{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CWFZIFX5223GCMCQ3T6B5DNHGC","short_pith_number":"pith:CWFZIFX5","schema_version":"1.0","canonical_sha256":"158b9416fdd6b6613050dcfc1e8da730825242a23bdba03c8a9ed126aba60d58","source":{"kind":"arxiv","id":"2305.02932","version":2},"attestation_state":"computed","paper":{"title":"Image Captioners Sometimes Tell More Than Images They See","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Honori Udo, Takafumi Koshinaka","submitted_at":"2023-05-04T15:32:41Z","abstract_excerpt":"Image captioning, a.k.a. \"image-to-text,\" which generates descriptive text from given images, has been rapidly developing throughout the era of deep learning. To what extent is the information in the original image preserved in the descriptive text generated by an image captioner? To answer that question, we have performed experiments involving the classification of images from descriptive text alone, without referring to the images at all, and compared results with those from standard image-based classifiers. We have evaluate several image captioning models with respect to a disaster image cl"},"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":"2305.02932","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T15:32:41Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"4e8015de2d7fe089f91cd165fdaee4ab794d79ca10306d2be9d7d0b123d32a46","abstract_canon_sha256":"ca89d387eda16104d2d47bf2f8b1a888ccd2b62f4f6e69cb25e3ca5e3bc9651a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:10.368700Z","signature_b64":"hYZJXU4J9imQ0Gg78g4FaL1QPOQz+/2zUBhgBCbb/bt3BSZY9WRx0q73RFj3Y0s5FCVIGtxT7KCJewO03nzeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"158b9416fdd6b6613050dcfc1e8da730825242a23bdba03c8a9ed126aba60d58","last_reissued_at":"2026-07-05T06:09:10.368207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:10.368207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Captioners Sometimes Tell More Than Images They See","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Honori Udo, Takafumi Koshinaka","submitted_at":"2023-05-04T15:32:41Z","abstract_excerpt":"Image captioning, a.k.a. \"image-to-text,\" which generates descriptive text from given images, has been rapidly developing throughout the era of deep learning. To what extent is the information in the original image preserved in the descriptive text generated by an image captioner? To answer that question, we have performed experiments involving the classification of images from descriptive text alone, without referring to the images at all, and compared results with those from standard image-based classifiers. We have evaluate several image captioning models with respect to a disaster image cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02932","kind":"arxiv","version":2},"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/2305.02932/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":"2305.02932","created_at":"2026-07-05T06:09:10.368266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.02932v2","created_at":"2026-07-05T06:09:10.368266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02932","created_at":"2026-07-05T06:09:10.368266+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWFZIFX5223G","created_at":"2026-07-05T06:09:10.368266+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWFZIFX5223GCMCQ","created_at":"2026-07-05T06:09:10.368266+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWFZIFX5","created_at":"2026-07-05T06:09:10.368266+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19944","citing_title":"Zero-shot Hazard Identification in Autonomous Driving: A Case Study on the COOOL Benchmark","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWFZIFX5223GCMCQ3T6B5DNHGC","json":"https://pith.science/pith/CWFZIFX5223GCMCQ3T6B5DNHGC.json","graph_json":"https://pith.science/api/pith-number/CWFZIFX5223GCMCQ3T6B5DNHGC/graph.json","events_json":"https://pith.science/api/pith-number/CWFZIFX5223GCMCQ3T6B5DNHGC/events.json","paper":"https://pith.science/paper/CWFZIFX5"},"agent_actions":{"view_html":"https://pith.science/pith/CWFZIFX5223GCMCQ3T6B5DNHGC","download_json":"https://pith.science/pith/CWFZIFX5223GCMCQ3T6B5DNHGC.json","view_paper":"https://pith.science/paper/CWFZIFX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.02932&json=true","fetch_graph":"https://pith.science/api/pith-number/CWFZIFX5223GCMCQ3T6B5DNHGC/graph.json","fetch_events":"https://pith.science/api/pith-number/CWFZIFX5223GCMCQ3T6B5DNHGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWFZIFX5223GCMCQ3T6B5DNHGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWFZIFX5223GCMCQ3T6B5DNHGC/action/storage_attestation","attest_author":"https://pith.science/pith/CWFZIFX5223GCMCQ3T6B5DNHGC/action/author_attestation","sign_citation":"https://pith.science/pith/CWFZIFX5223GCMCQ3T6B5DNHGC/action/citation_signature","submit_replication":"https://pith.science/pith/CWFZIFX5223GCMCQ3T6B5DNHGC/action/replication_record"}},"created_at":"2026-07-05T06:09:10.368266+00:00","updated_at":"2026-07-05T06:09:10.368266+00:00"}