{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z6D3MTFMVJ3EARRDE5WHHSXQW4","short_pith_number":"pith:Z6D3MTFM","schema_version":"1.0","canonical_sha256":"cf87b64cacaa76404623276c73caf0b738bccf0d83a5e9dd2a0b17ec02a0bd79","source":{"kind":"arxiv","id":"2606.00188","version":1},"attestation_state":"computed","paper":{"title":"PaintBench: Deterministic Evaluation of Precise Visual Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.GR","authors_text":"Ellis Brown, He He, Kai Xu, Rob Fergus, Saining Xie, Shrikar Madhu","submitted_at":"2026-05-29T16:01:14Z","abstract_excerpt":"While current multimodal models are proficient at open-ended visual editing, executing precise single-answer edits remains an important obstacle. To probe this challenge, we introduce PaintBench, a dynamically scalable benchmark targeting 20 fundamental precise visual editing operations across four categories: geometric transformation, structural manipulation, color change, and symbolic reasoning. Procedural generation with configurable complexity enables an effectively infinite, contamination-resistant evaluation suite, and deterministic pixel-level evaluation eliminates reliance on bias-pron"},"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":"2606.00188","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2026-05-29T16:01:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"52cd98e7be484a4f475e66b5dda55496cf019914ac51ec82d5d7ad40e1d86e59","abstract_canon_sha256":"9de6d7d4163d7807b81af626779f527bfb9b5d497ce1fd5b7ec996a447fa8080"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:20.940265Z","signature_b64":"OI0cRaCaPWPnDYeDf9T4A7+qMHsyPUWkiRaot2ai/E/ABvvFlADtw9hhIYGt/BHbVyuXbAMTTcMEYeE13SR1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf87b64cacaa76404623276c73caf0b738bccf0d83a5e9dd2a0b17ec02a0bd79","last_reissued_at":"2026-06-02T01:03:20.939890Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:20.939890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PaintBench: Deterministic Evaluation of Precise Visual Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.GR","authors_text":"Ellis Brown, He He, Kai Xu, Rob Fergus, Saining Xie, Shrikar Madhu","submitted_at":"2026-05-29T16:01:14Z","abstract_excerpt":"While current multimodal models are proficient at open-ended visual editing, executing precise single-answer edits remains an important obstacle. To probe this challenge, we introduce PaintBench, a dynamically scalable benchmark targeting 20 fundamental precise visual editing operations across four categories: geometric transformation, structural manipulation, color change, and symbolic reasoning. Procedural generation with configurable complexity enables an effectively infinite, contamination-resistant evaluation suite, and deterministic pixel-level evaluation eliminates reliance on bias-pron"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00188","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/2606.00188/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":"2606.00188","created_at":"2026-06-02T01:03:20.939944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00188v1","created_at":"2026-06-02T01:03:20.939944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00188","created_at":"2026-06-02T01:03:20.939944+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6D3MTFMVJ3E","created_at":"2026-06-02T01:03:20.939944+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6D3MTFMVJ3EARRD","created_at":"2026-06-02T01:03:20.939944+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6D3MTFM","created_at":"2026-06-02T01:03:20.939944+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/Z6D3MTFMVJ3EARRDE5WHHSXQW4","json":"https://pith.science/pith/Z6D3MTFMVJ3EARRDE5WHHSXQW4.json","graph_json":"https://pith.science/api/pith-number/Z6D3MTFMVJ3EARRDE5WHHSXQW4/graph.json","events_json":"https://pith.science/api/pith-number/Z6D3MTFMVJ3EARRDE5WHHSXQW4/events.json","paper":"https://pith.science/paper/Z6D3MTFM"},"agent_actions":{"view_html":"https://pith.science/pith/Z6D3MTFMVJ3EARRDE5WHHSXQW4","download_json":"https://pith.science/pith/Z6D3MTFMVJ3EARRDE5WHHSXQW4.json","view_paper":"https://pith.science/paper/Z6D3MTFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00188&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6D3MTFMVJ3EARRDE5WHHSXQW4/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6D3MTFMVJ3EARRDE5WHHSXQW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6D3MTFMVJ3EARRDE5WHHSXQW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6D3MTFMVJ3EARRDE5WHHSXQW4/action/storage_attestation","attest_author":"https://pith.science/pith/Z6D3MTFMVJ3EARRDE5WHHSXQW4/action/author_attestation","sign_citation":"https://pith.science/pith/Z6D3MTFMVJ3EARRDE5WHHSXQW4/action/citation_signature","submit_replication":"https://pith.science/pith/Z6D3MTFMVJ3EARRDE5WHHSXQW4/action/replication_record"}},"created_at":"2026-06-02T01:03:20.939944+00:00","updated_at":"2026-06-02T01:03:20.939944+00:00"}