{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LYKBEJU2Q434PI4LT3DTLWKLIY","short_pith_number":"pith:LYKBEJU2","schema_version":"1.0","canonical_sha256":"5e1412269a8737c7a38b9ec735d94b460ca92e3c6eb48385570f2e2d48e5de56","source":{"kind":"arxiv","id":"2607.23235","version":1},"attestation_state":"computed","paper":{"title":"A Reconstruction-Based Framework for Caption Evaluation Beyond Reference Captions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianqiang Huang, Jiaxin Qi, Kaihua Tang, Yuhua Zheng, Zhijiang Tang","submitted_at":"2026-07-25T14:41:34Z","abstract_excerpt":"Image captioning is a primary task in vision--language research, yet assessing how faithfully a caption preserves image semantics without relying on reference captions remains unsettled. Prevailing evaluations rely on human-annotated references, whose content reflects annotator intent and captioning proficiency. In this paper, we study a reconstruction-based principle for caption evaluation: a caption is as good as its capacity to enable reconstruction of the original image. However, because captioning inherently compresses visual information, it is impossible to recover all details, and pixel"},"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":"2607.23235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-25T14:41:34Z","cross_cats_sorted":[],"title_canon_sha256":"89ae38931bb448217b7dc29788ce82f28e98170e3d59c1b297d0f8e0fef2339a","abstract_canon_sha256":"430fd1f5de0936b8d844bf0ebd50104044eae56e32a132ec789c1fb0fd82848d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:43.226949Z","signature_b64":"+4hOLio+HOKiobrb9g39ML2WRen2RVI3lJ8o9x8dd/2E2Eb8xiNlGDfd8/YW07M1nn6vkDvnJqlmewlStAknAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e1412269a8737c7a38b9ec735d94b460ca92e3c6eb48385570f2e2d48e5de56","last_reissued_at":"2026-07-28T01:22:43.226159Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:43.226159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Reconstruction-Based Framework for Caption Evaluation Beyond Reference Captions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianqiang Huang, Jiaxin Qi, Kaihua Tang, Yuhua Zheng, Zhijiang Tang","submitted_at":"2026-07-25T14:41:34Z","abstract_excerpt":"Image captioning is a primary task in vision--language research, yet assessing how faithfully a caption preserves image semantics without relying on reference captions remains unsettled. Prevailing evaluations rely on human-annotated references, whose content reflects annotator intent and captioning proficiency. In this paper, we study a reconstruction-based principle for caption evaluation: a caption is as good as its capacity to enable reconstruction of the original image. However, because captioning inherently compresses visual information, it is impossible to recover all details, and pixel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23235","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/2607.23235/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":"2607.23235","created_at":"2026-07-28T01:22:43.226572+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23235v1","created_at":"2026-07-28T01:22:43.226572+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23235","created_at":"2026-07-28T01:22:43.226572+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYKBEJU2Q434","created_at":"2026-07-28T01:22:43.226572+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYKBEJU2Q434PI4L","created_at":"2026-07-28T01:22:43.226572+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYKBEJU2","created_at":"2026-07-28T01:22:43.226572+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/LYKBEJU2Q434PI4LT3DTLWKLIY","json":"https://pith.science/pith/LYKBEJU2Q434PI4LT3DTLWKLIY.json","graph_json":"https://pith.science/api/pith-number/LYKBEJU2Q434PI4LT3DTLWKLIY/graph.json","events_json":"https://pith.science/api/pith-number/LYKBEJU2Q434PI4LT3DTLWKLIY/events.json","paper":"https://pith.science/paper/LYKBEJU2"},"agent_actions":{"view_html":"https://pith.science/pith/LYKBEJU2Q434PI4LT3DTLWKLIY","download_json":"https://pith.science/pith/LYKBEJU2Q434PI4LT3DTLWKLIY.json","view_paper":"https://pith.science/paper/LYKBEJU2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23235&json=true","fetch_graph":"https://pith.science/api/pith-number/LYKBEJU2Q434PI4LT3DTLWKLIY/graph.json","fetch_events":"https://pith.science/api/pith-number/LYKBEJU2Q434PI4LT3DTLWKLIY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYKBEJU2Q434PI4LT3DTLWKLIY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYKBEJU2Q434PI4LT3DTLWKLIY/action/storage_attestation","attest_author":"https://pith.science/pith/LYKBEJU2Q434PI4LT3DTLWKLIY/action/author_attestation","sign_citation":"https://pith.science/pith/LYKBEJU2Q434PI4LT3DTLWKLIY/action/citation_signature","submit_replication":"https://pith.science/pith/LYKBEJU2Q434PI4LT3DTLWKLIY/action/replication_record"}},"created_at":"2026-07-28T01:22:43.226572+00:00","updated_at":"2026-07-28T01:22:43.226572+00:00"}