{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:24IFQGZDH4QUA7GH7CUTMRZRAO","short_pith_number":"pith:24IFQGZD","schema_version":"1.0","canonical_sha256":"d710581b233f21407cc7f8a936473103b393fbd2db8b71e2d1e6e49c0775af15","source":{"kind":"arxiv","id":"2501.09720","version":3},"attestation_state":"computed","paper":{"title":"A Simple Aerial Detection Baseline of Multimodal Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dong Chen, Qingyun Li, Xin He, Xinya Shu, Xue Yang, Yi Yu, Yushi Chen","submitted_at":"2025-01-16T18:09:22Z","abstract_excerpt":"The multimodal language models (MLMs) based on generative pre-trained Transformer are considered powerful candidates for unifying various domains and tasks. MLMs developed for remote sensing (RS) have demonstrated outstanding performance in multiple tasks, such as visual question answering and visual grounding. In addition to visual grounding that detects specific objects corresponded to given instruction, aerial detection, which detects all objects of multiple categories, is also a valuable and challenging task for RS foundation models. However, aerial detection has not been explored by exist"},"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":"2501.09720","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-16T18:09:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ab4009cb09193fb4416891059748c1693458a6e944e34c650315a628c4b7c9bd","abstract_canon_sha256":"fdc26d914e190893ea24578894be8b727a23c69c6644cffce0dbc925c84e6ec9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:27.955287Z","signature_b64":"xbp3IVIjDouyFo7i4X1UcS2e5Hw0slwDLgaNj6n4nj9CdLGtEAf79ERRnotLvp4Zfdy9GouXDcdpaBEQpiewAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d710581b233f21407cc7f8a936473103b393fbd2db8b71e2d1e6e49c0775af15","last_reissued_at":"2026-07-05T10:08:27.954805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:27.954805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Simple Aerial Detection Baseline of Multimodal Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dong Chen, Qingyun Li, Xin He, Xinya Shu, Xue Yang, Yi Yu, Yushi Chen","submitted_at":"2025-01-16T18:09:22Z","abstract_excerpt":"The multimodal language models (MLMs) based on generative pre-trained Transformer are considered powerful candidates for unifying various domains and tasks. MLMs developed for remote sensing (RS) have demonstrated outstanding performance in multiple tasks, such as visual question answering and visual grounding. In addition to visual grounding that detects specific objects corresponded to given instruction, aerial detection, which detects all objects of multiple categories, is also a valuable and challenging task for RS foundation models. However, aerial detection has not been explored by exist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09720","kind":"arxiv","version":3},"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/2501.09720/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":"2501.09720","created_at":"2026-07-05T10:08:27.954867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09720v3","created_at":"2026-07-05T10:08:27.954867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09720","created_at":"2026-07-05T10:08:27.954867+00:00"},{"alias_kind":"pith_short_12","alias_value":"24IFQGZDH4QU","created_at":"2026-07-05T10:08:27.954867+00:00"},{"alias_kind":"pith_short_16","alias_value":"24IFQGZDH4QUA7GH","created_at":"2026-07-05T10:08:27.954867+00:00"},{"alias_kind":"pith_short_8","alias_value":"24IFQGZD","created_at":"2026-07-05T10:08:27.954867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09471","citing_title":"Wholly-WOOD: Wholly Leveraging Diversified-quality Labels for Weakly-supervised Oriented Object Detection","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24IFQGZDH4QUA7GH7CUTMRZRAO","json":"https://pith.science/pith/24IFQGZDH4QUA7GH7CUTMRZRAO.json","graph_json":"https://pith.science/api/pith-number/24IFQGZDH4QUA7GH7CUTMRZRAO/graph.json","events_json":"https://pith.science/api/pith-number/24IFQGZDH4QUA7GH7CUTMRZRAO/events.json","paper":"https://pith.science/paper/24IFQGZD"},"agent_actions":{"view_html":"https://pith.science/pith/24IFQGZDH4QUA7GH7CUTMRZRAO","download_json":"https://pith.science/pith/24IFQGZDH4QUA7GH7CUTMRZRAO.json","view_paper":"https://pith.science/paper/24IFQGZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09720&json=true","fetch_graph":"https://pith.science/api/pith-number/24IFQGZDH4QUA7GH7CUTMRZRAO/graph.json","fetch_events":"https://pith.science/api/pith-number/24IFQGZDH4QUA7GH7CUTMRZRAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24IFQGZDH4QUA7GH7CUTMRZRAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24IFQGZDH4QUA7GH7CUTMRZRAO/action/storage_attestation","attest_author":"https://pith.science/pith/24IFQGZDH4QUA7GH7CUTMRZRAO/action/author_attestation","sign_citation":"https://pith.science/pith/24IFQGZDH4QUA7GH7CUTMRZRAO/action/citation_signature","submit_replication":"https://pith.science/pith/24IFQGZDH4QUA7GH7CUTMRZRAO/action/replication_record"}},"created_at":"2026-07-05T10:08:27.954867+00:00","updated_at":"2026-07-05T10:08:27.954867+00:00"}