{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QECEH2PFXT66XPET3AAQPSB52T","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":"345d1cf9bb0159a1296a2dcbc025192a26b89589978b8c6c1828d672a22da856","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T10:19:11Z","title_canon_sha256":"f5916dc36a60becccb929f15f6778e85f038cc1f8badd8177c14ef2b6a3840be"},"schema_version":"1.0","source":{"id":"2405.18959","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18959","created_at":"2026-07-05T08:24:45Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18959v1","created_at":"2026-07-05T08:24:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18959","created_at":"2026-07-05T08:24:45Z"},{"alias_kind":"pith_short_12","alias_value":"QECEH2PFXT66","created_at":"2026-07-05T08:24:45Z"},{"alias_kind":"pith_short_16","alias_value":"QECEH2PFXT66XPET","created_at":"2026-07-05T08:24:45Z"},{"alias_kind":"pith_short_8","alias_value":"QECEH2PF","created_at":"2026-07-05T08:24:45Z"}],"graph_snapshots":[{"event_id":"sha256:fb6fd07501d3977782b92b9e6b79898bf2cb37af4a97546dcf8e0ee047b02c55","target":"graph","created_at":"2026-07-05T08:24:45Z","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/2405.18959/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Remote Sensing Image-Text Retrieval (RSITR) is pivotal for knowledge services and data mining in the remote sensing (RS) domain. Considering the multi-scale representations in image content and text vocabulary can enable the models to learn richer representations and enhance retrieval. Current multi-scale RSITR approaches typically align multi-scale fused image features with text features, but overlook aligning image-text pairs at distinct scales separately. This oversight restricts their ability to learn joint representations suitable for effective retrieval. We introduce a novel Multi-Scale ","authors_text":"Dong Zhao, Dou Quan, Licheng Jiao, Rui Yang, Shuang Wang, Yanhe Guo, Yingping Han, Yuanheng Li","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T10:19:11Z","title":"Transcending Fusion: A Multi-Scale Alignment Method for Remote Sensing Image-Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18959","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:c4b383282eb1e801bfd0e68eb07c59b43d014eac0806f6cc0a98cfa4b0d054fb","target":"record","created_at":"2026-07-05T08:24:45Z","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":"345d1cf9bb0159a1296a2dcbc025192a26b89589978b8c6c1828d672a22da856","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T10:19:11Z","title_canon_sha256":"f5916dc36a60becccb929f15f6778e85f038cc1f8badd8177c14ef2b6a3840be"},"schema_version":"1.0","source":{"id":"2405.18959","kind":"arxiv","version":1}},"canonical_sha256":"810443e9e5bcfdebbc93d80107c83dd4d439bfb42ef0f5315d12ad463f13ab97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"810443e9e5bcfdebbc93d80107c83dd4d439bfb42ef0f5315d12ad463f13ab97","first_computed_at":"2026-07-05T08:24:45.989571Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:45.989571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pXF1+0xFB0DXPYpi+kpU4IGuSfwNnr2P67ZiIad4G748uqlStdSZVhoTgz4WIC87FFA0trtwMdOqdKMZVnTmDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:45.990055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18959","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4b383282eb1e801bfd0e68eb07c59b43d014eac0806f6cc0a98cfa4b0d054fb","sha256:fb6fd07501d3977782b92b9e6b79898bf2cb37af4a97546dcf8e0ee047b02c55"],"state_sha256":"334461424311fd0f085f44d1608b5d761b9240f01dc69ed960e3cc7db050cdcb"}