title":"CoPL: Contextual Prompt Learning for Vision-Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Balaji Vasan Srinivasan, K J Joseph, Koustava Goswami, Prateksha Udhayanan, Srikrishna Karanam","submitted_at":"2023-07-03T10:14:33Z","abstract_excerpt":"Recent advances in multimodal learning has resulted in powerful vision-language models, whose representations are generalizable across a variety of downstream tasks. Recently, their generalization ability has been further extended by incorporating trainable prompts, borrowed from the natural language processing literature. While such prompt learning techniques have shown impressive results, we identify that these prompts are trained based on global image features which limits itself in two aspects: First, by using global features, these prompts could be focusing less on the discriminative fore"},"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":"2307.00910","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-03T10:14:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3b4cc051821ffe955a3b1a850a1c703a30644ebfd276e5f4d9b823926a57c73e","abstract_canon_sha256":"34ef8b5d44bd35bfbd08f97dfd55d0562c7127a86e14601e08ab5d34e10aca00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:04.066835Z","signature_b64":"+bYoyZhUpvou38GiIxX78Ms2NS74fydUEQo/IJSF4aLTZlO2lszebYw92Y4YXkgstz+xNAg5WMIffjBKpVqVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c5790ef6c2a7a195216d537c1fc8188ec41d17c83685436ec70cd58c11df1ea","last_reissued_at":"2026-07-05T07:23:04.066301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:04.066301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoPL: Contextual Prompt Learning for Vision-Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Balaji Vasan Srinivasan, K J Joseph, Koustava Goswami, Prateksha Udhayanan, Srikrishna Karanam","submitted_at":"2023-07-03T10:14:33Z","abstract_excerpt":"Recent advances in multimodal learning has resulted in powerful vision-language models, whose representations are generalizable across a variety of downstream tasks. Recently, their generalization ability has been further extended by incorporating trainable prompts, borrowed from the natural language processing literature. While such prompt learning techniques have shown impressive results, we identify that these prompts are trained based on global image features which limits itself in two aspects: First, by using global features, these prompts could be focusing less on the discriminative fore"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00910","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/2307.00910/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":"2307.00910","created_at":"2026-07-05T07:23:04.066373+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.00910v2","created_at":"2026-07-05T07:23:04.066373+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00910","created_at":"2026-07-05T07:23:04.066373+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRLZB33MFJ5B","created_at":"2026-07-05T07:23:04.066373+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRLZB33MFJ5BSUQW","created_at":"2026-07-05T07:23:04.066373+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRLZB33M","created_at":"2026-07-05T07:23:04.066373+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/LRLZB33MFJ5BSUQW2U34D7EBRD","json":"https://pith.science/pith/LRLZB33MFJ5BSUQW2U34D7EBRD.json","graph_json":"https://pith.science/api/pith-number/LRLZB33MFJ5BSUQW2U34D7EBRD/graph.json","events_json":"https://pith.science/api/pith-number/LRLZB33MFJ5BSUQW2U34D7EBRD/events.json","paper":"https://pith.science/paper/LRLZB33M"},"agent_actions":{"view_html":"https://pith.science/pith/LRLZB33MFJ5BSUQW2U34D7EBRD","download_json":"https://pith.science/pith/LRLZB33MFJ5BSUQW2U34D7EBRD.json","view_paper":"https://pith.science/paper/LRLZB33M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.00910&json=true","fetch_graph":"https://pith.science/api/pith-number/LRLZB33MFJ5BSUQW2U34D7EBRD/graph.json","fetch_events":"https://pith.science/api/pith-number/LRLZB33MFJ5BSUQW2U34D7EBRD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRLZB33MFJ5BSUQW2U34D7EBRD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRLZB33MFJ5BSUQW2U34D7EBRD/action/storage_attestation","attest_author":"https://pith.science/pith/LRLZB33MFJ5BSUQW2U34D7EBRD/action/author_attestation","sign_citation":"https://pith.science/pith/LRLZB33MFJ5BSUQW2U34D7EBRD/action/citation_signature","submit_replication":"https://pith.science/pith/LRLZB33MFJ5BSUQW2U34D7EBRD/action/replication_record"}},"created_at":"2026-07-05T07:23:04.066373+00:00","updated_at":"2026-07-05T07:23:04.066373+00:00"}