{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XKQDBCIDAVBUDLWNWOKNZOTTT4","short_pith_number":"pith:XKQDBCID","schema_version":"1.0","canonical_sha256":"baa0308903054341aecdb394dcba739f15694c9ad222c86e0e09a479f2228345","source":{"kind":"arxiv","id":"2607.06185","version":1},"attestation_state":"computed","paper":{"title":"Structured-Condensed Prompt Tuning in Vision-Language Models for Fine-grained Image Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guohua Geng, Qinyu Zhang, Shuqiang Jiang, Weiqing Min, Xinda Liu","submitted_at":"2026-07-07T12:09:49Z","abstract_excerpt":"Fine-grained image recognition poses a significant challenge due to the substantial expertise and effort required for manual annotation. Vision-language models (VLMs) like CLIP provide a compelling zero-shot alternative, reducing reliance on extensive labeled data. However, their ability to capture subtle distinctions remains limited, leading to subpar recognition performance. While prompt tuning has proven effective for adapting VLMs, most existing methods treat class labels as isolated, discrete entities, overlooking the rich semantic relationships between them. This oversimplified assumptio"},"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":"2607.06185","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T12:09:49Z","cross_cats_sorted":[],"title_canon_sha256":"7b385db085cabaf39eacdf0714dfd26bfb114c87984339e9e8066aac3a91dabc","abstract_canon_sha256":"bd16e36022f5f6334fe3ae6546e573dc010dd53a130e5f01919d4b4e04cef993"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:19:16.925688Z","signature_b64":"8P51SAVVXBc2AUOblRpHJHjOV3wRm23ohJdd2kk84ioZwgTMRrOsK6Wx+qLQsS50qEEAnBEct7cUdQNXq3MFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"baa0308903054341aecdb394dcba739f15694c9ad222c86e0e09a479f2228345","last_reissued_at":"2026-07-08T01:19:16.925078Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:19:16.925078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured-Condensed Prompt Tuning in Vision-Language Models for Fine-grained Image Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guohua Geng, Qinyu Zhang, Shuqiang Jiang, Weiqing Min, Xinda Liu","submitted_at":"2026-07-07T12:09:49Z","abstract_excerpt":"Fine-grained image recognition poses a significant challenge due to the substantial expertise and effort required for manual annotation. Vision-language models (VLMs) like CLIP provide a compelling zero-shot alternative, reducing reliance on extensive labeled data. However, their ability to capture subtle distinctions remains limited, leading to subpar recognition performance. While prompt tuning has proven effective for adapting VLMs, most existing methods treat class labels as isolated, discrete entities, overlooking the rich semantic relationships between them. This oversimplified assumptio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06185","kind":"arxiv","version":1},"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/2607.06185/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":"2607.06185","created_at":"2026-07-08T01:19:16.925144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06185v1","created_at":"2026-07-08T01:19:16.925144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06185","created_at":"2026-07-08T01:19:16.925144+00:00"},{"alias_kind":"pith_short_12","alias_value":"XKQDBCIDAVBU","created_at":"2026-07-08T01:19:16.925144+00:00"},{"alias_kind":"pith_short_16","alias_value":"XKQDBCIDAVBUDLWN","created_at":"2026-07-08T01:19:16.925144+00:00"},{"alias_kind":"pith_short_8","alias_value":"XKQDBCID","created_at":"2026-07-08T01:19:16.925144+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/XKQDBCIDAVBUDLWNWOKNZOTTT4","json":"https://pith.science/pith/XKQDBCIDAVBUDLWNWOKNZOTTT4.json","graph_json":"https://pith.science/api/pith-number/XKQDBCIDAVBUDLWNWOKNZOTTT4/graph.json","events_json":"https://pith.science/api/pith-number/XKQDBCIDAVBUDLWNWOKNZOTTT4/events.json","paper":"https://pith.science/paper/XKQDBCID"},"agent_actions":{"view_html":"https://pith.science/pith/XKQDBCIDAVBUDLWNWOKNZOTTT4","download_json":"https://pith.science/pith/XKQDBCIDAVBUDLWNWOKNZOTTT4.json","view_paper":"https://pith.science/paper/XKQDBCID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06185&json=true","fetch_graph":"https://pith.science/api/pith-number/XKQDBCIDAVBUDLWNWOKNZOTTT4/graph.json","fetch_events":"https://pith.science/api/pith-number/XKQDBCIDAVBUDLWNWOKNZOTTT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XKQDBCIDAVBUDLWNWOKNZOTTT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XKQDBCIDAVBUDLWNWOKNZOTTT4/action/storage_attestation","attest_author":"https://pith.science/pith/XKQDBCIDAVBUDLWNWOKNZOTTT4/action/author_attestation","sign_citation":"https://pith.science/pith/XKQDBCIDAVBUDLWNWOKNZOTTT4/action/citation_signature","submit_replication":"https://pith.science/pith/XKQDBCIDAVBUDLWNWOKNZOTTT4/action/replication_record"}},"created_at":"2026-07-08T01:19:16.925144+00:00","updated_at":"2026-07-08T01:19:16.925144+00:00"}