{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EVZ6QCZXHAEY7S6FAL55EHI452","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":"b02a08147e5a7134d50082c40ccc983bcc05ec7673dd39fbd9e6fbf7321c343f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T01:36:18Z","title_canon_sha256":"cf429c6d5f352ddfdfd1bb18e70f316d07985c45750ea3721ecc0625e5b4603d"},"schema_version":"1.0","source":{"id":"2412.08859","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08859","created_at":"2026-07-05T09:48:02Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08859v1","created_at":"2026-07-05T09:48:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08859","created_at":"2026-07-05T09:48:02Z"},{"alias_kind":"pith_short_12","alias_value":"EVZ6QCZXHAEY","created_at":"2026-07-05T09:48:02Z"},{"alias_kind":"pith_short_16","alias_value":"EVZ6QCZXHAEY7S6F","created_at":"2026-07-05T09:48:02Z"},{"alias_kind":"pith_short_8","alias_value":"EVZ6QCZX","created_at":"2026-07-05T09:48:02Z"}],"graph_snapshots":[{"event_id":"sha256:99a995ddf4fca211e35798197c04876772fd73f36ab622289381a94b81922725","target":"graph","created_at":"2026-07-05T09:48:02Z","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/2412.08859/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Programming based approaches to reasoning tasks have substantially expanded the types of questions models can answer about visual scenes. Yet on benchmark visual reasoning data, when models answer correctly, they produce incorrect programs 33% of the time. These models are often right for the wrong reasons and risk unexpected failures on new data. Unit tests play a foundational role in ensuring code correctness and could be used to repair such failures. We propose Visual Unit Testing (ViUniT), a framework to improve the reliability of visual programs by automatically generating unit tests. In ","authors_text":"Artemis Panagopoulou, Caiming Xiong, Chris Callison-Burch, Honglu Zhou, Juan Carlos Niebles, Mark Yatskar, Silvio Savarese","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T01:36:18Z","title":"ViUniT: Visual Unit Tests for More Robust Visual Programming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08859","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":"sha256:75e1f71eda2bb3f0a692ebe998d666e9de231886f92b2889480c658678eb09b7","target":"record","created_at":"2026-07-05T09:48:02Z","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":"b02a08147e5a7134d50082c40ccc983bcc05ec7673dd39fbd9e6fbf7321c343f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T01:36:18Z","title_canon_sha256":"cf429c6d5f352ddfdfd1bb18e70f316d07985c45750ea3721ecc0625e5b4603d"},"schema_version":"1.0","source":{"id":"2412.08859","kind":"arxiv","version":1}},"canonical_sha256":"2573e80b3738098fcbc502fbd21d1cee9abc382ed1b668ecfc417575384ab418","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2573e80b3738098fcbc502fbd21d1cee9abc382ed1b668ecfc417575384ab418","first_computed_at":"2026-07-05T09:48:02.877288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:02.877288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7AMN+squXRLEWnf/blS7aOB6TXZn/tIZTOLnD4I5GsEh/YwQFbtxRLk4kqmOpWKKVq81vzHIqg8hk5a5w61aDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:02.877787Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08859","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75e1f71eda2bb3f0a692ebe998d666e9de231886f92b2889480c658678eb09b7","sha256:99a995ddf4fca211e35798197c04876772fd73f36ab622289381a94b81922725"],"state_sha256":"209c2fa30d1b2e55a3f9e968e6d076985607fb9fc1c20d01b9d65890eb19124d"}