{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EGE54Z5L5U2YJYBWC4NNAJPMWX","short_pith_number":"pith:EGE54Z5L","schema_version":"1.0","canonical_sha256":"2189de67abed3584e036171ad025ecb5c49ead030cc82e7f3eb1b09c37292e25","source":{"kind":"arxiv","id":"2311.17091","version":2},"attestation_state":"computed","paper":{"title":"Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiawang Bai, Xinchao Wang, Xin Li, Zeyu Xiao, Zhihe Lu","submitted_at":"2023-11-28T05:17:25Z","abstract_excerpt":"Fine-tuning pre-trained vision-language models (VLMs), e.g., CLIP, for the open-world generalization has gained increasing popularity due to its practical value. However, performance advancements are limited when relying solely on intricate algorithmic designs for a single model, even one exhibiting strong performance, e.g., CLIP-ViT-B/16. This paper, for the first time, explores the collaborative potential of leveraging much weaker VLMs to enhance the generalization of a robust single model. The affirmative findings motivate us to address the generalization problem from a novel perspective, i"},"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":"2311.17091","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T05:17:25Z","cross_cats_sorted":[],"title_canon_sha256":"d8136098482f51bb6ccdb46819763c0e39000ca45f9b7b0a3398269922f1095b","abstract_canon_sha256":"a0680a881283e397dbfcc5208e8a4443ebd93d166a3f1f017180687d0d4234f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:15.970443Z","signature_b64":"4DuWp/+/Xt4N3tQakairoDyVKGRY1tS4qoYNlrTTwEBIKk8SW+CNkNR2kJYVX1Ms/Dy83qrIJmczHXCcmT1nDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2189de67abed3584e036171ad025ecb5c49ead030cc82e7f3eb1b09c37292e25","last_reissued_at":"2026-07-05T08:26:15.969965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:15.969965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiawang Bai, Xinchao Wang, Xin Li, Zeyu Xiao, Zhihe Lu","submitted_at":"2023-11-28T05:17:25Z","abstract_excerpt":"Fine-tuning pre-trained vision-language models (VLMs), e.g., CLIP, for the open-world generalization has gained increasing popularity due to its practical value. However, performance advancements are limited when relying solely on intricate algorithmic designs for a single model, even one exhibiting strong performance, e.g., CLIP-ViT-B/16. This paper, for the first time, explores the collaborative potential of leveraging much weaker VLMs to enhance the generalization of a robust single model. The affirmative findings motivate us to address the generalization problem from a novel perspective, i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17091","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/2311.17091/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":"2311.17091","created_at":"2026-07-05T08:26:15.970021+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17091v2","created_at":"2026-07-05T08:26:15.970021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17091","created_at":"2026-07-05T08:26:15.970021+00:00"},{"alias_kind":"pith_short_12","alias_value":"EGE54Z5L5U2Y","created_at":"2026-07-05T08:26:15.970021+00:00"},{"alias_kind":"pith_short_16","alias_value":"EGE54Z5L5U2YJYBW","created_at":"2026-07-05T08:26:15.970021+00:00"},{"alias_kind":"pith_short_8","alias_value":"EGE54Z5L","created_at":"2026-07-05T08:26:15.970021+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26421","citing_title":"HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EGE54Z5L5U2YJYBWC4NNAJPMWX","json":"https://pith.science/pith/EGE54Z5L5U2YJYBWC4NNAJPMWX.json","graph_json":"https://pith.science/api/pith-number/EGE54Z5L5U2YJYBWC4NNAJPMWX/graph.json","events_json":"https://pith.science/api/pith-number/EGE54Z5L5U2YJYBWC4NNAJPMWX/events.json","paper":"https://pith.science/paper/EGE54Z5L"},"agent_actions":{"view_html":"https://pith.science/pith/EGE54Z5L5U2YJYBWC4NNAJPMWX","download_json":"https://pith.science/pith/EGE54Z5L5U2YJYBWC4NNAJPMWX.json","view_paper":"https://pith.science/paper/EGE54Z5L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17091&json=true","fetch_graph":"https://pith.science/api/pith-number/EGE54Z5L5U2YJYBWC4NNAJPMWX/graph.json","fetch_events":"https://pith.science/api/pith-number/EGE54Z5L5U2YJYBWC4NNAJPMWX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EGE54Z5L5U2YJYBWC4NNAJPMWX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EGE54Z5L5U2YJYBWC4NNAJPMWX/action/storage_attestation","attest_author":"https://pith.science/pith/EGE54Z5L5U2YJYBWC4NNAJPMWX/action/author_attestation","sign_citation":"https://pith.science/pith/EGE54Z5L5U2YJYBWC4NNAJPMWX/action/citation_signature","submit_replication":"https://pith.science/pith/EGE54Z5L5U2YJYBWC4NNAJPMWX/action/replication_record"}},"created_at":"2026-07-05T08:26:15.970021+00:00","updated_at":"2026-07-05T08:26:15.970021+00:00"}