{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7EDGGDV7ZF7MWPHRULMIFPMDHC","short_pith_number":"pith:7EDGGDV7","schema_version":"1.0","canonical_sha256":"f906630ebfc97ecb3cf1a2d882bd83389a4b26063b245ed2dabde1719af305e4","source":{"kind":"arxiv","id":"2402.04655","version":4},"attestation_state":"computed","paper":{"title":"Open-Vocabulary Calibration for Fine-tuned CLIP","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bob Zhang, Guoqing Wang, Hongxin Wei, Jindong Wang, Kaiyang Zhou, Shuoyuan Wang","submitted_at":"2024-02-07T08:42:48Z","abstract_excerpt":"Vision-language models (VLMs) have emerged as formidable tools, showing their strong capability in handling various open-vocabulary tasks in image recognition, text-driven visual content generation, and visual chatbots, to name a few. In recent years, considerable efforts and resources have been devoted to adaptation methods for improving downstream performance of VLMs, particularly on parameter-efficient fine-tuning methods like prompt learning. However, a crucial aspect that has been largely overlooked is the confidence calibration problem in fine-tuned VLMs, which could greatly reduce relia"},"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":"2402.04655","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T08:42:48Z","cross_cats_sorted":[],"title_canon_sha256":"97a24c593545837e838b840821f82912291dc09658837ff7f05f1f4fb66481a5","abstract_canon_sha256":"04335c94f8d5c95d7358a2feca93b6d43332d08ddaf87f8358b025da386b68ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:48.253393Z","signature_b64":"6mwAGD1R7WW7sPKoiWzXyUHEW3qJryqbkf0KqzZtPP1KU0qVqF/hVbIrtvxC6mE3yo3hL61lWYqpr1wUy4laBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f906630ebfc97ecb3cf1a2d882bd83389a4b26063b245ed2dabde1719af305e4","last_reissued_at":"2026-07-05T08:31:48.252896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:48.252896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-Vocabulary Calibration for Fine-tuned CLIP","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bob Zhang, Guoqing Wang, Hongxin Wei, Jindong Wang, Kaiyang Zhou, Shuoyuan Wang","submitted_at":"2024-02-07T08:42:48Z","abstract_excerpt":"Vision-language models (VLMs) have emerged as formidable tools, showing their strong capability in handling various open-vocabulary tasks in image recognition, text-driven visual content generation, and visual chatbots, to name a few. In recent years, considerable efforts and resources have been devoted to adaptation methods for improving downstream performance of VLMs, particularly on parameter-efficient fine-tuning methods like prompt learning. However, a crucial aspect that has been largely overlooked is the confidence calibration problem in fine-tuned VLMs, which could greatly reduce relia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04655","kind":"arxiv","version":4},"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/2402.04655/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":"2402.04655","created_at":"2026-07-05T08:31:48.252954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04655v4","created_at":"2026-07-05T08:31:48.252954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04655","created_at":"2026-07-05T08:31:48.252954+00:00"},{"alias_kind":"pith_short_12","alias_value":"7EDGGDV7ZF7M","created_at":"2026-07-05T08:31:48.252954+00:00"},{"alias_kind":"pith_short_16","alias_value":"7EDGGDV7ZF7MWPHR","created_at":"2026-07-05T08:31:48.252954+00:00"},{"alias_kind":"pith_short_8","alias_value":"7EDGGDV7","created_at":"2026-07-05T08:31:48.252954+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22819","citing_title":"Prompting without Panic: Attribute-aware, Zero-shot, Test-Time Calibration","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7EDGGDV7ZF7MWPHRULMIFPMDHC","json":"https://pith.science/pith/7EDGGDV7ZF7MWPHRULMIFPMDHC.json","graph_json":"https://pith.science/api/pith-number/7EDGGDV7ZF7MWPHRULMIFPMDHC/graph.json","events_json":"https://pith.science/api/pith-number/7EDGGDV7ZF7MWPHRULMIFPMDHC/events.json","paper":"https://pith.science/paper/7EDGGDV7"},"agent_actions":{"view_html":"https://pith.science/pith/7EDGGDV7ZF7MWPHRULMIFPMDHC","download_json":"https://pith.science/pith/7EDGGDV7ZF7MWPHRULMIFPMDHC.json","view_paper":"https://pith.science/paper/7EDGGDV7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04655&json=true","fetch_graph":"https://pith.science/api/pith-number/7EDGGDV7ZF7MWPHRULMIFPMDHC/graph.json","fetch_events":"https://pith.science/api/pith-number/7EDGGDV7ZF7MWPHRULMIFPMDHC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7EDGGDV7ZF7MWPHRULMIFPMDHC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7EDGGDV7ZF7MWPHRULMIFPMDHC/action/storage_attestation","attest_author":"https://pith.science/pith/7EDGGDV7ZF7MWPHRULMIFPMDHC/action/author_attestation","sign_citation":"https://pith.science/pith/7EDGGDV7ZF7MWPHRULMIFPMDHC/action/citation_signature","submit_replication":"https://pith.science/pith/7EDGGDV7ZF7MWPHRULMIFPMDHC/action/replication_record"}},"created_at":"2026-07-05T08:31:48.252954+00:00","updated_at":"2026-07-05T08:31:48.252954+00:00"}