{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MOYCSZPIQAK7ZMD323J7WIYTGD","short_pith_number":"pith:MOYCSZPI","schema_version":"1.0","canonical_sha256":"63b02965e88015fcb07bd6d3fb231330ed078c2710163c2741f78d530fb55bb4","source":{"kind":"arxiv","id":"2507.05165","version":1},"attestation_state":"computed","paper":{"title":"Differential Attention for Multimodal Crisis Event Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdullah-Al-Zubaer Imran, Junfeng Zhu, Nusrat Munia, Olfa Nasraoui","submitted_at":"2025-07-07T16:20:35Z","abstract_excerpt":"Social networks can be a valuable source of information during crisis events. In particular, users can post a stream of multimodal data that can be critical for real-time humanitarian response. However, effectively extracting meaningful information from this large and noisy data stream and effectively integrating heterogeneous data remains a formidable challenge. In this work, we explore vision language models (VLMs) and advanced fusion strategies to enhance the classification of crisis data in three different tasks. We incorporate LLaVA-generated text to improve text-image alignment. Addition"},"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":"2507.05165","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T16:20:35Z","cross_cats_sorted":[],"title_canon_sha256":"70ed36acac70c88dd8272cbe982f68b1870080eb87031231aebd511b8e744035","abstract_canon_sha256":"f8b0db74c0944b74632f35822b3e2aae3d7c8eb5dfe18248ff4188029e6a7550"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:10.167168Z","signature_b64":"SmSrZONLImlaGpuX7ce9T9Rt+q6Q2tvTDMl8REZqDF6X1ux4Ca35CRUt+Dz/Lq6DCzlqaA2f4gFvOi8NTkaDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63b02965e88015fcb07bd6d3fb231330ed078c2710163c2741f78d530fb55bb4","last_reissued_at":"2026-07-05T11:33:10.166699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:10.166699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differential Attention for Multimodal Crisis Event Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdullah-Al-Zubaer Imran, Junfeng Zhu, Nusrat Munia, Olfa Nasraoui","submitted_at":"2025-07-07T16:20:35Z","abstract_excerpt":"Social networks can be a valuable source of information during crisis events. In particular, users can post a stream of multimodal data that can be critical for real-time humanitarian response. However, effectively extracting meaningful information from this large and noisy data stream and effectively integrating heterogeneous data remains a formidable challenge. In this work, we explore vision language models (VLMs) and advanced fusion strategies to enhance the classification of crisis data in three different tasks. We incorporate LLaVA-generated text to improve text-image alignment. Addition"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05165","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/2507.05165/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":"2507.05165","created_at":"2026-07-05T11:33:10.166756+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05165v1","created_at":"2026-07-05T11:33:10.166756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05165","created_at":"2026-07-05T11:33:10.166756+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOYCSZPIQAK7","created_at":"2026-07-05T11:33:10.166756+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOYCSZPIQAK7ZMD3","created_at":"2026-07-05T11:33:10.166756+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOYCSZPI","created_at":"2026-07-05T11:33:10.166756+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MOYCSZPIQAK7ZMD323J7WIYTGD","json":"https://pith.science/pith/MOYCSZPIQAK7ZMD323J7WIYTGD.json","graph_json":"https://pith.science/api/pith-number/MOYCSZPIQAK7ZMD323J7WIYTGD/graph.json","events_json":"https://pith.science/api/pith-number/MOYCSZPIQAK7ZMD323J7WIYTGD/events.json","paper":"https://pith.science/paper/MOYCSZPI"},"agent_actions":{"view_html":"https://pith.science/pith/MOYCSZPIQAK7ZMD323J7WIYTGD","download_json":"https://pith.science/pith/MOYCSZPIQAK7ZMD323J7WIYTGD.json","view_paper":"https://pith.science/paper/MOYCSZPI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05165&json=true","fetch_graph":"https://pith.science/api/pith-number/MOYCSZPIQAK7ZMD323J7WIYTGD/graph.json","fetch_events":"https://pith.science/api/pith-number/MOYCSZPIQAK7ZMD323J7WIYTGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOYCSZPIQAK7ZMD323J7WIYTGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOYCSZPIQAK7ZMD323J7WIYTGD/action/storage_attestation","attest_author":"https://pith.science/pith/MOYCSZPIQAK7ZMD323J7WIYTGD/action/author_attestation","sign_citation":"https://pith.science/pith/MOYCSZPIQAK7ZMD323J7WIYTGD/action/citation_signature","submit_replication":"https://pith.science/pith/MOYCSZPIQAK7ZMD323J7WIYTGD/action/replication_record"}},"created_at":"2026-07-05T11:33:10.166756+00:00","updated_at":"2026-07-05T11:33:10.166756+00:00"}