{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WBHMEKX2WEW2NLIMBMTQIVD3BC","short_pith_number":"pith:WBHMEKX2","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"},"canonical_sha256":"b04ec22afab12da6ad0c0b2704547b08a5c940e46b14e66026321f8f707dd769","source":{"kind":"arxiv","id":"2607.28269","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28269","created_at":"2026-07-31T01:37:05Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28269v1","created_at":"2026-07-31T01:37:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28269","created_at":"2026-07-31T01:37:05Z"},{"alias_kind":"pith_short_12","alias_value":"WBHMEKX2WEW2","created_at":"2026-07-31T01:37:05Z"},{"alias_kind":"pith_short_16","alias_value":"WBHMEKX2WEW2NLIM","created_at":"2026-07-31T01:37:05Z"},{"alias_kind":"pith_short_8","alias_value":"WBHMEKX2","created_at":"2026-07-31T01:37:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WBHMEKX2WEW2NLIMBMTQIVD3BC","target":"record","payload":{"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"},"canonical_sha256":"b04ec22afab12da6ad0c0b2704547b08a5c940e46b14e66026321f8f707dd769","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"},"source_kind":"arxiv","source_id":"2607.28269","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:37:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+QF//S9kih1B/SumXlOqPLYgC4k1Lacy9K1n4Kjsckis53MvLhcrXgGYVEwP5G7QU0XIbzo+z7Nvk8MOP/5RAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T20:36:32.606032Z"},"content_sha256":"12e9b45efbb184aec67ff78e00a0466e76c97a7a1c5b68d9885bbedbe01d2285","schema_version":"1.0","event_id":"sha256:12e9b45efbb184aec67ff78e00a0466e76c97a7a1c5b68d9885bbedbe01d2285"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WBHMEKX2WEW2NLIMBMTQIVD3BC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:37:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kftuShn6toR4mYSXcbpWH6aGtdDnmJ3lwUww2M0dWLBzOmuXqkYr2+YPWHUI4Xx6PbWe6tpVU2SGlnQ9w3fxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T20:36:32.606553Z"},"content_sha256":"3a46ffa6ecd081293c517bdf36c0fd368a14ea4657d6ad3249eb48e908d0e6a9","schema_version":"1.0","event_id":"sha256:3a46ffa6ecd081293c517bdf36c0fd368a14ea4657d6ad3249eb48e908d0e6a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WBHMEKX2WEW2NLIMBMTQIVD3BC/bundle.json","state_url":"https://pith.science/pith/WBHMEKX2WEW2NLIMBMTQIVD3BC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WBHMEKX2WEW2NLIMBMTQIVD3BC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-02T20:36:32Z","links":{"resolver":"https://pith.science/pith/WBHMEKX2WEW2NLIMBMTQIVD3BC","bundle":"https://pith.science/pith/WBHMEKX2WEW2NLIMBMTQIVD3BC/bundle.json","state":"https://pith.science/pith/WBHMEKX2WEW2NLIMBMTQIVD3BC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WBHMEKX2WEW2NLIMBMTQIVD3BC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WBHMEKX2WEW2NLIMBMTQIVD3BC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"70032ffb4229bc7bb1c932ada7a2c2c5b98fedce16e0eef886bcecea08dca5d4","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T14:23:01Z","title_canon_sha256":"ea2fdc3f2eb4d680332a1dd74821fbbcf4a46d9dd0bc190718b923d936e4de31"},"schema_version":"1.0","source":{"id":"2607.28269","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28269","created_at":"2026-07-31T01:37:05Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28269v1","created_at":"2026-07-31T01:37:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28269","created_at":"2026-07-31T01:37:05Z"},{"alias_kind":"pith_short_12","alias_value":"WBHMEKX2WEW2","created_at":"2026-07-31T01:37:05Z"},{"alias_kind":"pith_short_16","alias_value":"WBHMEKX2WEW2NLIM","created_at":"2026-07-31T01:37:05Z"},{"alias_kind":"pith_short_8","alias_value":"WBHMEKX2","created_at":"2026-07-31T01:37:05Z"}],"graph_snapshots":[{"event_id":"sha256:3a46ffa6ecd081293c517bdf36c0fd368a14ea4657d6ad3249eb48e908d0e6a9","target":"graph","created_at":"2026-07-31T01:37:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.28269/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Adriano Mancini, Alessandro Galdelli, Lorenzo Severini, Simone Giano","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T14:23:01Z","title":"Theia: Large-Scale Multimodal Captioning and Automated Validation of the Incidents1M Dataset for Data-Free Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28269","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:12e9b45efbb184aec67ff78e00a0466e76c97a7a1c5b68d9885bbedbe01d2285","target":"record","created_at":"2026-07-31T01:37:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"70032ffb4229bc7bb1c932ada7a2c2c5b98fedce16e0eef886bcecea08dca5d4","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T14:23:01Z","title_canon_sha256":"ea2fdc3f2eb4d680332a1dd74821fbbcf4a46d9dd0bc190718b923d936e4de31"},"schema_version":"1.0","source":{"id":"2607.28269","kind":"arxiv","version":1}},"canonical_sha256":"b04ec22afab12da6ad0c0b2704547b08a5c940e46b14e66026321f8f707dd769","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b04ec22afab12da6ad0c0b2704547b08a5c940e46b14e66026321f8f707dd769","first_computed_at":"2026-07-31T01:37:05.396066Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:37:05.396066Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28269","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12e9b45efbb184aec67ff78e00a0466e76c97a7a1c5b68d9885bbedbe01d2285","sha256:3a46ffa6ecd081293c517bdf36c0fd368a14ea4657d6ad3249eb48e908d0e6a9"],"state_sha256":"7bbc7a737729bdac1c480ec43a2979a1dd6026bd49ae39a23c0478830d883c44"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jQkcr8I5uU14V73xydIU0GlmWCbXCEsfaLx237ocQeM5uziXaL1oFVP9ICnV7LxdqmQnv6lfZ6M/jqVCsXMwDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T20:36:32.610531Z","bundle_sha256":"9099357ba8c666a198887c744f74c69ce4036a6d94232bcfdef81c80833ca8c3"}}