{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KEIOOOETNYQFHWFCSPLSKURSZR","short_pith_number":"pith:KEIOOOET","schema_version":"1.0","canonical_sha256":"5110e738936e2053d8a293d7255232cc6fd67f94963f3191d59522d718b037e9","source":{"kind":"arxiv","id":"2608.02589","version":1},"attestation_state":"computed","paper":{"title":"CAPEval: A Decoupled Caption Evaluation across Understanding and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haochen Wang, Zhaoxiang Zhang, Zhipeng Liu","submitted_at":"2026-08-03T17:57:03Z","abstract_excerpt":"Captions serve as a primary supervision signal for both multimodal understanding and text-to-image generation. However, previous evaluations treat the caption quality as a single scalar objective, which conflates two distinct properties: (1) how much visual information a caption covers and (2) how reliably the image supports its stated claims. To this end, we design a decoupled caption evaluation benchmark, CAPEval (Coverage And Precision Evaluation), with human-written ground-truth captions and human-verified atomic checklist items. Specifically, CAPEval decomposes caption quality into Covera"},"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":"2608.02589","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T17:57:03Z","cross_cats_sorted":[],"title_canon_sha256":"17a77b84f9fc5bd61306e8b2d816bb8e6e7119eea39258835eb386e2a6f8f7f6","abstract_canon_sha256":"3acf6bc654cc6116ac6bec84651fb98bcbf4cd68ec99b6333bd54499d1be3749"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:44:19.623329Z","signature_b64":"Y6Mb4uqfkZj6llDvQG8xOSF6dcHj1hT7nGD2ToLmUzJj+QALQS19HY4AJMfwt2h+KzzySGNvkc+Tb4IAliX7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5110e738936e2053d8a293d7255232cc6fd67f94963f3191d59522d718b037e9","last_reissued_at":"2026-08-04T02:44:19.621096Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:44:19.621096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAPEval: A Decoupled Caption Evaluation across Understanding and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haochen Wang, Zhaoxiang Zhang, Zhipeng Liu","submitted_at":"2026-08-03T17:57:03Z","abstract_excerpt":"Captions serve as a primary supervision signal for both multimodal understanding and text-to-image generation. However, previous evaluations treat the caption quality as a single scalar objective, which conflates two distinct properties: (1) how much visual information a caption covers and (2) how reliably the image supports its stated claims. To this end, we design a decoupled caption evaluation benchmark, CAPEval (Coverage And Precision Evaluation), with human-written ground-truth captions and human-verified atomic checklist items. Specifically, CAPEval decomposes caption quality into Covera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02589","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/2608.02589/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":"2608.02589","created_at":"2026-08-04T02:44:19.623391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.02589v1","created_at":"2026-08-04T02:44:19.623391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02589","created_at":"2026-08-04T02:44:19.623391+00:00"},{"alias_kind":"pith_short_12","alias_value":"KEIOOOETNYQF","created_at":"2026-08-04T02:44:19.623391+00:00"},{"alias_kind":"pith_short_16","alias_value":"KEIOOOETNYQFHWFC","created_at":"2026-08-04T02:44:19.623391+00:00"},{"alias_kind":"pith_short_8","alias_value":"KEIOOOET","created_at":"2026-08-04T02:44:19.623391+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/KEIOOOETNYQFHWFCSPLSKURSZR","json":"https://pith.science/pith/KEIOOOETNYQFHWFCSPLSKURSZR.json","graph_json":"https://pith.science/api/pith-number/KEIOOOETNYQFHWFCSPLSKURSZR/graph.json","events_json":"https://pith.science/api/pith-number/KEIOOOETNYQFHWFCSPLSKURSZR/events.json","paper":"https://pith.science/paper/KEIOOOET"},"agent_actions":{"view_html":"https://pith.science/pith/KEIOOOETNYQFHWFCSPLSKURSZR","download_json":"https://pith.science/pith/KEIOOOETNYQFHWFCSPLSKURSZR.json","view_paper":"https://pith.science/paper/KEIOOOET","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.02589&json=true","fetch_graph":"https://pith.science/api/pith-number/KEIOOOETNYQFHWFCSPLSKURSZR/graph.json","fetch_events":"https://pith.science/api/pith-number/KEIOOOETNYQFHWFCSPLSKURSZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KEIOOOETNYQFHWFCSPLSKURSZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KEIOOOETNYQFHWFCSPLSKURSZR/action/storage_attestation","attest_author":"https://pith.science/pith/KEIOOOETNYQFHWFCSPLSKURSZR/action/author_attestation","sign_citation":"https://pith.science/pith/KEIOOOETNYQFHWFCSPLSKURSZR/action/citation_signature","submit_replication":"https://pith.science/pith/KEIOOOETNYQFHWFCSPLSKURSZR/action/replication_record"}},"created_at":"2026-08-04T02:44:19.623391+00:00","updated_at":"2026-08-04T02:44:19.623391+00:00"}