{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A5PSI4BXJQIOX5HZHPLFB7GVQ6","short_pith_number":"pith:A5PSI4BX","schema_version":"1.0","canonical_sha256":"075f2470374c10ebf4f93bd650fcd58782640fd2152ff5e2cba6989fec7fcf02","source":{"kind":"arxiv","id":"2411.11360","version":1},"attestation_state":"computed","paper":{"title":"CCExpert: Advancing MLLM Capability in Remote Sensing Change Captioning with Difference-Aware Integration and a Foundational Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Mingze Wang, Sheng Xu, Yanjing Li, Zhiming Wang","submitted_at":"2024-11-18T08:10:49Z","abstract_excerpt":"Remote Sensing Image Change Captioning (RSICC) aims to generate natural language descriptions of surface changes between multi-temporal remote sensing images, detailing the categories, locations, and dynamics of changed objects (e.g., additions or disappearances). Many current methods attempt to leverage the long-sequence understanding and reasoning capabilities of multimodal large language models (MLLMs) for this task. However, without comprehensive data support, these approaches often alter the essential feature transmission pathways of MLLMs, disrupting the intrinsic knowledge within the mo"},"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":"2411.11360","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-18T08:10:49Z","cross_cats_sorted":[],"title_canon_sha256":"b070758b1e2a1a5aae11324c48e573397ecc143aa773876fa223d0ea6a76dc03","abstract_canon_sha256":"e7ca81613ea8e6b4c0fad327a0e900d7a4bba1c8b254e0d6249610ca65e05332"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:55.151613Z","signature_b64":"MYwu7a2GwSs5gBT/Zg3sWt5ef+zsQB1iWsIo0VU/fKBNTNr9VIxqcHce7Y5h7WgZTUm5WdieT/ryhTUwQmXXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"075f2470374c10ebf4f93bd650fcd58782640fd2152ff5e2cba6989fec7fcf02","last_reissued_at":"2026-07-05T09:36:55.151143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:55.151143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CCExpert: Advancing MLLM Capability in Remote Sensing Change Captioning with Difference-Aware Integration and a Foundational Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Mingze Wang, Sheng Xu, Yanjing Li, Zhiming Wang","submitted_at":"2024-11-18T08:10:49Z","abstract_excerpt":"Remote Sensing Image Change Captioning (RSICC) aims to generate natural language descriptions of surface changes between multi-temporal remote sensing images, detailing the categories, locations, and dynamics of changed objects (e.g., additions or disappearances). Many current methods attempt to leverage the long-sequence understanding and reasoning capabilities of multimodal large language models (MLLMs) for this task. However, without comprehensive data support, these approaches often alter the essential feature transmission pathways of MLLMs, disrupting the intrinsic knowledge within the mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11360","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/2411.11360/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":"2411.11360","created_at":"2026-07-05T09:36:55.151195+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11360v1","created_at":"2026-07-05T09:36:55.151195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11360","created_at":"2026-07-05T09:36:55.151195+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5PSI4BXJQIO","created_at":"2026-07-05T09:36:55.151195+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5PSI4BXJQIOX5HZ","created_at":"2026-07-05T09:36:55.151195+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5PSI4BX","created_at":"2026-07-05T09:36:55.151195+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28266","citing_title":"RSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change Captioning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15024","citing_title":"HiSem: Hierarchical Semantic Disentangling for Remote Sensing Image Change Captioning","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31745","citing_title":"JL1-CC&QA: Extending the JL1-CD Benchmark with Change Captioning and Question Answering","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22333","citing_title":"ChangeQuery: Advancing Remote Sensing Change Analysis for Natural and Human-Induced Disasters from Visual Detection to Semantic Understanding","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14044","citing_title":"Decoding the Delta: Unifying Remote Sensing Change Detection and Understanding with Multimodal Large Language Models","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A5PSI4BXJQIOX5HZHPLFB7GVQ6","json":"https://pith.science/pith/A5PSI4BXJQIOX5HZHPLFB7GVQ6.json","graph_json":"https://pith.science/api/pith-number/A5PSI4BXJQIOX5HZHPLFB7GVQ6/graph.json","events_json":"https://pith.science/api/pith-number/A5PSI4BXJQIOX5HZHPLFB7GVQ6/events.json","paper":"https://pith.science/paper/A5PSI4BX"},"agent_actions":{"view_html":"https://pith.science/pith/A5PSI4BXJQIOX5HZHPLFB7GVQ6","download_json":"https://pith.science/pith/A5PSI4BXJQIOX5HZHPLFB7GVQ6.json","view_paper":"https://pith.science/paper/A5PSI4BX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11360&json=true","fetch_graph":"https://pith.science/api/pith-number/A5PSI4BXJQIOX5HZHPLFB7GVQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/A5PSI4BXJQIOX5HZHPLFB7GVQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5PSI4BXJQIOX5HZHPLFB7GVQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5PSI4BXJQIOX5HZHPLFB7GVQ6/action/storage_attestation","attest_author":"https://pith.science/pith/A5PSI4BXJQIOX5HZHPLFB7GVQ6/action/author_attestation","sign_citation":"https://pith.science/pith/A5PSI4BXJQIOX5HZHPLFB7GVQ6/action/citation_signature","submit_replication":"https://pith.science/pith/A5PSI4BXJQIOX5HZHPLFB7GVQ6/action/replication_record"}},"created_at":"2026-07-05T09:36:55.151195+00:00","updated_at":"2026-07-05T09:36:55.151195+00:00"}