{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ONR6ZCJFTHMC37WASNDX6QYMEJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a160b583fd31f1b52898252e704d65d9950f89632f0696912488dbcbcf68fe74","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-12T11:09:49Z","title_canon_sha256":"b72394049d5c5efb7e4183dba8692f8c5c36d4754c4f939e8d5a7161d682a1c5"},"schema_version":"1.0","source":{"id":"2506.10575","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10575","created_at":"2026-07-05T11:20:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10575v1","created_at":"2026-07-05T11:20:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10575","created_at":"2026-07-05T11:20:26Z"},{"alias_kind":"pith_short_12","alias_value":"ONR6ZCJFTHMC","created_at":"2026-07-05T11:20:26Z"},{"alias_kind":"pith_short_16","alias_value":"ONR6ZCJFTHMC37WA","created_at":"2026-07-05T11:20:26Z"},{"alias_kind":"pith_short_8","alias_value":"ONR6ZCJF","created_at":"2026-07-05T11:20:26Z"}],"graph_snapshots":[{"event_id":"sha256:9663b4ddda20e5b27cac02ed82e22d3f2eabed77613b71b75d67fd805e1583e2","target":"graph","created_at":"2026-07-05T11:20:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.10575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benefited from image-text contrastive learning, pre-trained vision-language models, e.g., CLIP, allow to direct leverage texts as images (TaI) for parameter-efficient fine-tuning (PEFT). While CLIP is capable of making image features to be similar to the corresponding text features, the modality gap remains a nontrivial issue and limits image recognition performance of TaI. Using multi-label image recognition (MLR) as an example, we present a novel method, called T2I-PAL to tackle the modality gap issue when using only text captions for PEFT. The core design of T2I-PAL is to leverage pre-train","authors_text":"Chun-Mei Feng, Kai Yu, Rick Siow Mong Goh, Salman Khan, Wangmeng Zuo, Xinxing Xu, Yong Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-12T11:09:49Z","title":"Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10575","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1d1ba1e9f708628e40a2c6242f9c57ddf33573e7d4ca50e40935d4e306d71d03","target":"record","created_at":"2026-07-05T11:20:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a160b583fd31f1b52898252e704d65d9950f89632f0696912488dbcbcf68fe74","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-12T11:09:49Z","title_canon_sha256":"b72394049d5c5efb7e4183dba8692f8c5c36d4754c4f939e8d5a7161d682a1c5"},"schema_version":"1.0","source":{"id":"2506.10575","kind":"arxiv","version":1}},"canonical_sha256":"7363ec892599d82dfec093477f430c224bf6d3f3771e42b7d44bc8ff9e9495d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7363ec892599d82dfec093477f430c224bf6d3f3771e42b7d44bc8ff9e9495d0","first_computed_at":"2026-07-05T11:20:26.583006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:26.583006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"053M+tHSIx3Kiultgfhbe7laUtlYNfFXb6O9MTGJufmP8+Bx0horO+8sOcIeTTcUMRIkfn8bF3MEvL84MUlvDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:26.583541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.10575","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d1ba1e9f708628e40a2c6242f9c57ddf33573e7d4ca50e40935d4e306d71d03","sha256:9663b4ddda20e5b27cac02ed82e22d3f2eabed77613b71b75d67fd805e1583e2"],"state_sha256":"c736f373dc15f8439b5dd82d5c0b8a4547148c6da4e8841415a447b499baa873"}