{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KQD5CV6X6PJHVG2VR24ORZIB6Y","short_pith_number":"pith:KQD5CV6X","schema_version":"1.0","canonical_sha256":"5407d157d7f3d27a9b558eb8e8e501f61de8598e167a51bd544abba2f65b08db","source":{"kind":"arxiv","id":"2506.15903","version":1},"attestation_state":"computed","paper":{"title":"VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Josef Kucha\\v{r}, Marek Kadl\\v{c}\\'ik, Michal Spiegel, Michal \\v{S}tef\\'anik","submitted_at":"2025-06-18T22:17:30Z","abstract_excerpt":"We introduce a large-scale dataset for instruction-guided vector image editing, consisting of over 270,000 pairs of SVG images paired with natural language edit instructions. Our dataset enables training and evaluation of models that modify vector graphics based on textual commands. We describe the data collection process, including image pairing via CLIP similarity and instruction generation with vision-language models. Initial experiments with state-of-the-art large language models reveal that current methods struggle to produce accurate and valid edits, underscoring the challenge of this ta"},"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":"2506.15903","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T22:17:30Z","cross_cats_sorted":[],"title_canon_sha256":"bd71f891d11157d4c95e7162dcfae468b99c3054e1bbe0d475a9b1fefd65098c","abstract_canon_sha256":"1f6f1a9a2d2ce8fad554e81995e1057de3ffe5bb38b917fe67175db15b075231"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:26.200930Z","signature_b64":"ni3gZvlNtMFUxiJVMol8kFXyUorG2QiMsXK7tsRxMLMJzQp4RRUqCTmm1rtoKt63NG06Mj7CvhU/ylVtLwS+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5407d157d7f3d27a9b558eb8e8e501f61de8598e167a51bd544abba2f65b08db","last_reissued_at":"2026-07-05T11:24:26.200451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:26.200451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Josef Kucha\\v{r}, Marek Kadl\\v{c}\\'ik, Michal Spiegel, Michal \\v{S}tef\\'anik","submitted_at":"2025-06-18T22:17:30Z","abstract_excerpt":"We introduce a large-scale dataset for instruction-guided vector image editing, consisting of over 270,000 pairs of SVG images paired with natural language edit instructions. Our dataset enables training and evaluation of models that modify vector graphics based on textual commands. We describe the data collection process, including image pairing via CLIP similarity and instruction generation with vision-language models. Initial experiments with state-of-the-art large language models reveal that current methods struggle to produce accurate and valid edits, underscoring the challenge of this ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15903","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/2506.15903/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":"2506.15903","created_at":"2026-07-05T11:24:26.200509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15903v1","created_at":"2026-07-05T11:24:26.200509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15903","created_at":"2026-07-05T11:24:26.200509+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQD5CV6X6PJH","created_at":"2026-07-05T11:24:26.200509+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQD5CV6X6PJHVG2V","created_at":"2026-07-05T11:24:26.200509+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQD5CV6X","created_at":"2026-07-05T11:24:26.200509+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31278","citing_title":"Editing Everything Everywhere All at Once","ref_index":124,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KQD5CV6X6PJHVG2VR24ORZIB6Y","json":"https://pith.science/pith/KQD5CV6X6PJHVG2VR24ORZIB6Y.json","graph_json":"https://pith.science/api/pith-number/KQD5CV6X6PJHVG2VR24ORZIB6Y/graph.json","events_json":"https://pith.science/api/pith-number/KQD5CV6X6PJHVG2VR24ORZIB6Y/events.json","paper":"https://pith.science/paper/KQD5CV6X"},"agent_actions":{"view_html":"https://pith.science/pith/KQD5CV6X6PJHVG2VR24ORZIB6Y","download_json":"https://pith.science/pith/KQD5CV6X6PJHVG2VR24ORZIB6Y.json","view_paper":"https://pith.science/paper/KQD5CV6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15903&json=true","fetch_graph":"https://pith.science/api/pith-number/KQD5CV6X6PJHVG2VR24ORZIB6Y/graph.json","fetch_events":"https://pith.science/api/pith-number/KQD5CV6X6PJHVG2VR24ORZIB6Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQD5CV6X6PJHVG2VR24ORZIB6Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQD5CV6X6PJHVG2VR24ORZIB6Y/action/storage_attestation","attest_author":"https://pith.science/pith/KQD5CV6X6PJHVG2VR24ORZIB6Y/action/author_attestation","sign_citation":"https://pith.science/pith/KQD5CV6X6PJHVG2VR24ORZIB6Y/action/citation_signature","submit_replication":"https://pith.science/pith/KQD5CV6X6PJHVG2VR24ORZIB6Y/action/replication_record"}},"created_at":"2026-07-05T11:24:26.200509+00:00","updated_at":"2026-07-05T11:24:26.200509+00:00"}