{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AM5LX225727U7KHXJMF5MKD63N","short_pith_number":"pith:AM5LX225","schema_version":"1.0","canonical_sha256":"033abbeb5dfebf4fa8f74b0bd6287edb56c6bceb2a847e5066aff4f04b1f12ba","source":{"kind":"arxiv","id":"2411.14807","version":1},"attestation_state":"computed","paper":{"title":"Harlequin: Color-driven Generation of Synthetic Data for Referring Expression Comprehension","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Elena Izzo, Lamberto Ballan, Luca Parolari","submitted_at":"2024-11-22T09:08:36Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.14807","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T09:08:36Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b1f0bd9be2d21be103cd4cb8deb1b18b33fd27dbf11bcec26f4f9e1d76cffe41","abstract_canon_sha256":"8684e654c981bbec36d35c40399408e1986ce4a6660b428c7768eee60886543f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:12.288026Z","signature_b64":"xO1r9QuZTyGMefBKQEy8WDYoP8BDVj9iahRcEFcqwZ6aK6xm3IuojJ5wYjt6Of9kSgtauf7MzxNkqNYZEQXaAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"033abbeb5dfebf4fa8f74b0bd6287edb56c6bceb2a847e5066aff4f04b1f12ba","last_reissued_at":"2026-07-05T09:39:12.287556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:12.287556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harlequin: Color-driven Generation of Synthetic Data for Referring Expression Comprehension","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Elena Izzo, Lamberto Ballan, Luca Parolari","submitted_at":"2024-11-22T09:08:36Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14807","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.14807/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.14807","created_at":"2026-07-05T09:39:12.287633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14807v1","created_at":"2026-07-05T09:39:12.287633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14807","created_at":"2026-07-05T09:39:12.287633+00:00"},{"alias_kind":"pith_short_12","alias_value":"AM5LX225727U","created_at":"2026-07-05T09:39:12.287633+00:00"},{"alias_kind":"pith_short_16","alias_value":"AM5LX225727U7KHX","created_at":"2026-07-05T09:39:12.287633+00:00"},{"alias_kind":"pith_short_8","alias_value":"AM5LX225","created_at":"2026-07-05T09:39:12.287633+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AM5LX225727U7KHXJMF5MKD63N","json":"https://pith.science/pith/AM5LX225727U7KHXJMF5MKD63N.json","graph_json":"https://pith.science/api/pith-number/AM5LX225727U7KHXJMF5MKD63N/graph.json","events_json":"https://pith.science/api/pith-number/AM5LX225727U7KHXJMF5MKD63N/events.json","paper":"https://pith.science/paper/AM5LX225"},"agent_actions":{"view_html":"https://pith.science/pith/AM5LX225727U7KHXJMF5MKD63N","download_json":"https://pith.science/pith/AM5LX225727U7KHXJMF5MKD63N.json","view_paper":"https://pith.science/paper/AM5LX225","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14807&json=true","fetch_graph":"https://pith.science/api/pith-number/AM5LX225727U7KHXJMF5MKD63N/graph.json","fetch_events":"https://pith.science/api/pith-number/AM5LX225727U7KHXJMF5MKD63N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AM5LX225727U7KHXJMF5MKD63N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AM5LX225727U7KHXJMF5MKD63N/action/storage_attestation","attest_author":"https://pith.science/pith/AM5LX225727U7KHXJMF5MKD63N/action/author_attestation","sign_citation":"https://pith.science/pith/AM5LX225727U7KHXJMF5MKD63N/action/citation_signature","submit_replication":"https://pith.science/pith/AM5LX225727U7KHXJMF5MKD63N/action/replication_record"}},"created_at":"2026-07-05T09:39:12.287633+00:00","updated_at":"2026-07-05T09:39:12.287633+00:00"}