{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DQ76N25NRAMZHAA2GZUGSLISE5","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":"c7aafd8dfc729abefaf5c7442f89eeb57b67faaa3f9c789ad9bf31b6ba7f890b","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-14T09:39:03Z","title_canon_sha256":"3382f0e32bc1386483b243238d8b56e0459d4971e9b1ab0621eaea5b14de6eb9"},"schema_version":"1.0","source":{"id":"2209.06515","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.06515","created_at":"2026-07-05T04:58:39Z"},{"alias_kind":"arxiv_version","alias_value":"2209.06515v3","created_at":"2026-07-05T04:58:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06515","created_at":"2026-07-05T04:58:39Z"},{"alias_kind":"pith_short_12","alias_value":"DQ76N25NRAMZ","created_at":"2026-07-05T04:58:39Z"},{"alias_kind":"pith_short_16","alias_value":"DQ76N25NRAMZHAA2","created_at":"2026-07-05T04:58:39Z"},{"alias_kind":"pith_short_8","alias_value":"DQ76N25N","created_at":"2026-07-05T04:58:39Z"}],"graph_snapshots":[{"event_id":"sha256:65a11c6203ca381b66116c549b3526db3866105a31c19da590fab5273773ce58","target":"graph","created_at":"2026-07-05T04:58:39Z","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/2209.06515/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semantic localization (SeLo) refers to the task of obtaining the most relevant locations in large-scale remote sensing (RS) images using semantic information such as text. As an emerging task based on cross-modal retrieval, SeLo achieves semantic-level retrieval with only caption-level annotation, which demonstrates its great potential in unifying downstream tasks. Although SeLo has been carried out successively, but there is currently no work has systematically explores and analyzes this urgent direction. In this paper, we thoroughly study this field and provide a complete benchmark in terms ","authors_text":"Chongyang Li, Hongqi Wang, Jialiang Chen, Shouke Li, Wenkai Zhang, Xian Sun, Yongqiang Mao, Zhaoying Pan, Zhiqiang Yuan","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-14T09:39:03Z","title":"Learning to Evaluate Performance of Multi-modal Semantic Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06515","kind":"arxiv","version":3},"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:fcd0fdda025686c6d8c2d4c618eda3010c60ad01ce08e3af1343973556ed44bf","target":"record","created_at":"2026-07-05T04:58:39Z","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":"c7aafd8dfc729abefaf5c7442f89eeb57b67faaa3f9c789ad9bf31b6ba7f890b","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-14T09:39:03Z","title_canon_sha256":"3382f0e32bc1386483b243238d8b56e0459d4971e9b1ab0621eaea5b14de6eb9"},"schema_version":"1.0","source":{"id":"2209.06515","kind":"arxiv","version":3}},"canonical_sha256":"1c3fe6ebad881993801a3668692d12274165b8ae59e14cd0864832b1469ad44a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c3fe6ebad881993801a3668692d12274165b8ae59e14cd0864832b1469ad44a","first_computed_at":"2026-07-05T04:58:39.589953Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:58:39.589953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bEg+/hLLCPl7Sn/Zy7JXDOUH5Mva2TmSLQ6YGqAMXSh34Y3CZeueuFcgIc5wE/IEU1QkmbcT9CaZcbDAZzseBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:58:39.590448Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.06515","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcd0fdda025686c6d8c2d4c618eda3010c60ad01ce08e3af1343973556ed44bf","sha256:65a11c6203ca381b66116c549b3526db3866105a31c19da590fab5273773ce58"],"state_sha256":"a77e2d88aaeff5e8cc74cc32a591090c2ab29d74d3dea7d97c97be14e5dd55f8"}