{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BLLYWUK4J5GNZBHJKKKUA7WULW","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":"99c4bcb45fe29503c332a218d14664f19a323adaa465134dc2e8272a6a04ce31","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-19T17:31:59Z","title_canon_sha256":"8fd2b75a12303423ec2e0c5d3a0a607f2a5ecedc4a1c1587292cf98ff7d823b7"},"schema_version":"1.0","source":{"id":"2502.13898","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13898","created_at":"2026-07-05T11:27:24Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13898v3","created_at":"2026-07-05T11:27:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13898","created_at":"2026-07-05T11:27:24Z"},{"alias_kind":"pith_short_12","alias_value":"BLLYWUK4J5GN","created_at":"2026-07-05T11:27:24Z"},{"alias_kind":"pith_short_16","alias_value":"BLLYWUK4J5GNZBHJ","created_at":"2026-07-05T11:27:24Z"},{"alias_kind":"pith_short_8","alias_value":"BLLYWUK4","created_at":"2026-07-05T11:27:24Z"}],"graph_snapshots":[{"event_id":"sha256:df4e49d4acc8ceb46fc9290af9aa198c19b218c3daeaea6d9f311670060d0370","target":"graph","created_at":"2026-07-05T11:27:24Z","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/2502.13898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current image captioning systems lack the ability to link descriptive text to specific visual elements, making their outputs difficult to verify. While recent approaches offer some grounding capabilities, they cannot track object identities across multiple references or ground both actions and objects simultaneously. We propose a novel ID-based grounding system that enables consistent object reference tracking and action-object linking. We present GroundCap, a dataset containing 52,016 images from 77 movies, with 344 human-annotated and 52,016 automatically generated captions. Each caption is ","authors_text":"Daniel A. P. Oliveira, David Martins de Matos, Louren\\c{c}o Teodoro","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-19T17:31:59Z","title":"GroundCap: A Visually Grounded Image Captioning Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13898","kind":"arxiv","version":3},"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":"sha256:56234881472b304a90e7376d55515747e4aded6676d3fbab0d678d47474e41a8","target":"record","created_at":"2026-07-05T11:27:24Z","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":"99c4bcb45fe29503c332a218d14664f19a323adaa465134dc2e8272a6a04ce31","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-19T17:31:59Z","title_canon_sha256":"8fd2b75a12303423ec2e0c5d3a0a607f2a5ecedc4a1c1587292cf98ff7d823b7"},"schema_version":"1.0","source":{"id":"2502.13898","kind":"arxiv","version":3}},"canonical_sha256":"0ad78b515c4f4cdc84e95295407ed45d9d36a03772bfbdf7b24acee230161008","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ad78b515c4f4cdc84e95295407ed45d9d36a03772bfbdf7b24acee230161008","first_computed_at":"2026-07-05T11:27:24.213216Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:24.213216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8XuW2jvcIIvnhX6Hi7+5WkwCz8Kbc7diYk0hz0KXjhPH3HpKIWwvr4aMyA/KdV4LaG6L7hA9+byAWvBTYhKYAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:24.213726Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.13898","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56234881472b304a90e7376d55515747e4aded6676d3fbab0d678d47474e41a8","sha256:df4e49d4acc8ceb46fc9290af9aa198c19b218c3daeaea6d9f311670060d0370"],"state_sha256":"8ec7d0bbef4e87f400925231218f80ddf18673d85910073e67eadd93474bf623"}