{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7IKRP7VCYFCS474UTDRIK7RLRO","short_pith_number":"pith:7IKRP7VC","schema_version":"1.0","canonical_sha256":"fa1517fea2c1452e7f9498e2857e2b8bac17bf6b35fe2a930b55b99535ef030e","source":{"kind":"arxiv","id":"2504.03254","version":1},"attestation_state":"computed","paper":{"title":"SARLANG-1M: A Benchmark for Vision-Language Modeling in SAR Image Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aoran Xiao, Hongruixuan Chen, Junshi Xia, Naoto Yokoya, Yexian Ren, Yimin Wei, Yuting Zhu","submitted_at":"2025-04-04T08:09:53Z","abstract_excerpt":"Synthetic Aperture Radar (SAR) is a crucial remote sensing technology, enabling all-weather, day-and-night observation with strong surface penetration for precise and continuous environmental monitoring and analysis. However, SAR image interpretation remains challenging due to its complex physical imaging mechanisms and significant visual disparities from human perception. Recently, Vision-Language Models (VLMs) have demonstrated remarkable success in RGB image understanding, offering powerful open-vocabulary interpretation and flexible language interaction. However, their application to SAR i"},"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":"2504.03254","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-04T08:09:53Z","cross_cats_sorted":[],"title_canon_sha256":"c20e46d770c9587486e7e53f04e5f9fa9d4effbf1b77f38bc000458192b11908","abstract_canon_sha256":"67246ba563012b5f0844f72a32413d26911ad53f4687d8cef3737257cea29f8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:28.958441Z","signature_b64":"xzzLn894Pq1yvCXA74HcUBu2rH56V2169MC2TPtCo7lu33lyJvIq8r66XAOX2rBvXOb/zEcYdmXZzo1U4zktCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa1517fea2c1452e7f9498e2857e2b8bac17bf6b35fe2a930b55b99535ef030e","last_reissued_at":"2026-07-05T10:44:28.958029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:28.958029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SARLANG-1M: A Benchmark for Vision-Language Modeling in SAR Image Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aoran Xiao, Hongruixuan Chen, Junshi Xia, Naoto Yokoya, Yexian Ren, Yimin Wei, Yuting Zhu","submitted_at":"2025-04-04T08:09:53Z","abstract_excerpt":"Synthetic Aperture Radar (SAR) is a crucial remote sensing technology, enabling all-weather, day-and-night observation with strong surface penetration for precise and continuous environmental monitoring and analysis. However, SAR image interpretation remains challenging due to its complex physical imaging mechanisms and significant visual disparities from human perception. Recently, Vision-Language Models (VLMs) have demonstrated remarkable success in RGB image understanding, offering powerful open-vocabulary interpretation and flexible language interaction. However, their application to SAR i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03254","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/2504.03254/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":"2504.03254","created_at":"2026-07-05T10:44:28.958087+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.03254v1","created_at":"2026-07-05T10:44:28.958087+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03254","created_at":"2026-07-05T10:44:28.958087+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IKRP7VCYFCS","created_at":"2026-07-05T10:44:28.958087+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IKRP7VCYFCS474U","created_at":"2026-07-05T10:44:28.958087+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IKRP7VC","created_at":"2026-07-05T10:44:28.958087+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.22665","citing_title":"SARVLM: A Vision Language Foundation Model for Semantic Understanding in SAR Imagery","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03189","citing_title":"Sentinel2Cap: A Human-Annotated Benchmark Dataset for Multimodal Remote Sensing Image Captioning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13654","citing_title":"Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap","ref_index":237,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7IKRP7VCYFCS474UTDRIK7RLRO","json":"https://pith.science/pith/7IKRP7VCYFCS474UTDRIK7RLRO.json","graph_json":"https://pith.science/api/pith-number/7IKRP7VCYFCS474UTDRIK7RLRO/graph.json","events_json":"https://pith.science/api/pith-number/7IKRP7VCYFCS474UTDRIK7RLRO/events.json","paper":"https://pith.science/paper/7IKRP7VC"},"agent_actions":{"view_html":"https://pith.science/pith/7IKRP7VCYFCS474UTDRIK7RLRO","download_json":"https://pith.science/pith/7IKRP7VCYFCS474UTDRIK7RLRO.json","view_paper":"https://pith.science/paper/7IKRP7VC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.03254&json=true","fetch_graph":"https://pith.science/api/pith-number/7IKRP7VCYFCS474UTDRIK7RLRO/graph.json","fetch_events":"https://pith.science/api/pith-number/7IKRP7VCYFCS474UTDRIK7RLRO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IKRP7VCYFCS474UTDRIK7RLRO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IKRP7VCYFCS474UTDRIK7RLRO/action/storage_attestation","attest_author":"https://pith.science/pith/7IKRP7VCYFCS474UTDRIK7RLRO/action/author_attestation","sign_citation":"https://pith.science/pith/7IKRP7VCYFCS474UTDRIK7RLRO/action/citation_signature","submit_replication":"https://pith.science/pith/7IKRP7VCYFCS474UTDRIK7RLRO/action/replication_record"}},"created_at":"2026-07-05T10:44:28.958087+00:00","updated_at":"2026-07-05T10:44:28.958087+00:00"}