{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7WGBRCLAUDZ2SMRQRX6VKJ6JK6","short_pith_number":"pith:7WGBRCLA","schema_version":"1.0","canonical_sha256":"fd8c188960a0f3a932308dfd5527c9579cca83399dfe0510909445004e976321","source":{"kind":"arxiv","id":"2606.09428","version":1},"attestation_state":"computed","paper":{"title":"Guide Me Out: A Framework to Benchmark VLM Operators Communication in Crisis Scenarios","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Giacomo Gonella, Marco Guerini, Stefano Menini","submitted_at":"2026-06-08T12:40:26Z","abstract_excerpt":"Effective crisis response requires spatially grounded communication that bridges linguistic guidance of civilians with the physical environment, accounting for structural bottlenecks, evolving threats, and agent-specific contexts. Yet, current NLP research in crisis communication remains mainly limited to static, text-only classification settings, overlooking the critical communicative role of AI operators in dynamic, embodied scenarios. We address this gap with a novel benchmarking framework for evaluating Vision-Language Models (VLMs) tasked with guiding civilian agents through simulated eva"},"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":"2606.09428","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T12:40:26Z","cross_cats_sorted":[],"title_canon_sha256":"777549fe04acf7a5432a86fd101539beb8cbc0ce780e8026fb26dc3a906a8e0d","abstract_canon_sha256":"718369de5bc879319b30baeb89cdd0e835ac47d3377f7516d135b4498cf38845"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:47.840768Z","signature_b64":"iVIJRPXvO/ceqjFAA49IolCAmXS4X+Hh9/RJz21EM8UY1N+Syn2m1uFV93xZR/yS7Fkrdpi74fAGHEdVWYS+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd8c188960a0f3a932308dfd5527c9579cca83399dfe0510909445004e976321","last_reissued_at":"2026-06-09T02:08:47.839552Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:47.839552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guide Me Out: A Framework to Benchmark VLM Operators Communication in Crisis Scenarios","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Giacomo Gonella, Marco Guerini, Stefano Menini","submitted_at":"2026-06-08T12:40:26Z","abstract_excerpt":"Effective crisis response requires spatially grounded communication that bridges linguistic guidance of civilians with the physical environment, accounting for structural bottlenecks, evolving threats, and agent-specific contexts. Yet, current NLP research in crisis communication remains mainly limited to static, text-only classification settings, overlooking the critical communicative role of AI operators in dynamic, embodied scenarios. We address this gap with a novel benchmarking framework for evaluating Vision-Language Models (VLMs) tasked with guiding civilian agents through simulated eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09428","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/2606.09428/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":"2606.09428","created_at":"2026-06-09T02:08:47.839732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09428v1","created_at":"2026-06-09T02:08:47.839732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09428","created_at":"2026-06-09T02:08:47.839732+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WGBRCLAUDZ2","created_at":"2026-06-09T02:08:47.839732+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WGBRCLAUDZ2SMRQ","created_at":"2026-06-09T02:08:47.839732+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WGBRCLA","created_at":"2026-06-09T02:08:47.839732+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/7WGBRCLAUDZ2SMRQRX6VKJ6JK6","json":"https://pith.science/pith/7WGBRCLAUDZ2SMRQRX6VKJ6JK6.json","graph_json":"https://pith.science/api/pith-number/7WGBRCLAUDZ2SMRQRX6VKJ6JK6/graph.json","events_json":"https://pith.science/api/pith-number/7WGBRCLAUDZ2SMRQRX6VKJ6JK6/events.json","paper":"https://pith.science/paper/7WGBRCLA"},"agent_actions":{"view_html":"https://pith.science/pith/7WGBRCLAUDZ2SMRQRX6VKJ6JK6","download_json":"https://pith.science/pith/7WGBRCLAUDZ2SMRQRX6VKJ6JK6.json","view_paper":"https://pith.science/paper/7WGBRCLA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09428&json=true","fetch_graph":"https://pith.science/api/pith-number/7WGBRCLAUDZ2SMRQRX6VKJ6JK6/graph.json","fetch_events":"https://pith.science/api/pith-number/7WGBRCLAUDZ2SMRQRX6VKJ6JK6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WGBRCLAUDZ2SMRQRX6VKJ6JK6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WGBRCLAUDZ2SMRQRX6VKJ6JK6/action/storage_attestation","attest_author":"https://pith.science/pith/7WGBRCLAUDZ2SMRQRX6VKJ6JK6/action/author_attestation","sign_citation":"https://pith.science/pith/7WGBRCLAUDZ2SMRQRX6VKJ6JK6/action/citation_signature","submit_replication":"https://pith.science/pith/7WGBRCLAUDZ2SMRQRX6VKJ6JK6/action/replication_record"}},"created_at":"2026-06-09T02:08:47.839732+00:00","updated_at":"2026-06-09T02:08:47.839732+00:00"}