{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KIL4ZU5VVXDWSRWTJDW3F52JML","short_pith_number":"pith:KIL4ZU5V","schema_version":"1.0","canonical_sha256":"5217ccd3b5adc76946d348edb2f74962e7c64c90be97c230af96c63dd087639e","source":{"kind":"arxiv","id":"2405.00485","version":3},"attestation_state":"computed","paper":{"title":"What Makes for Good Image Captions?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Delong Chen, Etsuko Ishii, Ho Shu Chan, Pascale Fung, Samuel Cahyawijaya, Yejin Bang","submitted_at":"2024-05-01T12:49:57Z","abstract_excerpt":"This paper establishes a formal information-theoretic framework for image captioning, conceptualizing captions as compressed linguistic representations that selectively encode semantic units in images. Our framework posits that good image captions should balance three key aspects: informationally sufficient, minimally redundant, and readily comprehensible by humans. By formulating these aspects as quantitative measures with adjustable weights, our framework provides a flexible foundation for analyzing and optimizing image captioning systems across diverse task requirements. To demonstrate its "},"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":"2405.00485","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-01T12:49:57Z","cross_cats_sorted":[],"title_canon_sha256":"47d9601191ecdfc50c342e209a27c0365a3d31e0574a2b9370ae045d74f747e4","abstract_canon_sha256":"49a1b780395aea270907b1ae360dfee2c01d5470b1446ca0d2788a52475786ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:42.972610Z","signature_b64":"lTKTaBImz2B2/ncZ1pVTWO1pRXwf3z93zcD5nieDrXYh7i7jxlVfySqQwFE0y3S6vlSyMQp+cxlSP3DmsvONCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5217ccd3b5adc76946d348edb2f74962e7c64c90be97c230af96c63dd087639e","last_reissued_at":"2026-07-05T11:56:42.972125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:42.972125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Makes for Good Image Captions?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Delong Chen, Etsuko Ishii, Ho Shu Chan, Pascale Fung, Samuel Cahyawijaya, Yejin Bang","submitted_at":"2024-05-01T12:49:57Z","abstract_excerpt":"This paper establishes a formal information-theoretic framework for image captioning, conceptualizing captions as compressed linguistic representations that selectively encode semantic units in images. Our framework posits that good image captions should balance three key aspects: informationally sufficient, minimally redundant, and readily comprehensible by humans. By formulating these aspects as quantitative measures with adjustable weights, our framework provides a flexible foundation for analyzing and optimizing image captioning systems across diverse task requirements. To demonstrate its "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00485","kind":"arxiv","version":3},"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/2405.00485/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":"2405.00485","created_at":"2026-07-05T11:56:42.972183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.00485v3","created_at":"2026-07-05T11:56:42.972183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00485","created_at":"2026-07-05T11:56:42.972183+00:00"},{"alias_kind":"pith_short_12","alias_value":"KIL4ZU5VVXDW","created_at":"2026-07-05T11:56:42.972183+00:00"},{"alias_kind":"pith_short_16","alias_value":"KIL4ZU5VVXDWSRWT","created_at":"2026-07-05T11:56:42.972183+00:00"},{"alias_kind":"pith_short_8","alias_value":"KIL4ZU5V","created_at":"2026-07-05T11:56:42.972183+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22855","citing_title":"Evaluating Remote Sensing Image Captions Beyond Metric Biases","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KIL4ZU5VVXDWSRWTJDW3F52JML","json":"https://pith.science/pith/KIL4ZU5VVXDWSRWTJDW3F52JML.json","graph_json":"https://pith.science/api/pith-number/KIL4ZU5VVXDWSRWTJDW3F52JML/graph.json","events_json":"https://pith.science/api/pith-number/KIL4ZU5VVXDWSRWTJDW3F52JML/events.json","paper":"https://pith.science/paper/KIL4ZU5V"},"agent_actions":{"view_html":"https://pith.science/pith/KIL4ZU5VVXDWSRWTJDW3F52JML","download_json":"https://pith.science/pith/KIL4ZU5VVXDWSRWTJDW3F52JML.json","view_paper":"https://pith.science/paper/KIL4ZU5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.00485&json=true","fetch_graph":"https://pith.science/api/pith-number/KIL4ZU5VVXDWSRWTJDW3F52JML/graph.json","fetch_events":"https://pith.science/api/pith-number/KIL4ZU5VVXDWSRWTJDW3F52JML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KIL4ZU5VVXDWSRWTJDW3F52JML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KIL4ZU5VVXDWSRWTJDW3F52JML/action/storage_attestation","attest_author":"https://pith.science/pith/KIL4ZU5VVXDWSRWTJDW3F52JML/action/author_attestation","sign_citation":"https://pith.science/pith/KIL4ZU5VVXDWSRWTJDW3F52JML/action/citation_signature","submit_replication":"https://pith.science/pith/KIL4ZU5VVXDWSRWTJDW3F52JML/action/replication_record"}},"created_at":"2026-07-05T11:56:42.972183+00:00","updated_at":"2026-07-05T11:56:42.972183+00:00"}