{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZDK6QXNGELI6KA3RK4HS3NKDGT","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":"56b6457f0762e925d8901f4e6d2c907e8918220d31c5694ad2f5f2c6f59f0ab2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T15:36:10Z","title_canon_sha256":"f6e903e8f84a46fd124e92a42d4627b43f81b3d27dbbf668d5cc1fadc62a0631"},"schema_version":"1.0","source":{"id":"2608.11074","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11074","created_at":"2026-08-12T01:24:33Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11074v1","created_at":"2026-08-12T01:24:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11074","created_at":"2026-08-12T01:24:33Z"},{"alias_kind":"pith_short_12","alias_value":"ZDK6QXNGELI6","created_at":"2026-08-12T01:24:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZDK6QXNGELI6KA3R","created_at":"2026-08-12T01:24:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZDK6QXNG","created_at":"2026-08-12T01:24:33Z"}],"graph_snapshots":[{"event_id":"sha256:f91ab1e1c40b41434d4e7ec33172adec55d671eb87c4225452f4d880f9a17824","target":"graph","created_at":"2026-08-12T01:24:33Z","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/2608.11074/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating detailed image captions from Vision-Language Models (VLMs) requires going beyond surface-level semantic similarity. Reference-based metrics (e.g., CIDEr and SPICE) and LLM-as-scorer protocols struggle to verify dense factual claims, while existing QA-based alternatives generally offer lower probe density, narrower domain coverage, or no explicit alignment between individual questions and segmented image regions. We introduce CapProbe, a full-scene dense QA benchmark that turns detailed caption evaluation into region-aligned factual checking. Each image is decomposed into coarse sema","authors_text":"Borui Jiang, Han Shu, Mouxiao Huang, Qiangyu Yan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T15:36:10Z","title":"CapProbe: Evaluating Detailed Image Captions via Full-Scene Dense Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11074","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":"sha256:6798ff49e914501d52bd33a9a371dd3e7511f147a4823c4f9f21db5ccd01470d","target":"record","created_at":"2026-08-12T01:24:33Z","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":"56b6457f0762e925d8901f4e6d2c907e8918220d31c5694ad2f5f2c6f59f0ab2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T15:36:10Z","title_canon_sha256":"f6e903e8f84a46fd124e92a42d4627b43f81b3d27dbbf668d5cc1fadc62a0631"},"schema_version":"1.0","source":{"id":"2608.11074","kind":"arxiv","version":1}},"canonical_sha256":"c8d5e85da622d1e50371570f2db54334d20289a24805cdaeaf563326350696a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8d5e85da622d1e50371570f2db54334d20289a24805cdaeaf563326350696a3","first_computed_at":"2026-08-12T01:24:33.203237Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T01:24:33.203237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sXrq/PRFA4umSjOKm8sYli31ofiBIqBuYGL6HRdlId7y/qRXJlIl3rGk+esclFYrOuADLFVjtI+PbL65MpHTCQ==","signature_status":"signed_v1","signed_at":"2026-08-12T01:24:33.205031Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11074","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6798ff49e914501d52bd33a9a371dd3e7511f147a4823c4f9f21db5ccd01470d","sha256:f91ab1e1c40b41434d4e7ec33172adec55d671eb87c4225452f4d880f9a17824"],"state_sha256":"4febfa90c1a1fa288d97fcd54682740867374063db884301d90ce120b1d03a9e"}