{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CS5SKNS2IOD6D3YZ22KAV4FLVS","short_pith_number":"pith:CS5SKNS2","schema_version":"1.0","canonical_sha256":"14bb25365a4387e1ef19d6940af0abac9a11c6cf5d5d81b97907896d724f6bb1","source":{"kind":"arxiv","id":"2501.08114","version":1},"attestation_state":"computed","paper":{"title":"Change Captioning in Remote Sensing: Evolution to SAT-Cap -- A Single-Stage Transformer Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pedram Ghamisi, Weikang Yu, Yuduo Wang","submitted_at":"2025-01-14T13:46:03Z","abstract_excerpt":"Change captioning has become essential for accurately describing changes in multi-temporal remote sensing data, providing an intuitive way to monitor Earth's dynamics through natural language. However, existing change captioning methods face two key challenges: high computational demands due to multistage fusion strategy, and insufficient detail in object descriptions due to limited semantic extraction from individual images. To solve these challenges, we propose SAT-Cap based on the transformers model with a single-stage feature fusion for remote sensing change captioning. In particular, SAT-"},"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":"2501.08114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T13:46:03Z","cross_cats_sorted":[],"title_canon_sha256":"2b9edab5efbcd4baad168ddcb1bc06d68708d6ae37f230fbaf0290418d29298c","abstract_canon_sha256":"53e1b7770c40d3a010746520f1f590d8aa650d0c5061541928f783483968cd97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:56.031129Z","signature_b64":"/ltKGncsIQ5+lf5AVZ9tcRObNffuz/bAHCRjh37GewZyGHIgZDkHqL7O0OXvdaPCwD5wSFhEcmtcEI+8DEwDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14bb25365a4387e1ef19d6940af0abac9a11c6cf5d5d81b97907896d724f6bb1","last_reissued_at":"2026-07-05T10:00:56.030733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:56.030733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Change Captioning in Remote Sensing: Evolution to SAT-Cap -- A Single-Stage Transformer Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pedram Ghamisi, Weikang Yu, Yuduo Wang","submitted_at":"2025-01-14T13:46:03Z","abstract_excerpt":"Change captioning has become essential for accurately describing changes in multi-temporal remote sensing data, providing an intuitive way to monitor Earth's dynamics through natural language. However, existing change captioning methods face two key challenges: high computational demands due to multistage fusion strategy, and insufficient detail in object descriptions due to limited semantic extraction from individual images. To solve these challenges, we propose SAT-Cap based on the transformers model with a single-stage feature fusion for remote sensing change captioning. In particular, SAT-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08114","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/2501.08114/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":"2501.08114","created_at":"2026-07-05T10:00:56.030787+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08114v1","created_at":"2026-07-05T10:00:56.030787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08114","created_at":"2026-07-05T10:00:56.030787+00:00"},{"alias_kind":"pith_short_12","alias_value":"CS5SKNS2IOD6","created_at":"2026-07-05T10:00:56.030787+00:00"},{"alias_kind":"pith_short_16","alias_value":"CS5SKNS2IOD6D3YZ","created_at":"2026-07-05T10:00:56.030787+00:00"},{"alias_kind":"pith_short_8","alias_value":"CS5SKNS2","created_at":"2026-07-05T10:00:56.030787+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15558","citing_title":"Text-RSIR: A Text-Guided Framework for Efficient Remote Sensing Image Transmission and Reconstruction","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CS5SKNS2IOD6D3YZ22KAV4FLVS","json":"https://pith.science/pith/CS5SKNS2IOD6D3YZ22KAV4FLVS.json","graph_json":"https://pith.science/api/pith-number/CS5SKNS2IOD6D3YZ22KAV4FLVS/graph.json","events_json":"https://pith.science/api/pith-number/CS5SKNS2IOD6D3YZ22KAV4FLVS/events.json","paper":"https://pith.science/paper/CS5SKNS2"},"agent_actions":{"view_html":"https://pith.science/pith/CS5SKNS2IOD6D3YZ22KAV4FLVS","download_json":"https://pith.science/pith/CS5SKNS2IOD6D3YZ22KAV4FLVS.json","view_paper":"https://pith.science/paper/CS5SKNS2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08114&json=true","fetch_graph":"https://pith.science/api/pith-number/CS5SKNS2IOD6D3YZ22KAV4FLVS/graph.json","fetch_events":"https://pith.science/api/pith-number/CS5SKNS2IOD6D3YZ22KAV4FLVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CS5SKNS2IOD6D3YZ22KAV4FLVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CS5SKNS2IOD6D3YZ22KAV4FLVS/action/storage_attestation","attest_author":"https://pith.science/pith/CS5SKNS2IOD6D3YZ22KAV4FLVS/action/author_attestation","sign_citation":"https://pith.science/pith/CS5SKNS2IOD6D3YZ22KAV4FLVS/action/citation_signature","submit_replication":"https://pith.science/pith/CS5SKNS2IOD6D3YZ22KAV4FLVS/action/replication_record"}},"created_at":"2026-07-05T10:00:56.030787+00:00","updated_at":"2026-07-05T10:00:56.030787+00:00"}