{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YNIFR5B6QYVSO4WJT4NRGBFASZ","short_pith_number":"pith:YNIFR5B6","schema_version":"1.0","canonical_sha256":"c35058f43e862b2772c99f1b1304a0965e4011e1f88a3c447b38f771a8c5bba5","source":{"kind":"arxiv","id":"2209.14169","version":2},"attestation_state":"computed","paper":{"title":"CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bin Cui, Longtian Qiu, Renrui Zhang, Xianzheng Ma, Xuming He, Xupeng Miao, Ziyu Guo","submitted_at":"2022-09-28T15:22:11Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has been shown to learn visual representations with great transferability, which achieves promising accuracy for zero-shot classification. To further improve its downstream performance, existing works propose additional learnable modules upon CLIP and fine-tune them by few-shot training sets. However, the resulting extra training cost and data requirement severely hinder the efficiency for model deployment and knowledge transfer. In this paper, we introduce a free-lunch enhancement method, CALIP, to boost CLIP's zero-shot performance via a paramet"},"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":"2209.14169","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-28T15:22:11Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"3de717611718127d5fa4ffd6c73dea4ba5e27d9e0aeee356780cf77b0857f0da","abstract_canon_sha256":"8c99a594495871e5c1fe1b5f177676fa345c4ccd2b53a08a8b76b6001ef1e2b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:09.462527Z","signature_b64":"DJ/Tm6jdUhWf/mGg95NYl4XNrbdrJaLeQhZjLzsu1+nR7tDjqNdpmtiUB+AVSBIXRsDTuzo5rTk+8UFcIYOPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c35058f43e862b2772c99f1b1304a0965e4011e1f88a3c447b38f771a8c5bba5","last_reissued_at":"2026-07-05T05:26:09.462030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:09.462030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bin Cui, Longtian Qiu, Renrui Zhang, Xianzheng Ma, Xuming He, Xupeng Miao, Ziyu Guo","submitted_at":"2022-09-28T15:22:11Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has been shown to learn visual representations with great transferability, which achieves promising accuracy for zero-shot classification. To further improve its downstream performance, existing works propose additional learnable modules upon CLIP and fine-tune them by few-shot training sets. However, the resulting extra training cost and data requirement severely hinder the efficiency for model deployment and knowledge transfer. In this paper, we introduce a free-lunch enhancement method, CALIP, to boost CLIP's zero-shot performance via a paramet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14169","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/2209.14169/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":"2209.14169","created_at":"2026-07-05T05:26:09.462093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.14169v2","created_at":"2026-07-05T05:26:09.462093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14169","created_at":"2026-07-05T05:26:09.462093+00:00"},{"alias_kind":"pith_short_12","alias_value":"YNIFR5B6QYVS","created_at":"2026-07-05T05:26:09.462093+00:00"},{"alias_kind":"pith_short_16","alias_value":"YNIFR5B6QYVSO4WJ","created_at":"2026-07-05T05:26:09.462093+00:00"},{"alias_kind":"pith_short_8","alias_value":"YNIFR5B6","created_at":"2026-07-05T05:26:09.462093+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.21122","citing_title":"NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09921","citing_title":"WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2303.16199","citing_title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","ref_index":188,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YNIFR5B6QYVSO4WJT4NRGBFASZ","json":"https://pith.science/pith/YNIFR5B6QYVSO4WJT4NRGBFASZ.json","graph_json":"https://pith.science/api/pith-number/YNIFR5B6QYVSO4WJT4NRGBFASZ/graph.json","events_json":"https://pith.science/api/pith-number/YNIFR5B6QYVSO4WJT4NRGBFASZ/events.json","paper":"https://pith.science/paper/YNIFR5B6"},"agent_actions":{"view_html":"https://pith.science/pith/YNIFR5B6QYVSO4WJT4NRGBFASZ","download_json":"https://pith.science/pith/YNIFR5B6QYVSO4WJT4NRGBFASZ.json","view_paper":"https://pith.science/paper/YNIFR5B6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.14169&json=true","fetch_graph":"https://pith.science/api/pith-number/YNIFR5B6QYVSO4WJT4NRGBFASZ/graph.json","fetch_events":"https://pith.science/api/pith-number/YNIFR5B6QYVSO4WJT4NRGBFASZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YNIFR5B6QYVSO4WJT4NRGBFASZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YNIFR5B6QYVSO4WJT4NRGBFASZ/action/storage_attestation","attest_author":"https://pith.science/pith/YNIFR5B6QYVSO4WJT4NRGBFASZ/action/author_attestation","sign_citation":"https://pith.science/pith/YNIFR5B6QYVSO4WJT4NRGBFASZ/action/citation_signature","submit_replication":"https://pith.science/pith/YNIFR5B6QYVSO4WJT4NRGBFASZ/action/replication_record"}},"created_at":"2026-07-05T05:26:09.462093+00:00","updated_at":"2026-07-05T05:26:09.462093+00:00"}