{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:63LXD4ABPVBUKR47ATQNQIHSWS","short_pith_number":"pith:63LXD4AB","schema_version":"1.0","canonical_sha256":"f6d771f0017d4345479f04e0d820f2b4b9c03766b546f46a7626a78bdbffec62","source":{"kind":"arxiv","id":"2401.09712","version":1},"attestation_state":"computed","paper":{"title":"SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yang Zhan, Yuan Yuan, Zhitong Xiong","submitted_at":"2024-01-18T04:10:20Z","abstract_excerpt":"Large language models (LLMs) have recently been extended to the vision-language realm, obtaining impressive general multi-modal capabilities. However, the exploration of multi-modal large language models (MLLMs) for remote sensing (RS) data is still in its infancy, and the performance is not satisfactory. In this work, we introduce SkyEyeGPT, a unified multi-modal large language model specifically designed for RS vision-language understanding. To this end, we meticulously curate an RS multi-modal instruction tuning dataset, including single-task and multi-task conversation instructions. After "},"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":"2401.09712","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-18T04:10:20Z","cross_cats_sorted":[],"title_canon_sha256":"3f86438b4823788cae402f9908d68db93f3cf4242d31e15977e90e4a20724f95","abstract_canon_sha256":"e083974629fff61e2479d1bc2d86f7ef2c817f1a680433e2a43bfc68e915c0ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:01.159681Z","signature_b64":"ulDqEOiFD8t8gCuqih0b/x78FWa9P2PyM3/EMB03AZjQ/kqKS3hEJeRbu4R5TCenK2K93gsaDVdSp2b6rZyzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6d771f0017d4345479f04e0d820f2b4b9c03766b546f46a7626a78bdbffec62","last_reissued_at":"2026-07-05T07:35:01.159085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:01.159085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yang Zhan, Yuan Yuan, Zhitong Xiong","submitted_at":"2024-01-18T04:10:20Z","abstract_excerpt":"Large language models (LLMs) have recently been extended to the vision-language realm, obtaining impressive general multi-modal capabilities. However, the exploration of multi-modal large language models (MLLMs) for remote sensing (RS) data is still in its infancy, and the performance is not satisfactory. In this work, we introduce SkyEyeGPT, a unified multi-modal large language model specifically designed for RS vision-language understanding. To this end, we meticulously curate an RS multi-modal instruction tuning dataset, including single-task and multi-task conversation instructions. After "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09712","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/2401.09712/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":"2401.09712","created_at":"2026-07-05T07:35:01.159146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.09712v1","created_at":"2026-07-05T07:35:01.159146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09712","created_at":"2026-07-05T07:35:01.159146+00:00"},{"alias_kind":"pith_short_12","alias_value":"63LXD4ABPVBU","created_at":"2026-07-05T07:35:01.159146+00:00"},{"alias_kind":"pith_short_16","alias_value":"63LXD4ABPVBUKR47","created_at":"2026-07-05T07:35:01.159146+00:00"},{"alias_kind":"pith_short_8","alias_value":"63LXD4AB","created_at":"2026-07-05T07:35:01.159146+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31467","citing_title":"AeroVerse-SatAgent: UAV-Satellite Collaborative Spatial Reasoning Inspired by the Dual Visual Pathway Theory of Cognitive Neuroscience","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14475","citing_title":"GeoVista: Visually Grounded Active Perception for Ultra-High-Resolution Remote Sensing Understanding","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/63LXD4ABPVBUKR47ATQNQIHSWS","json":"https://pith.science/pith/63LXD4ABPVBUKR47ATQNQIHSWS.json","graph_json":"https://pith.science/api/pith-number/63LXD4ABPVBUKR47ATQNQIHSWS/graph.json","events_json":"https://pith.science/api/pith-number/63LXD4ABPVBUKR47ATQNQIHSWS/events.json","paper":"https://pith.science/paper/63LXD4AB"},"agent_actions":{"view_html":"https://pith.science/pith/63LXD4ABPVBUKR47ATQNQIHSWS","download_json":"https://pith.science/pith/63LXD4ABPVBUKR47ATQNQIHSWS.json","view_paper":"https://pith.science/paper/63LXD4AB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.09712&json=true","fetch_graph":"https://pith.science/api/pith-number/63LXD4ABPVBUKR47ATQNQIHSWS/graph.json","fetch_events":"https://pith.science/api/pith-number/63LXD4ABPVBUKR47ATQNQIHSWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/63LXD4ABPVBUKR47ATQNQIHSWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/63LXD4ABPVBUKR47ATQNQIHSWS/action/storage_attestation","attest_author":"https://pith.science/pith/63LXD4ABPVBUKR47ATQNQIHSWS/action/author_attestation","sign_citation":"https://pith.science/pith/63LXD4ABPVBUKR47ATQNQIHSWS/action/citation_signature","submit_replication":"https://pith.science/pith/63LXD4ABPVBUKR47ATQNQIHSWS/action/replication_record"}},"created_at":"2026-07-05T07:35:01.159146+00:00","updated_at":"2026-07-05T07:35:01.159146+00:00"}