{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WBHMEKX2WEW2NLIMBMTQIVD3BC","short_pith_number":"pith:WBHMEKX2","schema_version":"1.0","canonical_sha256":"b04ec22afab12da6ad0c0b2704547b08a5c940e46b14e66026321f8f707dd769","source":{"kind":"arxiv","id":"2607.28269","version":1},"attestation_state":"computed","paper":{"title":"Theia: Large-Scale Multimodal Captioning and Automated Validation of the Incidents1M Dataset for Data-Free Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Adriano Mancini, Alessandro Galdelli, Lorenzo Severini, Simone Giano","submitted_at":"2026-07-30T14:23:01Z","abstract_excerpt":"The deployment of Vision-Language Models (VLMs) in critical domains like disaster management requires high-quality multimodal datasets, especially for transferring knowledge via Data-Free Knowledge Distillation (DFKD). However, existing datasets in this domain either entirely lack descriptive text, such as Incidents1M, or suffer from severe text-image semantic misalignment, such as CrisisMMD. In this work, we present a novel methodology to construct and automatically validate a large-scale multimodal dataset for disaster response. Starting from the vision-only Incidents1M, we successfully reco"},"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":"2607.28269","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T14:23:01Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"ea2fdc3f2eb4d680332a1dd74821fbbcf4a46d9dd0bc190718b923d936e4de31","abstract_canon_sha256":"70032ffb4229bc7bb1c932ada7a2c2c5b98fedce16e0eef886bcecea08dca5d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b04ec22afab12da6ad0c0b2704547b08a5c940e46b14e66026321f8f707dd769","last_reissued_at":"2026-07-31T01:37:05.396066Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:37:05.396066Z"},"graph_snapshot":{"paper":{"title":"Theia: Large-Scale Multimodal Captioning and Automated Validation of the Incidents1M Dataset for Data-Free Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Adriano Mancini, Alessandro Galdelli, Lorenzo Severini, Simone Giano","submitted_at":"2026-07-30T14:23:01Z","abstract_excerpt":"The deployment of Vision-Language Models (VLMs) in critical domains like disaster management requires high-quality multimodal datasets, especially for transferring knowledge via Data-Free Knowledge Distillation (DFKD). However, existing datasets in this domain either entirely lack descriptive text, such as Incidents1M, or suffer from severe text-image semantic misalignment, such as CrisisMMD. In this work, we present a novel methodology to construct and automatically validate a large-scale multimodal dataset for disaster response. Starting from the vision-only Incidents1M, we successfully reco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28269","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/2607.28269/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":"2607.28269","created_at":"2026-07-31T01:37:05.399231+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28269v1","created_at":"2026-07-31T01:37:05.399231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28269","created_at":"2026-07-31T01:37:05.399231+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBHMEKX2WEW2","created_at":"2026-07-31T01:37:05.399231+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBHMEKX2WEW2NLIM","created_at":"2026-07-31T01:37:05.399231+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBHMEKX2","created_at":"2026-07-31T01:37:05.399231+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/WBHMEKX2WEW2NLIMBMTQIVD3BC","json":"https://pith.science/pith/WBHMEKX2WEW2NLIMBMTQIVD3BC.json","graph_json":"https://pith.science/api/pith-number/WBHMEKX2WEW2NLIMBMTQIVD3BC/graph.json","events_json":"https://pith.science/api/pith-number/WBHMEKX2WEW2NLIMBMTQIVD3BC/events.json","paper":"https://pith.science/paper/WBHMEKX2"},"agent_actions":{"view_html":"https://pith.science/pith/WBHMEKX2WEW2NLIMBMTQIVD3BC","download_json":"https://pith.science/pith/WBHMEKX2WEW2NLIMBMTQIVD3BC.json","view_paper":"https://pith.science/paper/WBHMEKX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28269&json=true","fetch_graph":"https://pith.science/api/pith-number/WBHMEKX2WEW2NLIMBMTQIVD3BC/graph.json","fetch_events":"https://pith.science/api/pith-number/WBHMEKX2WEW2NLIMBMTQIVD3BC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBHMEKX2WEW2NLIMBMTQIVD3BC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBHMEKX2WEW2NLIMBMTQIVD3BC/action/storage_attestation","attest_author":"https://pith.science/pith/WBHMEKX2WEW2NLIMBMTQIVD3BC/action/author_attestation","sign_citation":"https://pith.science/pith/WBHMEKX2WEW2NLIMBMTQIVD3BC/action/citation_signature","submit_replication":"https://pith.science/pith/WBHMEKX2WEW2NLIMBMTQIVD3BC/action/replication_record"}},"created_at":"2026-07-31T01:37:05.399231+00:00","updated_at":"2026-07-31T01:37:05.399231+00:00"}