{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:COYYJEU42LSBBJPNCXQH22AQ3O","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":"0ac0619e4f45b3b70b1b83d6a7b13f0cfa0c95a99f5d2ed5582b6367b4651672","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-19T13:39:09Z","title_canon_sha256":"d7ca0b8dd83455ed1cd07a623aee7daa9c4586f108615eca3c2b5a86f0f09a93"},"schema_version":"1.0","source":{"id":"2606.21419","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21419","created_at":"2026-06-23T01:13:09Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21419v1","created_at":"2026-06-23T01:13:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21419","created_at":"2026-06-23T01:13:09Z"},{"alias_kind":"pith_short_12","alias_value":"COYYJEU42LSB","created_at":"2026-06-23T01:13:09Z"},{"alias_kind":"pith_short_16","alias_value":"COYYJEU42LSBBJPN","created_at":"2026-06-23T01:13:09Z"},{"alias_kind":"pith_short_8","alias_value":"COYYJEU4","created_at":"2026-06-23T01:13:09Z"}],"graph_snapshots":[{"event_id":"sha256:6c992176ed4fe263dfd817f3f212ca02f9f8077adb0d9d8ebc6b5bbb82b72b14","target":"graph","created_at":"2026-06-23T01:13:09Z","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/2606.21419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent progress in Vision-Language Models (VLMs), mixed-domain image-caption datasets for both general-purpose and CCTV-based video surveillance systems remain limited. To address this gap, we introduce a large-scale multimodal dataset comprising 141,364 images, 981,947 image-level captions, 1,742,264 region-level captions, and 1,391,779 bounding box annotations. Each image is associated with an average of seven image-level captions describing different aspects of the overall scene, as well as seven region-level captions for each annotated bounding box. These complementary caption type","authors_text":"Arlindo Luciano Tulumba Roberto, Hyungjoon Kim","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-19T13:39:09Z","title":"MIRCaps: A Large-Scale Mixed-Domain Dataset with Image-Level and Region-Level Captions for Fine-Grained Vision-Language Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21419","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:d95fd09d0884d35298081e0e13f29582db6968aa751859d49f9cb9d5d7b43953","target":"record","created_at":"2026-06-23T01:13:09Z","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":"0ac0619e4f45b3b70b1b83d6a7b13f0cfa0c95a99f5d2ed5582b6367b4651672","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-19T13:39:09Z","title_canon_sha256":"d7ca0b8dd83455ed1cd07a623aee7daa9c4586f108615eca3c2b5a86f0f09a93"},"schema_version":"1.0","source":{"id":"2606.21419","kind":"arxiv","version":1}},"canonical_sha256":"13b184929cd2e410a5ed15e07d6810dbb32279b7b373c7448abb316e2cde109c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13b184929cd2e410a5ed15e07d6810dbb32279b7b373c7448abb316e2cde109c","first_computed_at":"2026-06-23T01:13:09.666374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:13:09.666374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DQ2IpmmM7eoCYxm/x/S8suHLtnJrGT1R3xSKKViBuPg/a42EMkUcFZ1RrMuj5ZbedLcrLOfPLPQ77aoNmtyZBw==","signature_status":"signed_v1","signed_at":"2026-06-23T01:13:09.666818Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21419","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d95fd09d0884d35298081e0e13f29582db6968aa751859d49f9cb9d5d7b43953","sha256:6c992176ed4fe263dfd817f3f212ca02f9f8077adb0d9d8ebc6b5bbb82b72b14"],"state_sha256":"d9687e0496fd7806ae900f23264a914927726df18016bf8a42257c4f75b7e170"}