{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4MQOPMK6EDPGSKRBXONVNJ3VFQ","short_pith_number":"pith:4MQOPMK6","schema_version":"1.0","canonical_sha256":"e320e7b15e20de692a21bb9b56a7752c19a469a6cbc2a9f5a33ba5c4a39cc06d","source":{"kind":"arxiv","id":"2608.11292","version":1},"attestation_state":"computed","paper":{"title":"Self-Evolving Code-with-Image Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jin Sun, Liangjie Hong, Liang Wu, Mayank Darbari, Ninghao Liu, Ruitong Sun, Tianze Yang, Yanqiao Wang, Yucheng Shi","submitted_at":"2026-08-11T17:14:06Z","abstract_excerpt":"Multimodal models increasingly reach for tools when solving visual tasks (crop, zoom, rotate, brighten), a paradigm known as thinking-with-images. The central challenge is one of perception: tools mostly serve to expose visual evidence, reasoning over that evidence stays in language, and most targets are ones a human could in principle determine by inspection. Some visual questions, however, are not bottlenecked by perception: recovering their answers requires executing a multi-step visual algorithm over the pixels. On such questions a model often names the correct algorithm at once yet still "},"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":"2608.11292","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T17:14:06Z","cross_cats_sorted":[],"title_canon_sha256":"06261ed3b3d57ce198c4c054e34a2b1239abf4ba8401f4385c8c07b01ad7c50c","abstract_canon_sha256":"3b78f1ebd4226d6c0a27ec3307675172242304f98766cd3eef0142c853fcd074"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T00:20:58.716848Z","signature_b64":"+8IRRHAQF8elDfeulG+4Ri422TuqPtq8fYXTQBtszFKx0kRlYDYBOM2wNMaBkVBiP7ibScbzImE6O3Lf0QD9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e320e7b15e20de692a21bb9b56a7752c19a469a6cbc2a9f5a33ba5c4a39cc06d","last_reissued_at":"2026-08-13T00:20:58.706457Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T00:20:58.706457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Evolving Code-with-Image Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jin Sun, Liangjie Hong, Liang Wu, Mayank Darbari, Ninghao Liu, Ruitong Sun, Tianze Yang, Yanqiao Wang, Yucheng Shi","submitted_at":"2026-08-11T17:14:06Z","abstract_excerpt":"Multimodal models increasingly reach for tools when solving visual tasks (crop, zoom, rotate, brighten), a paradigm known as thinking-with-images. The central challenge is one of perception: tools mostly serve to expose visual evidence, reasoning over that evidence stays in language, and most targets are ones a human could in principle determine by inspection. Some visual questions, however, are not bottlenecked by perception: recovering their answers requires executing a multi-step visual algorithm over the pixels. On such questions a model often names the correct algorithm at once yet still "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11292","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/2608.11292/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":"2608.11292","created_at":"2026-08-13T00:20:58.715396+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.11292v1","created_at":"2026-08-13T00:20:58.715396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11292","created_at":"2026-08-13T00:20:58.715396+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MQOPMK6EDPG","created_at":"2026-08-13T00:20:58.715396+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MQOPMK6EDPGSKRB","created_at":"2026-08-13T00:20:58.715396+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MQOPMK6","created_at":"2026-08-13T00:20:58.715396+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/4MQOPMK6EDPGSKRBXONVNJ3VFQ","json":"https://pith.science/pith/4MQOPMK6EDPGSKRBXONVNJ3VFQ.json","graph_json":"https://pith.science/api/pith-number/4MQOPMK6EDPGSKRBXONVNJ3VFQ/graph.json","events_json":"https://pith.science/api/pith-number/4MQOPMK6EDPGSKRBXONVNJ3VFQ/events.json","paper":"https://pith.science/paper/4MQOPMK6"},"agent_actions":{"view_html":"https://pith.science/pith/4MQOPMK6EDPGSKRBXONVNJ3VFQ","download_json":"https://pith.science/pith/4MQOPMK6EDPGSKRBXONVNJ3VFQ.json","view_paper":"https://pith.science/paper/4MQOPMK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.11292&json=true","fetch_graph":"https://pith.science/api/pith-number/4MQOPMK6EDPGSKRBXONVNJ3VFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4MQOPMK6EDPGSKRBXONVNJ3VFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MQOPMK6EDPGSKRBXONVNJ3VFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MQOPMK6EDPGSKRBXONVNJ3VFQ/action/storage_attestation","attest_author":"https://pith.science/pith/4MQOPMK6EDPGSKRBXONVNJ3VFQ/action/author_attestation","sign_citation":"https://pith.science/pith/4MQOPMK6EDPGSKRBXONVNJ3VFQ/action/citation_signature","submit_replication":"https://pith.science/pith/4MQOPMK6EDPGSKRBXONVNJ3VFQ/action/replication_record"}},"created_at":"2026-08-13T00:20:58.715396+00:00","updated_at":"2026-08-13T00:20:58.715396+00:00"}