{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AKK224GTYEY5VUMKVN47PI2FSE","short_pith_number":"pith:AKK224GT","schema_version":"1.0","canonical_sha256":"0295ad70d3c131dad18aab79f7a345910f5d83fe6b09fea4d81a45abe5b250ca","source":{"kind":"arxiv","id":"2305.14095","version":2},"attestation_state":"computed","paper":{"title":"S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jinwoo Shin, Kyungmin Lee, Minkyu Kim, Sangwoo Mo","submitted_at":"2023-05-23T14:18:11Z","abstract_excerpt":"Vision-language models, such as contrastive language-image pre-training (CLIP), have demonstrated impressive results in natural image domains. However, these models often struggle when applied to specialized domains like remote sensing, and adapting to such domains is challenging due to the limited number of image-text pairs available for training. To address this, we propose S-CLIP, a semi-supervised learning method for training CLIP that utilizes additional unpaired images. S-CLIP employs two pseudo-labeling strategies specifically designed for contrastive learning and the language modality."},"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":"2305.14095","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T14:18:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4d8110b591108933d882619c20c87905ef93435d55e42d94357fde7d6e1480cc","abstract_canon_sha256":"f52df6f727953307e8a4b5ea8989b9855ce1ad844b89c4eb52461ec26fac7a8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:47.468654Z","signature_b64":"mQCKrWTLR1JH4mIZuvmt7hAb+VkIRPHXzGm+VICLP9BubBC2ddjAfL9K2uAipvyQanl1MPHnU0BQXPguLIXkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0295ad70d3c131dad18aab79f7a345910f5d83fe6b09fea4d81a45abe5b250ca","last_reissued_at":"2026-07-05T07:04:47.468186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:47.468186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jinwoo Shin, Kyungmin Lee, Minkyu Kim, Sangwoo Mo","submitted_at":"2023-05-23T14:18:11Z","abstract_excerpt":"Vision-language models, such as contrastive language-image pre-training (CLIP), have demonstrated impressive results in natural image domains. However, these models often struggle when applied to specialized domains like remote sensing, and adapting to such domains is challenging due to the limited number of image-text pairs available for training. To address this, we propose S-CLIP, a semi-supervised learning method for training CLIP that utilizes additional unpaired images. S-CLIP employs two pseudo-labeling strategies specifically designed for contrastive learning and the language modality."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14095","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/2305.14095/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":"2305.14095","created_at":"2026-07-05T07:04:47.468246+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14095v2","created_at":"2026-07-05T07:04:47.468246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14095","created_at":"2026-07-05T07:04:47.468246+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKK224GTYEY5","created_at":"2026-07-05T07:04:47.468246+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKK224GTYEY5VUMK","created_at":"2026-07-05T07:04:47.468246+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKK224GT","created_at":"2026-07-05T07:04:47.468246+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/AKK224GTYEY5VUMKVN47PI2FSE","json":"https://pith.science/pith/AKK224GTYEY5VUMKVN47PI2FSE.json","graph_json":"https://pith.science/api/pith-number/AKK224GTYEY5VUMKVN47PI2FSE/graph.json","events_json":"https://pith.science/api/pith-number/AKK224GTYEY5VUMKVN47PI2FSE/events.json","paper":"https://pith.science/paper/AKK224GT"},"agent_actions":{"view_html":"https://pith.science/pith/AKK224GTYEY5VUMKVN47PI2FSE","download_json":"https://pith.science/pith/AKK224GTYEY5VUMKVN47PI2FSE.json","view_paper":"https://pith.science/paper/AKK224GT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14095&json=true","fetch_graph":"https://pith.science/api/pith-number/AKK224GTYEY5VUMKVN47PI2FSE/graph.json","fetch_events":"https://pith.science/api/pith-number/AKK224GTYEY5VUMKVN47PI2FSE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKK224GTYEY5VUMKVN47PI2FSE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKK224GTYEY5VUMKVN47PI2FSE/action/storage_attestation","attest_author":"https://pith.science/pith/AKK224GTYEY5VUMKVN47PI2FSE/action/author_attestation","sign_citation":"https://pith.science/pith/AKK224GTYEY5VUMKVN47PI2FSE/action/citation_signature","submit_replication":"https://pith.science/pith/AKK224GTYEY5VUMKVN47PI2FSE/action/replication_record"}},"created_at":"2026-07-05T07:04:47.468246+00:00","updated_at":"2026-07-05T07:04:47.468246+00:00"}