{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V4PO4DFF4UKMLVKU4Y3OR6RILU","short_pith_number":"pith:V4PO4DFF","schema_version":"1.0","canonical_sha256":"af1eee0ca5e514c5d554e636e8fa285d02d9b6bc62a526966312655b4cc65c36","source":{"kind":"arxiv","id":"2505.16756","version":1},"attestation_state":"computed","paper":{"title":"Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Asoke K. Nandi, Bin Zhao, Hailong Ning, Huanmin Dou, Petia Radeva, Siying Wang, Tao Lei, Xiaopeng Cao","submitted_at":"2025-05-22T14:59:30Z","abstract_excerpt":"Remote Sensing Image-Text Retrieval (RSITR) plays a critical role in geographic information interpretation, disaster monitoring, and urban planning by establishing semantic associations between image and textual descriptions. Existing Parameter-Efficient Fine-Tuning (PEFT) methods for Vision-and-Language Pre-training (VLP) models typically adopt symmetric adapter structures for exploring cross-modal correlations. However, the strong discriminative nature of text modality may dominate the optimization process and inhibits image representation learning. The nonnegligible imbalanced cross-modal o"},"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":"2505.16756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T14:59:30Z","cross_cats_sorted":["cs.IR","cs.MM"],"title_canon_sha256":"2237f2a7abedf09109256cfb8ed87b230774a9c4090028fe7c352c452b48b3ad","abstract_canon_sha256":"18b50e84d95e6ff31502c0b3a8c2729a224b60c8c3d60f524e4e7e0cdd75d025"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:40.327075Z","signature_b64":"ipp+C9+fMSY/ZFcNc/08YZm/6YNuw+PnlsRB2e+ggHbfzdgksqH2fsMRvO+xcLQfmJ95KyquukG0UuMepPrUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af1eee0ca5e514c5d554e636e8fa285d02d9b6bc62a526966312655b4cc65c36","last_reissued_at":"2026-07-05T11:07:40.326592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:40.326592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Asoke K. Nandi, Bin Zhao, Hailong Ning, Huanmin Dou, Petia Radeva, Siying Wang, Tao Lei, Xiaopeng Cao","submitted_at":"2025-05-22T14:59:30Z","abstract_excerpt":"Remote Sensing Image-Text Retrieval (RSITR) plays a critical role in geographic information interpretation, disaster monitoring, and urban planning by establishing semantic associations between image and textual descriptions. Existing Parameter-Efficient Fine-Tuning (PEFT) methods for Vision-and-Language Pre-training (VLP) models typically adopt symmetric adapter structures for exploring cross-modal correlations. However, the strong discriminative nature of text modality may dominate the optimization process and inhibits image representation learning. The nonnegligible imbalanced cross-modal o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16756","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/2505.16756/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":"2505.16756","created_at":"2026-07-05T11:07:40.326646+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16756v1","created_at":"2026-07-05T11:07:40.326646+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16756","created_at":"2026-07-05T11:07:40.326646+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4PO4DFF4UKM","created_at":"2026-07-05T11:07:40.326646+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4PO4DFF4UKMLVKU","created_at":"2026-07-05T11:07:40.326646+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4PO4DFF","created_at":"2026-07-05T11:07:40.326646+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/V4PO4DFF4UKMLVKU4Y3OR6RILU","json":"https://pith.science/pith/V4PO4DFF4UKMLVKU4Y3OR6RILU.json","graph_json":"https://pith.science/api/pith-number/V4PO4DFF4UKMLVKU4Y3OR6RILU/graph.json","events_json":"https://pith.science/api/pith-number/V4PO4DFF4UKMLVKU4Y3OR6RILU/events.json","paper":"https://pith.science/paper/V4PO4DFF"},"agent_actions":{"view_html":"https://pith.science/pith/V4PO4DFF4UKMLVKU4Y3OR6RILU","download_json":"https://pith.science/pith/V4PO4DFF4UKMLVKU4Y3OR6RILU.json","view_paper":"https://pith.science/paper/V4PO4DFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16756&json=true","fetch_graph":"https://pith.science/api/pith-number/V4PO4DFF4UKMLVKU4Y3OR6RILU/graph.json","fetch_events":"https://pith.science/api/pith-number/V4PO4DFF4UKMLVKU4Y3OR6RILU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4PO4DFF4UKMLVKU4Y3OR6RILU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4PO4DFF4UKMLVKU4Y3OR6RILU/action/storage_attestation","attest_author":"https://pith.science/pith/V4PO4DFF4UKMLVKU4Y3OR6RILU/action/author_attestation","sign_citation":"https://pith.science/pith/V4PO4DFF4UKMLVKU4Y3OR6RILU/action/citation_signature","submit_replication":"https://pith.science/pith/V4PO4DFF4UKMLVKU4Y3OR6RILU/action/replication_record"}},"created_at":"2026-07-05T11:07:40.326646+00:00","updated_at":"2026-07-05T11:07:40.326646+00:00"}