{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AM5LX225727U7KHXJMF5MKD63N","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":"8684e654c981bbec36d35c40399408e1986ce4a6660b428c7768eee60886543f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T09:08:36Z","title_canon_sha256":"b1f0bd9be2d21be103cd4cb8deb1b18b33fd27dbf11bcec26f4f9e1d76cffe41"},"schema_version":"1.0","source":{"id":"2411.14807","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14807","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14807v1","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14807","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"AM5LX225727U","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_16","alias_value":"AM5LX225727U7KHX","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_8","alias_value":"AM5LX225","created_at":"2026-07-05T09:39:12Z"}],"graph_snapshots":[{"event_id":"sha256:b2237548efa9245dd504dc152d0d58d4dafe2a8612ed71c1638a199c9a205fdb","target":"graph","created_at":"2026-07-05T09:39:12Z","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/2411.14807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring Expression Comprehension (REC) aims to identify a particular object in a scene by a natural language expression, and is an important topic in visual language understanding. State-of-the-art methods for this task are based on deep learning, which generally requires expensive and manually labeled annotations. Some works tackle the problem with limited-supervision learning or relying on Large Vision and Language Models. However, the development of techniques to synthesize labeled data is overlooked. In this paper, we propose a novel framework that generates artificial data for the REC t","authors_text":"Elena Izzo, Lamberto Ballan, Luca Parolari","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T09:08:36Z","title":"Harlequin: Color-driven Generation of Synthetic Data for Referring Expression Comprehension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14807","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":"sha256:71be0f41c01c44c02e7e0aaa64076bf855326bec95033d5074043b2f84f8e3b9","target":"record","created_at":"2026-07-05T09:39:12Z","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":"8684e654c981bbec36d35c40399408e1986ce4a6660b428c7768eee60886543f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T09:08:36Z","title_canon_sha256":"b1f0bd9be2d21be103cd4cb8deb1b18b33fd27dbf11bcec26f4f9e1d76cffe41"},"schema_version":"1.0","source":{"id":"2411.14807","kind":"arxiv","version":1}},"canonical_sha256":"033abbeb5dfebf4fa8f74b0bd6287edb56c6bceb2a847e5066aff4f04b1f12ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"033abbeb5dfebf4fa8f74b0bd6287edb56c6bceb2a847e5066aff4f04b1f12ba","first_computed_at":"2026-07-05T09:39:12.287556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:12.287556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xO1r9QuZTyGMefBKQEy8WDYoP8BDVj9iahRcEFcqwZ6aK6xm3IuojJ5wYjt6Of9kSgtauf7MzxNkqNYZEQXaAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:12.288026Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14807","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71be0f41c01c44c02e7e0aaa64076bf855326bec95033d5074043b2f84f8e3b9","sha256:b2237548efa9245dd504dc152d0d58d4dafe2a8612ed71c1638a199c9a205fdb"],"state_sha256":"c11e3bceaf48eb1a017852f4c57f9b8d23fa856fc8729991e824b359373aa980"}