{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5ZOUT47SIGJOPTVP5OXOH4IWC6","short_pith_number":"pith:5ZOUT47S","schema_version":"1.0","canonical_sha256":"ee5d49f3f24192e7ceafebaee3f116179876fae77ad3300ed9fd8b63daac5177","source":{"kind":"arxiv","id":"2507.05887","version":2},"attestation_state":"computed","paper":{"title":"GeoMag: A Vision-Language Model for Pixel-level Fine-Grained Remote Sensing Image Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changhua Pei, Hao Liu, Jianhui Li, Xianzhi Ma","submitted_at":"2025-07-08T11:21:03Z","abstract_excerpt":"The application of Vision-Language Models (VLMs) in remote sensing (RS) image understanding has achieved notable progress, demonstrating the basic ability to recognize and describe geographical entities. However, existing RS-VLMs are mostly limited to image-level and region-level tasks, lacking the capability to handle pixel-level tasks and performing poorly in small-object recognition scenarios. Moreover, RS-VLMs consume significant computational resources when processing high-resolution RS images, further restricting their practical applicability. In this context, we propose GeoMag (Geograph"},"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":"2507.05887","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T11:21:03Z","cross_cats_sorted":[],"title_canon_sha256":"ce60fee8cfd4c57784558e3e42561e14ce428b9e03cec3c35a5d649a55a46a97","abstract_canon_sha256":"eb2da2aac07f0715cad29c8af6bde7f699cf5f7c888cc210728543fcc50464de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:13.182487Z","signature_b64":"MkHgawi91nn4YVXOpmkWQhCFdOw5ob+goV6wO47avycy5Vzyv1Lh/z3PINUqZa4KEpXRBTw612NfwZw6wYGmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee5d49f3f24192e7ceafebaee3f116179876fae77ad3300ed9fd8b63daac5177","last_reissued_at":"2026-07-05T11:39:13.182036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:13.182036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoMag: A Vision-Language Model for Pixel-level Fine-Grained Remote Sensing Image Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changhua Pei, Hao Liu, Jianhui Li, Xianzhi Ma","submitted_at":"2025-07-08T11:21:03Z","abstract_excerpt":"The application of Vision-Language Models (VLMs) in remote sensing (RS) image understanding has achieved notable progress, demonstrating the basic ability to recognize and describe geographical entities. However, existing RS-VLMs are mostly limited to image-level and region-level tasks, lacking the capability to handle pixel-level tasks and performing poorly in small-object recognition scenarios. Moreover, RS-VLMs consume significant computational resources when processing high-resolution RS images, further restricting their practical applicability. In this context, we propose GeoMag (Geograph"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05887","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/2507.05887/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":"2507.05887","created_at":"2026-07-05T11:39:13.182085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05887v2","created_at":"2026-07-05T11:39:13.182085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05887","created_at":"2026-07-05T11:39:13.182085+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZOUT47SIGJO","created_at":"2026-07-05T11:39:13.182085+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZOUT47SIGJOPTVP","created_at":"2026-07-05T11:39:13.182085+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZOUT47S","created_at":"2026-07-05T11:39:13.182085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13654","citing_title":"Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap","ref_index":143,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ZOUT47SIGJOPTVP5OXOH4IWC6","json":"https://pith.science/pith/5ZOUT47SIGJOPTVP5OXOH4IWC6.json","graph_json":"https://pith.science/api/pith-number/5ZOUT47SIGJOPTVP5OXOH4IWC6/graph.json","events_json":"https://pith.science/api/pith-number/5ZOUT47SIGJOPTVP5OXOH4IWC6/events.json","paper":"https://pith.science/paper/5ZOUT47S"},"agent_actions":{"view_html":"https://pith.science/pith/5ZOUT47SIGJOPTVP5OXOH4IWC6","download_json":"https://pith.science/pith/5ZOUT47SIGJOPTVP5OXOH4IWC6.json","view_paper":"https://pith.science/paper/5ZOUT47S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05887&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZOUT47SIGJOPTVP5OXOH4IWC6/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZOUT47SIGJOPTVP5OXOH4IWC6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZOUT47SIGJOPTVP5OXOH4IWC6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZOUT47SIGJOPTVP5OXOH4IWC6/action/storage_attestation","attest_author":"https://pith.science/pith/5ZOUT47SIGJOPTVP5OXOH4IWC6/action/author_attestation","sign_citation":"https://pith.science/pith/5ZOUT47SIGJOPTVP5OXOH4IWC6/action/citation_signature","submit_replication":"https://pith.science/pith/5ZOUT47SIGJOPTVP5OXOH4IWC6/action/replication_record"}},"created_at":"2026-07-05T11:39:13.182085+00:00","updated_at":"2026-07-05T11:39:13.182085+00:00"}