{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KEIOOOETNYQFHWFCSPLSKURSZR","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":"3acf6bc654cc6116ac6bec84651fb98bcbf4cd68ec99b6333bd54499d1be3749","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T17:57:03Z","title_canon_sha256":"17a77b84f9fc5bd61306e8b2d816bb8e6e7119eea39258835eb386e2a6f8f7f6"},"schema_version":"1.0","source":{"id":"2608.02589","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02589","created_at":"2026-08-04T02:44:19Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02589v1","created_at":"2026-08-04T02:44:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02589","created_at":"2026-08-04T02:44:19Z"},{"alias_kind":"pith_short_12","alias_value":"KEIOOOETNYQF","created_at":"2026-08-04T02:44:19Z"},{"alias_kind":"pith_short_16","alias_value":"KEIOOOETNYQFHWFC","created_at":"2026-08-04T02:44:19Z"},{"alias_kind":"pith_short_8","alias_value":"KEIOOOET","created_at":"2026-08-04T02:44:19Z"}],"graph_snapshots":[{"event_id":"sha256:b85ddebcd497f0b91c6a56e832840b7f92844def876603af6ac391f83dda4768","target":"graph","created_at":"2026-08-04T02:44:19Z","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/2608.02589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haochen Wang, Zhaoxiang Zhang, Zhipeng Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T17:57:03Z","title":"CAPEval: A Decoupled Caption Evaluation across Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02589","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":"sha256:2e69deaca65e5108528285b7b3d43681395c05b2b7bb19dbc1d8eb607aeaf6ee","target":"record","created_at":"2026-08-04T02:44:19Z","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":"3acf6bc654cc6116ac6bec84651fb98bcbf4cd68ec99b6333bd54499d1be3749","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T17:57:03Z","title_canon_sha256":"17a77b84f9fc5bd61306e8b2d816bb8e6e7119eea39258835eb386e2a6f8f7f6"},"schema_version":"1.0","source":{"id":"2608.02589","kind":"arxiv","version":1}},"canonical_sha256":"5110e738936e2053d8a293d7255232cc6fd67f94963f3191d59522d718b037e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5110e738936e2053d8a293d7255232cc6fd67f94963f3191d59522d718b037e9","first_computed_at":"2026-08-04T02:44:19.621096Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:44:19.621096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y6Mb4uqfkZj6llDvQG8xOSF6dcHj1hT7nGD2ToLmUzJj+QALQS19HY4AJMfwt2h+KzzySGNvkc+Tb4IAliX7BQ==","signature_status":"signed_v1","signed_at":"2026-08-04T02:44:19.623329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02589","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e69deaca65e5108528285b7b3d43681395c05b2b7bb19dbc1d8eb607aeaf6ee","sha256:b85ddebcd497f0b91c6a56e832840b7f92844def876603af6ac391f83dda4768"],"state_sha256":"3e347bac7b48dad4e48f43c12681feb36aa272b5b6f39e2c8f008e18bad5c975"}