{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OVKPPTWWMEGKBHLUMJEJYNWS6C","short_pith_number":"pith:OVKPPTWW","schema_version":"1.0","canonical_sha256":"7554f7ced6610ca09d7462489c36d2f0866d0425520c5d05bf036be03f1d6fa1","source":{"kind":"arxiv","id":"2504.09644","version":1},"attestation_state":"computed","paper":{"title":"SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Pang, Deyu Meng, Guisong Xia, Jing Yao, Kaiyu Li, Li Pang, Xiangyong Cao, Yupeng Deng, Zepeng Xin, Zhi Wang","submitted_at":"2025-04-13T16:36:47Z","abstract_excerpt":"Remote sensing has become critical for understanding environmental dynamics, urban planning, and disaster management. However, traditional remote sensing workflows often rely on explicit segmentation or detection methods, which struggle to handle complex, implicit queries that require reasoning over spatial context, domain knowledge, and implicit user intent. Motivated by this, we introduce a new task, \\ie, geospatial pixel reasoning, which allows implicit querying and reasoning and generates the mask of the target region. To advance this task, we construct and release the first large-scale be"},"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":"2504.09644","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-13T16:36:47Z","cross_cats_sorted":[],"title_canon_sha256":"320774c609e48a40c3395cd35bea54b17c38305f5978089811997e120e8e73ec","abstract_canon_sha256":"f692bf0e5f22f158df49964c87a3bd3c491fa02961ff33d56a334e3fa039e539"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:40.647234Z","signature_b64":"1/konXmbbBzRwXw4euUBx30zuWHWMQsOt4ihFCUTVqC9eOaHcLh+9OpBRCls1neP5yMMZVbA5+1tMgtLgRurCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7554f7ced6610ca09d7462489c36d2f0866d0425520c5d05bf036be03f1d6fa1","last_reissued_at":"2026-07-05T10:48:40.646747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:40.646747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Pang, Deyu Meng, Guisong Xia, Jing Yao, Kaiyu Li, Li Pang, Xiangyong Cao, Yupeng Deng, Zepeng Xin, Zhi Wang","submitted_at":"2025-04-13T16:36:47Z","abstract_excerpt":"Remote sensing has become critical for understanding environmental dynamics, urban planning, and disaster management. However, traditional remote sensing workflows often rely on explicit segmentation or detection methods, which struggle to handle complex, implicit queries that require reasoning over spatial context, domain knowledge, and implicit user intent. Motivated by this, we introduce a new task, \\ie, geospatial pixel reasoning, which allows implicit querying and reasoning and generates the mask of the target region. To advance this task, we construct and release the first large-scale be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09644","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/2504.09644/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":"2504.09644","created_at":"2026-07-05T10:48:40.646808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.09644v1","created_at":"2026-07-05T10:48:40.646808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09644","created_at":"2026-07-05T10:48:40.646808+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVKPPTWWMEGK","created_at":"2026-07-05T10:48:40.646808+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVKPPTWWMEGKBHLU","created_at":"2026-07-05T10:48:40.646808+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVKPPTWW","created_at":"2026-07-05T10:48:40.646808+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10819","citing_title":"Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Tasks","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06217","citing_title":"DisasterBench: A Multimodal Benchmark for UAV-Based Disaster Response in Complex Environments","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00987","citing_title":"An Open-Source Benchmark and Baseline for Multi-temporal Referring Segmentation","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22034","citing_title":"AgroVG: A Large-Scale Multi-Source Benchmark for Agricultural Visual Grounding","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2511.23332","citing_title":"UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24919","citing_title":"Agentic AI for Remote Sensing: Technical Challenges and Research Directions","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24919","citing_title":"Agentic AI for Remote Sensing: Technical Challenges and Research Directions","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07765","citing_title":"RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15670","citing_title":"PixDLM: A Dual-Path Multimodal Language Model for UAV Reasoning Segmentation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17243","citing_title":"RemoteShield: Enable Robust Multimodal Large Language Models for Earth Observation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04451","citing_title":"RemoteZero: Geospatial Reasoning with Zero Human Annotations","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OVKPPTWWMEGKBHLUMJEJYNWS6C","json":"https://pith.science/pith/OVKPPTWWMEGKBHLUMJEJYNWS6C.json","graph_json":"https://pith.science/api/pith-number/OVKPPTWWMEGKBHLUMJEJYNWS6C/graph.json","events_json":"https://pith.science/api/pith-number/OVKPPTWWMEGKBHLUMJEJYNWS6C/events.json","paper":"https://pith.science/paper/OVKPPTWW"},"agent_actions":{"view_html":"https://pith.science/pith/OVKPPTWWMEGKBHLUMJEJYNWS6C","download_json":"https://pith.science/pith/OVKPPTWWMEGKBHLUMJEJYNWS6C.json","view_paper":"https://pith.science/paper/OVKPPTWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.09644&json=true","fetch_graph":"https://pith.science/api/pith-number/OVKPPTWWMEGKBHLUMJEJYNWS6C/graph.json","fetch_events":"https://pith.science/api/pith-number/OVKPPTWWMEGKBHLUMJEJYNWS6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVKPPTWWMEGKBHLUMJEJYNWS6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVKPPTWWMEGKBHLUMJEJYNWS6C/action/storage_attestation","attest_author":"https://pith.science/pith/OVKPPTWWMEGKBHLUMJEJYNWS6C/action/author_attestation","sign_citation":"https://pith.science/pith/OVKPPTWWMEGKBHLUMJEJYNWS6C/action/citation_signature","submit_replication":"https://pith.science/pith/OVKPPTWWMEGKBHLUMJEJYNWS6C/action/replication_record"}},"created_at":"2026-07-05T10:48:40.646808+00:00","updated_at":"2026-07-05T10:48:40.646808+00:00"}